CN110825897A - Image screening method, device and mobile terminal - Google Patents

Abstract

The present invention provides an image screening method, device and mobile terminal. The method includes: acquiring a set of images to be screened obtained by continuously photographing a shooting object; acquiring scoring features corresponding to the set of images to be screened; The image features corresponding to the features; according to the scoring features and the image features corresponding to each of the images, score each of the images to obtain a score value for each of the images; The target images whose score values are greater than or equal to the score threshold are selected from the set of images to be screened. The present invention can improve the accuracy of image screening.

Description

Image screening method, device and mobile terminal

technical field

The present invention relates to the technical field of image processing, and in particular, to an image screening method, device and mobile terminal.

Background technique

With the rapid development of mobile communication technology, mobile terminals (such as mobile phones, etc.) have become an indispensable part of people's life and work. With the continuous development of the configuration of the mobile terminal, the photographing function of the mobile terminal is becoming more and more powerful.

However, when a user uses a mobile terminal to shoot a large number of pictures, a picture set for the recall video needs to be created, usually several pictures with higher definition are selected as the picture set for creating the recall video according to the definition of the pictures.

But for different people and under different needs, the subjective evaluation of the same image is different, for example, in a dimly lit space, multiple images are taken at the same angle and pose, and the The image needs to be hazy and unclear, but the previous image screening method will only retain the clearest image, and the existing standard for image screening only based on clarity is a relatively objective standard, which may lead to image screening. The result is inaccurate.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide an image screening method, device, and mobile terminal to solve the problem that the picture screening criteria in the prior art are relatively objective criteria, which may lead to inaccurate picture screening results.

In order to solve the above technical problems, the embodiments of the present invention are implemented as follows:

In a first aspect, an embodiment of the present invention provides an image screening method, including: acquiring a set of images to be screened obtained by continuously shooting a photographic object; acquiring a configured scoring feature based on the set of images to be screened; Extracting image features corresponding to the scoring features from each image in the screening image set; scoring each of the images according to the scoring features and the image features corresponding to each of the images to obtain each of the The scoring value of the image; according to each scoring value, select the target image whose scoring value is greater than or equal to the scoring threshold from the set of images to be screened.

In a second aspect, an embodiment of the present invention provides an image screening apparatus, including: an image set acquisition module, configured to acquire a set of images to be screened obtained by continuously shooting objects; a scoring feature acquisition module, configured to obtain an image set based on the Screening an image set to obtain configured scoring features; an image feature extraction module for extracting image features corresponding to the scoring features from each image in the image set to be screened; a scoring value acquisition module for The scoring feature and the image feature corresponding to each of the described images are used to score each of the described images to obtain the scoring value of each of the described images; the target image screening module is used to select from the described scoring values according to each of the scoring values. Target images whose score values are greater than or equal to the score threshold are selected from the set of images to be screened.

In a third aspect, an embodiment of the present invention provides a mobile terminal, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program is executed by the processor When implementing the steps of the image screening method described in any one of the above.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, any one of the image screening methods described above is implemented A step of.

In the embodiment of the present invention, by acquiring the image set to be screened obtained by continuously photographing the shooting object, the scoring feature corresponding to the image set to be screened is obtained, and the score corresponding to the scoring feature is extracted from each image of the image set to be screened. Image features, according to the scoring features and the image features corresponding to each image, score each image to obtain the scoring value of each image, and screen out the image set to be screened according to the scoring value greater than or equal to the scoring threshold. target image. In this embodiment of the present invention, each image is scored by combining scoring features, rather than simply screening out images with higher definition, thereby improving the accuracy of image screening.

Description of drawings

1 is a flow chart of steps of an image screening method provided by an embodiment of the present invention;

FIG. 1a is a schematic diagram of acquiring an image set to be screened according to an embodiment of the present invention;

Fig. 1b is a schematic diagram of a same type of image cleaning function provided by an embodiment of the present invention;

1c is a schematic diagram of a custom screening condition provided by an embodiment of the present invention;

2 is a flowchart of steps of an image screening method provided by an embodiment of the present invention;

3 is a flowchart of steps of an image screening method provided by an embodiment of the present invention;

4 is a flowchart of steps of an image screening method provided by an embodiment of the present invention;

5 is a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention;

6 is a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention;

7 is a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention;

8 is a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention;

FIG. 9 is a structural block diagram of an image screening apparatus provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Example 1

Referring to FIG. 1, a flowchart of steps of an image screening method provided by an embodiment of the present invention is shown, which may specifically include the following steps:

Step 101: Acquire a set of images to be screened obtained by continuously photographing the photographing object.

The embodiments of the present invention can be applied to the solution in which the terminal side screens images of the same type and retains the images desired by the user.

The terminal may be a mobile terminal, such as a mobile electronic device such as a mobile phone and a tablet computer, or a PC (Personal Computer, personal computer) end, such as a desktop computer, a notebook computer, and the like.

The shooting object refers to the object corresponding to the collection of the image set to be screened, and the object to be screened may be a person, a potted plant, a landscape, etc., and specifically, it may be determined according to the actual situation.

The image set to be screened refers to an image set composed of multiple images obtained by continuously shooting the object. The image set to be screened may include 3 images, 5 images, or 8 images, etc. It depends on the situation. For example, referring to FIG. 1a, a schematic diagram of acquiring an image set to be screened provided by an embodiment of the present invention is shown. As shown in FIG. According to the brightness of the object, the images corresponding to the shooting objects are collected according to different sharpnesses, so as to obtain multiple images corresponding to the shooting objects, and the multiple images constitute the image set to be screened.

The image set to be screened may also be an image set composed of multiple images obtained by starting the continuous shooting function built in the terminal, and specifically, it may be determined according to business requirements, which is not specifically limited in this embodiment of the present invention.

In the present invention, the set of images to be screened that needs to be cleaned can be acquired in advance, and then the images in the set of images to be screened can be cleaned up, or after the user triggers the same type of image cleaning function, the user selects an image, and then the terminal according to the user. For the selected image, images of the same type as the selected image are obtained from the images saved in the album, that is, the set of images to be screened is formed.

Step 102 is performed after acquiring the set of images to be screened obtained by continuously photographing the object.

Step 102: Acquire scoring features corresponding to the to-be-screened image set.

Scoring features refer to pre-acquired image features used for scoring each image in the image set to be screened.

The scoring feature can be the image features extracted from these pictures according to the most popular pictures in the shooting scene corresponding to the image set to be screened in the most recent period of time, such as character pose, background, degree of blurring, character angle and so on features.

The scoring feature can also be an image feature customized by the user for each image in the image set to be screened. For example, the user can customize the feature of the image set to be screened according to the features he wants, such as blur, highlight, etc.

Of course, the scoring feature may also be other forms of image features corresponding to the image set to be screened, such as features of a partial area of the image, and so on. The scoring features will be described in detail in the following method embodiments respectively, and details are not described herein again in the embodiments of the present invention.

A “same type of image cleaning” function may be preset in the terminal system. For example, referring to FIG. 1b, a schematic diagram of a same type of image cleaning function provided by an embodiment of the present invention is shown. As shown in FIG. 1b, when the user opens the terminal After the album is displayed, a button of "cleaning up images of the same type" is displayed in the interface, and the user can click this button to trigger the cleaning operation for the images of the same type saved in the album.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

After the image set to be screened is obtained, the scoring feature corresponding to the image set to be screened can be obtained, and the method of obtaining the scoring feature will be described in detail in the following method embodiments respectively, which will not be repeated in this embodiment of the present invention.

Step 103 is performed after obtaining the scoring features corresponding to the image set to be screened.

Step 103: Extract image features corresponding to the scoring features from each image in the to-be-screened image set.

Image features refer to the image features extracted from each image in the to-be-screened image set according to the pre-acquired scoring features corresponding to the to-be-screened image set. The feature of the task pose is extracted from each image of ; and when the scoring feature is a highlight feature, the highlight image feature can be extracted from each image of the image set to be screened.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

The specific implementation process of extracting image features corresponding to scoring features from each image in the image set to be screened will be described in detail in the following method embodiments, which will not be repeated in the embodiments of the present invention.

After the image features corresponding to the scoring features are extracted from each image in the image set to be screened, step 104 is performed.

Step 104: Score each of the images according to the scoring features and the image features corresponding to each of the images, to obtain a scoring value of each of the images.

After the image features of each image are obtained, the image features corresponding to each image can be scored according to the scoring features, so as to obtain the scoring value corresponding to each image. For example, the scoring features include A and B, and the scoring feature A corresponds to The image feature is feature a of image 1, and the image feature corresponding to scoring feature B is feature b of image 1. When scoring image 1, feature a can be scored according to scoring feature A, and feature a can be scored according to scoring feature B. b. Score, and then according to the corresponding weights of the two features, finally get the total score of image 1, that is, the score value of image 1.

It can be understood that the above example is only a solution for obtaining a score value for better understanding of the technical solutions of the embodiments of the present invention. In practical applications, those skilled in the art can also obtain the score of the image in other ways. value, which is not limited in this embodiment of the present invention.

Step 105 is performed after each image is scored according to the scoring feature and the image feature corresponding to each image to obtain the scoring value of each image.

Step 105 : According to each of the scoring values, screen out the target images whose scoring values are greater than or equal to the scoring threshold from the set of images to be screened.

The scoring threshold refers to a score preset by business personnel for saving images, and the scoring threshold may be 0.5, 0.6, 0.8, etc. Specifically, it may be determined according to business requirements, which is not limited in this embodiment of the present invention.

The target image refers to the image whose score value is greater than or equal to the score threshold in the image set to be screened.

After obtaining the score value of each image in the image set to be screened, the score value of each image in the image set to be screened can be compared with the score threshold, so that target images with a score value greater than the score threshold can be screened from the image set to be screened , for example, image set A to be screened contains image 1, image 2, image 3 and image 4, the score threshold is 0.5, the score value of image 1 is 0.4, the score value of image 2 is 0.8, and the score value of image 3 is 0.9 , the score value of image 4 is 0.5, then the target images in A are image 2 and image 3.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

After the target image is screened out from the set of images to be screened, the target image can also be saved and other images are cleared. Specifically, a detailed description is given in conjunction with the following preferred embodiments.

In a preferred embodiment of the present invention, after the above step 105, it may further include:

Step S: Save the target image, and delete other images in the to-be-screened image set except the target image.

In this embodiment of the present invention, after a target image whose score value is greater than or equal to the score threshold is selected from the set of images to be screened, the target image can be saved in the system album, and other images other than the target image in the set of images to be screened can be saved. Images are removed from the album. For example, if the image set to be screened contains image a, image b, image c, image d, and image e, where image a and image c are target images, after scoring, image a and image c Save in the album, and clear image b, image d and image e from the album.

The embodiments of the present invention can enable users to score similar photos according to user-defined requirements or cloud big data, filter photos according to the scores, keep the photos they most want, delete other redundant photos, and save the system memory space. occupied.

In the image screening method provided by the embodiment of the present invention, by acquiring the to-be-screened image set obtained by continuously photographing the shooting object, obtaining the scoring feature corresponding to the to-be-screened image set, and extracting and scoring from each image of the to-be-screened image set The image features corresponding to the features, score each image according to the scoring features and the image features corresponding to each image, and obtain the scoring value of each image. Target image for scoring threshold. In this embodiment of the present invention, each image is scored by combining scoring features, rather than simply screening out images with higher definition, thereby improving the accuracy of image screening.

Embodiment 2

Referring to FIG. 2, a flowchart of steps of an image screening method provided by an embodiment of the present invention is shown, which may specifically include the following steps:

Step 201: Acquire a set of images to be screened obtained by continuously photographing the photographing object.

In this embodiment of the present invention, the specific implementation of step 201 is similar to the implementation of step 101 in the above-mentioned first embodiment. For the specific implementation process, reference may be made to the above description of step 101, which is not repeated in this embodiment of the present invention.

Step 202: Determine a shooting scene corresponding to the shooting object according to the to-be-screened image set.

The shooting scene refers to the scene in which the to-be-screened image set is obtained when the subject is photographed, and the shooting scene may include indoor, outdoor, night, day, etc., and may specifically be determined according to the actual situation.

After obtaining the image set to be screened, the shooting scene when shooting the object can be determined according to a plurality of images in the image set to be screened. For example, as shown in FIG. The shooting scene corresponding to the shooting object (ie, the potted plant) is an indoor scene.

After the shooting scene corresponding to the shooting object is determined, step 203 is executed.

Step 203 : From a pre-stored image library, obtain a matching image whose heat value is greater than the heat value threshold and matches the shooting scene.

The image library refers to a preset database for storing images, and multiple images of different shooting objects in multiple scenes are stored in the image library.

It can be understood that the image library may be a database preset on the terminal side, or a database set on the cloud, and specifically, it may be determined according to business requirements.

The hotness value refers to the value corresponding to the hotness attribute of the image, and the hotness value can be used to represent the hotness attribute of the image in a recent period of time, that is, the degree to which the image is liked by the user.

The hotness threshold refers to the threshold corresponding to the hotness value of the image preset by the business personnel. When the hotness value of the image is greater than the hotness threshold, it means that the image is highly favored by users at the current stage. At this stage, it is less popular with users.

A matching image refers to an image whose heat value obtained from the image library is greater than the heat threshold and matches the shooting scene.

After obtaining the shooting scene corresponding to the shooting object, a plurality of matching images can be obtained from the image library according to the shooting scene, and then according to the heat value corresponding to the multiple images, matching images with a heat value greater than a heat threshold value are screened out.

Step 204 is performed after obtaining a matching image from the pre-stored image library whose heat value is greater than the heat value threshold and matches the shooting scene.

Step 204: Extract the first scoring feature in the matching image.

The first scoring feature refers to a feature for scoring each image in the image set to be screened, and the first scoring feature may be features such as character pose, background, degree of blurring, character angle, and the like.

After obtaining the matching image corresponding to the image set to be screened, the first scoring feature can be extracted from the matching image. For example, as shown in Fig. 1a, when the scene of the subject is an indoor scene, the indoor scene can be obtained from the image library In the scenario, there are multiple matching images whose heat value is greater than the heat value threshold, and then corresponding image features are extracted from these matching images as the first scoring feature.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

After extracting the first scoring feature in the matching image, step 205 is performed.

Step 205: Extract a first image feature corresponding to the first scoring feature from each of the images.

The first image feature refers to the image feature corresponding to the first scoring feature extracted from each image of the to-be-screened image set. For example, when the first scoring feature corresponding to the to-be-screened image set is a person pose, the The first image feature containing the pose of the person is extracted from each image of the image set to be screened; and when the first scoring feature corresponding to the image set to be screened is the background, the background of each image can be extracted from each image feature as the first image feature.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

After the first scoring feature corresponding to the set of images to be screened is extracted from the matching images, the first image feature corresponding to the first scoring feature may be extracted from each image of the set of images to be screened, and then step 206 is performed.

Step 206: Compare the first image feature corresponding to each of the images with the first scoring feature to obtain a comparison result.

After obtaining the first image feature and the first scoring feature, for each image in the images to be screened, the first image feature and the first scoring feature of each image can be compared to obtain a comparison result, for example, image A The first image features are a and b, and the corresponding first scoring features are feature 1 and feature 2, respectively, then a and feature 1 can be compared, and b and feature 2 can be compared to obtain two results, which are used as the Comparing results.

After the comparison result is obtained, step 207 is executed.

Step 207: According to the comparison result, determine the score value of each of the images.

After the comparison result is obtained, the scoring value of each image can be determined according to the comparison result between the first image feature and the first scoring feature. It is understandable that the technology for obtaining the scoring value by feature comparison is a relatively mature technology in the field. , the specific manner of how to determine the score value of the image according to the comparison result will not be described in detail in this embodiment of the present invention.

Of course, when there are multiple first scoring features, there are also multiple first image features, then when obtaining the scoring value, the final scoring value can be calculated according to the weight corresponding to each first image feature. A scoring feature is a and b, the corresponding first image features are feature 1 and feature 2 respectively, the weight of feature 1 is 0.3, the weight of feature 2 is 0.5, the score value obtained by comparing a and feature 1 is 0.5, b The score obtained by comparing with feature 2 is 0.8, then the final score is 0.5*0.3+0.5*0.8=0.55.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

In specific implementation, when there are multiple first image features and first scoring features, when calculating the scoring value of an image, the calculation may also be performed with reference to other methods, which is not limited in this embodiment of the present invention.

After the rating value of each image is determined according to the comparison result, step 208 is performed.

Step 208: According to each of the score values, screen out the target images whose score values are greater than or equal to the score threshold from the set of images to be screened.

In the present invention, the specific implementation of step 208 is similar to the implementation of step 105 in the above-mentioned first embodiment, and the specific implementation process can refer to the above description of step 105, which is not repeated in this embodiment of the present invention.

The embodiments of the present invention screen photos based on big data. Since images with high popularity represent current people's aesthetic viewpoints, the accuracy of image scoring can be improved.

The image screening method provided by the embodiment of the present invention, in addition to having the beneficial effects of the image screening method provided by the above-mentioned first embodiment, can also combine the pre-stored scoring features of images with higher heat values to score each image, which can improve the Real-time and accurate image scoring.

Embodiment 3

Referring to FIG. 3, a flowchart of steps of an image screening method provided by an embodiment of the present invention is shown, which may specifically include the following steps:

Step 301: Acquire a set of images to be screened obtained by continuously photographing the photographing object.

In this embodiment of the present invention, the specific implementation of step 301 is similar to the implementation of step 101 in the above-mentioned first embodiment, and the specific implementation process can refer to the above description of step 101, which is not repeated in this embodiment of the present invention.

Step 302: Acquire a second scoring feature set by the user for the to-be-screened image set, and a first scoring weight corresponding to the second scoring feature.

The second scoring feature refers to a feature that is customized by the user for the image set to be screened and used to score images. The second scoring feature may be a highlight feature, a blur feature, etc. set by the user. Depends.

The first scoring weight refers to a weight corresponding to the second scoring feature set by the user.

A user-defined feature function is preset in the system. When the user executes this function, the required second scoring feature and the first scoring weight corresponding to the second scoring feature can be set. For example, referring to FIG. A schematic diagram of a custom filter condition provided by an embodiment of the present invention is shown. As shown in Figure 1c, when the user opens an album, a button of "filter condition" is displayed in the interface. After the user obtains the image set to be filtered, You can click the "Filter Condition" button to trigger the function of customizing filter conditions. Then, the user can set filter conditions (ie, the second scoring feature) for the image set to be filtered, such as automatic, highlight, dim, blur and other features.

Of course, after setting the second scoring feature, the user may also set a corresponding first scoring weight for the second scoring feature.

After acquiring the second scoring feature set by the user for the image set to be screened, and the first scoring weight corresponding to the second scoring feature, step 303 is performed.

Step 303: Extract a second image feature corresponding to the second scoring feature from each of the images.

The second image feature refers to an image feature corresponding to the second scoring feature in each image of the image set to be screened.

After acquiring the second scoring feature set by the user for the image set to be screened, a second image feature corresponding to the second scoring feature may be extracted from each image in the image set to be screened.

After the second image feature is extracted from each image, step 304 is performed.

Step 304: According to the second scoring feature, score the second image feature corresponding to each of the images to obtain a first initial scoring value corresponding to each of the second image features.

The first initial scoring value refers to a scoring value obtained by scoring the second image feature according to the second scoring feature.

After the second image feature is extracted from each image, the second image feature may be scored according to the second scoring feature, so as to obtain a first initial scoring value corresponding to each second image feature.

After obtaining the first initial score value corresponding to each second image feature, step 305 is performed.

Step 305: Calculate the score value of each of the images according to each of the first initial score values and each of the first score weights.

After obtaining the first initial score value corresponding to the second image feature of each image and the first score weight corresponding to each second score feature, the first initial score value corresponding to each image and the first score value can be combined The scoring weight is calculated to obtain the scoring value of each image. For example, the first initial scoring value corresponding to image A is 0.7, and the first scoring weight is 0.8, then the scoring value of image A is 0.7*0.8=0.56.

Of course, for each image, there can be multiple second scoring features set by the user for each image, so the extracted second image features should also be multiple, and each second scoring feature corresponds to a scoring weight , when calculating, the calculation is performed according to the first initial scoring value and the first scoring weight of each second image feature. For example, the second scoring features set by the user for image B are a and b, and the corresponding first scoring weight are 0.5 and 0.6, and the corresponding second image features are feature 1 and feature 2. After scoring feature 1 with a, the obtained first initial score is 0.8, and after scoring with b corresponding to feature 2, the obtained The first initial score value is 0.5, then the final score value of image B is 0.5*0.8+0.6*0.5=0.7.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

Step 306 is executed after the score value of each image is calculated according to each first initial score value and each first score weight.

Step 306 : According to each of the score values, screen out the target images whose score values are greater than or equal to the score threshold from the set of images to be screened.

In the present invention, the specific implementation of step 306 is similar to the implementation of step 105 in the above-mentioned first embodiment, and the specific implementation process can refer to the above description of step 105, which is not repeated in this embodiment of the present invention.

The embodiment of the present invention can increase the subjective will of the user by combining the user-defined scoring feature, rather than only the objective scoring of the terminal, and can try to retain the image that the user wants to save.

The image screening method provided by the embodiment of the present invention, in addition to having the beneficial effects of the image screening method provided in the first embodiment, can also score images according to user-defined scoring features and scoring weights, and screen images according to the scores, Thereby, the user can retain the desired image.

Embodiment 4

Referring to FIG. 4 , a flowchart of steps of an image screening method provided by an embodiment of the present invention is shown, which may specifically include the following steps:

Step 401: Acquire a set of images to be screened obtained by continuously photographing the photographing object.

In this embodiment of the present invention, the specific implementation of step 401 is similar to the implementation of step 101 in the above-mentioned first embodiment. For the specific implementation process, reference may be made to the above description of step 101, which is not repeated in this embodiment of the present invention.

Step 402: Obtain the image scoring area selected by the user for each of the images.

The image scoring area refers to the area selected by the user for scoring each image in the image set to be screened. For example, if the user selects the upper half of the image as the scoring area, the upper half of the image is the image scoring area; or the user selects the left half of the image as the scoring area, then the left half of the image is the image scoring area; of course, the image scoring area can also be the characters or green plants in the image selected by the user The area where the object is located.

After acquiring the image set to be screened, the user can select a corresponding image scoring area for each image in the image set to be screened. It is understood that the image scoring area selected by the user for each image in the image set to be screened can be the same area For example, the region where the person is located is selected as the image scoring region, or the upper half of the image is selected as the image scoring region, and so on.

Step 403 is performed after acquiring the image scoring area selected by the user for each image.

Step 403: Acquire a third scoring feature set by the user for each of the image scoring regions, and a second scoring weight corresponding to the third scoring feature.

The third scoring feature refers to a feature set by the user for scoring each image scoring area, and the third scoring feature is a user-defined feature, which can be a highlight feature, a blur feature, etc. Specifically, it can be It depends on the actual situation.

The second scoring weight refers to the weight set by the user for the third scoring feature.

After acquiring the image scoring area selected by the user for each image, the user may also set a corresponding third scoring feature for the image scoring area, and the user may set a corresponding scoring weight for the third scoring feature.

For a specific setting process, reference may be made to the description of step 302 in the third embodiment above, which is not repeated in this embodiment of the present invention.

After acquiring the third scoring feature set by the user for each image scoring region, and the second scoring weight corresponding to the third scoring feature, step 404 is executed.

Step 404: Extract the regional image feature corresponding to the third scoring feature from the image scoring region corresponding to each of the images.

The regional image feature refers to the image feature corresponding to the third scoring feature in the image scoring region of each image.

After acquiring the third scoring feature set by the user for each image scoring region, the corresponding regional image feature may be extracted from the image scoring region of each image according to the third scoring feature.

Step 405 is executed after the region image feature corresponding to the third scoring feature is extracted from the image scoring region corresponding to each image.

Step 405: For each of the image scoring regions, score the region image features according to the third scoring feature to obtain a second initial scoring value.

The second initial scoring value refers to a scoring value obtained by scoring the regional image feature according to the third scoring feature.

After extracting the regional image feature corresponding to the third scoring feature from the image scoring region corresponding to each image, for the image scoring region of each image, the image may be scored according to the third scoring feature corresponding to the image scoring region. The region image features corresponding to the scoring region are scored to obtain a second initial scoring value.

After the second initial score value is obtained, step 406 is performed.

Step 406 : According to the second initial score value and the second score weight, calculate and obtain the regional score value corresponding to the image scoring region, and use the regional score value as the score value of the image.

The region scoring value refers to the scoring value obtained by scoring the image scoring region of each image.

After obtaining the second initial scoring value corresponding to the regional image feature of each image and the second scoring weight corresponding to each third scoring feature, the second initial scoring value and the second scoring weight corresponding to each image can be combined , and calculate the score value of each image. For example, if the second initial score value corresponding to image A is 0.7 and the second score weight is 0.8, then the score value of image A is 0.7*0.8=0.56.

Of course, for each image, there may be multiple third scoring features set by the user for the image scoring area of each image, then there should also be multiple extracted regional image features, and each third scoring feature corresponds to A second scoring weight is calculated according to the second initial scoring value and the second scoring weight of the image features of each region. For example, the third scoring features set by the user for image B are a and b, corresponding to The second scoring weights are 0.5 and 0.6, and the corresponding regional image features are feature 1 and feature 2. After scoring feature 1 with a, the obtained second initial scoring value is 0.8. After scoring with b corresponding to feature 2 , the obtained second initial score value is 0.5, then the final score value of image B is 0.5*0.8+0.6*0.5=0.7.

It can be understood that the above examples are only examples listed for better understanding of the technical solutions of the embodiments of the present invention, and are not used as the only limitations on the embodiments of the present invention.

Of course, for an image, it can also include two or more image scoring regions, then after obtaining the regional scoring value of each image scoring region, these region scoring values can be added to obtain the final score of the image value.

After calculating the regional score value corresponding to the image scoring region according to the second initial scoring value and the second scoring weight, and using the regional scoring value as the scoring value of the image, step 407 is performed.

Step 407 : According to each of the score values, screen out the target images whose score values are greater than or equal to the score threshold from the set of images to be screened.

In the present invention, the specific implementation of step 407 is similar to the implementation of step 105 in the above-mentioned first embodiment, and the specific implementation process can refer to the above description of step 105, which is not repeated in this embodiment of the present invention.

The embodiment of the present invention combines the user-defined scoring features for a part of the image, which can increase the user's subjective will rather than only the terminal's objective scoring, and can try to retain the image features that the user wants to save.

The image screening method provided in this embodiment of the present invention, in addition to the beneficial effects of the image screening method provided in the first embodiment, can also allow the user to select regions and features in the image that need to be scored, and then score the image. The user's subjective will selects the image that needs to be saved, so that the user's desired image can be retained.

Embodiment 5

Referring to FIG. 5 , a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention is shown, which may specifically include the following modules:

An image set obtaining module 510, configured to obtain a set of images to be screened obtained by continuously shooting the shooting object;

a scoring feature obtaining module 520, configured to obtain scoring features corresponding to the to-be-screened image set;

an image feature extraction module 530, configured to extract image features corresponding to the scoring features from each image in the to-be-screened image set;

a scoring value obtaining module 540, configured to score each of the images according to the scoring features and the image features corresponding to each of the images, to obtain a scoring value of each of the images;

The target image screening module 550 is configured to screen out target images whose score values are greater than or equal to the score threshold from the set of images to be screened according to each of the score values.

Preferably, the device further comprises:

An image processing module, configured to save the target image and delete other images except the target image in the set of images to be screened.

The image screening device provided by the embodiment of the present invention obtains the to-be-screened image set obtained by continuously photographing the object, obtains the scoring feature corresponding to the to-be-screened image set, and extracts and scores from each image of the to-be-screened image set. The image features corresponding to the features, score each image according to the scoring features and the image features corresponding to each image, and obtain the scoring value of each image. Target image for scoring threshold. In the embodiment of the present invention, each image is scored by using a preconfigured scoring feature, instead of simply screening out images with higher definition, so that the accuracy of image screening can be improved.

Embodiment 6

Referring to FIG. 6, a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention is shown, which may specifically include the following modules:

An image set obtaining module 610, configured to obtain a set of images to be screened obtained by continuously shooting the shooting object;

a scoring feature obtaining module 620, configured to obtain scoring features corresponding to the to-be-screened image set;

An image feature extraction module 630, configured to extract image features corresponding to the scoring features from each image of the to-be-screened image set;

a scoring value obtaining module 640, configured to score each of the images according to the scoring features and the image features corresponding to each of the images, to obtain a scoring value of each of the images;

The target image screening module 650 is configured to screen out target images whose score values are greater than or equal to the score threshold from the set of images to be screened according to each of the score values.

Preferably, the scoring feature acquisition module 620 includes:

A shooting scene determination sub-module 621, configured to determine the shooting scene corresponding to the shooting object according to the to-be-screened image set;

A matching image acquisition sub-module 622, configured to acquire, from a pre-stored image library, a matching image whose heat value is greater than the heat threshold and matches the shooting scene;

The first feature extraction sub-module 623 is used to extract the first scoring feature in the matching image;

The image feature extraction module 630 includes:

The first image feature extraction sub-module 631 is used to extract the first image feature corresponding to the first scoring feature from each of the images;

The scoring value obtaining module 640 includes:

The comparison result acquisition sub-module 641 is used to compare the first image feature corresponding to each of the images with the first scoring feature to obtain a comparison result;

The first score obtaining sub-module 642 is configured to determine the score value of each of the images according to the comparison result.

In addition to the beneficial effects of the image screening device provided in the fifth embodiment of the present invention, the image screening device provided by the embodiment of the present invention can also score each image in combination with the scoring feature of pre-stored images with higher heat values. Improve the real-time and accuracy of image scoring.

Embodiment 7

Referring to FIG. 7 , a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention is shown, which may specifically include the following modules:

An image set obtaining module 710, configured to obtain a set of images to be screened obtained by continuously shooting the shooting object;

a scoring feature obtaining module 720, configured to obtain scoring features corresponding to the to-be-screened image set;

An image feature extraction module 730, configured to extract an image feature corresponding to the scoring feature from each image of the to-be-screened image set;

a scoring value obtaining module 740, configured to score each of the images according to the scoring features and the image features corresponding to each of the images, to obtain a scoring value of each of the images;

The target image screening module 750 is configured to screen out target images whose score values are greater than or equal to a score threshold from the set of images to be screened according to each of the score values.

Preferably, the scoring feature acquisition module 720 includes:

The second feature setting sub-module 721 is configured to acquire the second scoring feature set by the user for the to-be-screened image set, and the first scoring weight corresponding to the second scoring feature;

The image feature extraction module 730 includes:

A second image feature extraction sub-module 731, configured to extract a second image feature corresponding to the second scoring feature from each of the images;

The scoring value obtaining module 740 includes:

The first initial score acquisition sub-module 741 is configured to score the second image features corresponding to each of the images according to the second scoring features, and obtain a first initial score value corresponding to each of the second image features ;

The second score obtaining sub-module 742 is configured to calculate and obtain the score value of each of the images according to each of the first initial score values and each of the first score weights.

In addition to the beneficial effects of the image screening device provided in the fifth embodiment of the present invention, the image screening device provided by the embodiment of the present invention can also score images according to user-defined scoring features and scoring weights, and screen images according to the scores. Thereby, the user can retain the desired image.

Embodiment 8

Referring to FIG. 8, a schematic structural diagram of an image screening apparatus provided by an embodiment of the present invention is shown, which may specifically include the following modules:

An image set obtaining module 810, configured to obtain a set of images to be screened obtained by continuously shooting the shooting object;

a scoring feature obtaining module 820, configured to obtain scoring features corresponding to the to-be-screened image set;

An image feature extraction module 830, configured to extract image features corresponding to the scoring features from each image in the to-be-screened image set;

a scoring value obtaining module 840, configured to score each of the images according to the scoring features and the image features corresponding to each of the images, to obtain a scoring value of each of the images;

The target image screening module 850 is configured to screen out target images whose score values are greater than or equal to a score threshold from the set of images to be screened according to each of the score values.

Preferably, the scoring feature acquisition module 820 includes:

The scoring area setting sub-module 821 is used to obtain the image scoring area selected by the user for each of the images;

A third feature extraction sub-module 822, configured to obtain a third scoring feature set by the user for each of the image scoring regions, and a second scoring weight corresponding to the third scoring feature;

The image feature extraction module 830 includes:

The regional feature extraction sub-module 831 is used to extract the regional image feature corresponding to the third scoring feature from the image scoring region corresponding to each of the images;

The scoring value obtaining module 840 includes:

The second initial score obtaining sub-module 841 is configured to, for each of the image scoring regions, score the image features of the region according to the third scoring feature to obtain a second initial scoring value;

The third score obtaining sub-module 842 is configured to calculate and obtain the regional score value corresponding to the image score region according to the second initial score value and the second score weight, and use the regional score value as the score of the image. rating value.

In addition to the beneficial effects of the image screening device provided in the fifth embodiment of the present invention, the image screening device provided by the embodiment of the present invention can also allow the user to select regions and features in the image that need to be scored, and then score the image, which can The image to be saved is selected according to the user's subjective wishes, so that the image desired by the user can be retained.

Embodiment 9

Referring to FIG. 9 , it is a schematic diagram of a hardware structure of a mobile terminal for implementing various embodiments of the present invention.

The mobile terminal 900 includes but is not limited to: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909, a processor 910, and Power 911 and other components. Those skilled in the art can understand that the structure of the mobile terminal shown in FIG. 9 does not constitute a limitation on the mobile terminal, and the mobile terminal may include more or less components than the one shown, or combine some components, or different components layout. In this embodiment of the present invention, the mobile terminal includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palmtop computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.

The processor 910 is configured to obtain a set of images to be screened obtained by continuously photographing the object; obtain scoring features corresponding to the set of images to be screened; and extract from each image of the set of images to be screened The image features corresponding to the scoring features; according to the scoring features and the image features corresponding to each of the images, score each of the images to obtain a scoring value of each of the images; according to the scoring values, from The target images whose score value is greater than or equal to the score threshold value are selected from the set of images to be screened.

In the embodiment of the present invention, by acquiring the image set to be screened obtained by continuously photographing the shooting object, the scoring feature corresponding to the image set to be screened is obtained, and the score corresponding to the scoring feature is extracted from each image of the image set to be screened. Image features: According to the scoring features and the image features corresponding to each image, score each image to obtain the scoring value of each image, and screen out the target image whose score value is greater than the scoring threshold from the image set to be screened according to each scoring value. . In the embodiment of the present invention, each image is scored by using a preconfigured scoring feature, instead of simply screening out images with higher definition, so that the accuracy of image screening can be improved.

It should be understood that, in this embodiment of the present invention, the radio frequency unit 901 can be used for receiving and sending signals during sending and receiving of information or during a call. Specifically, after receiving the downlink data from the base station, it is processed by the processor 910; The uplink data is sent to the base station. Generally, the radio frequency unit 901 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 901 can also communicate with the network and other devices through a wireless communication system.

The mobile terminal provides the user with wireless broadband Internet access through the network module 902, such as helping the user to send and receive emails, browse web pages, access streaming media, and the like.

The audio output unit 903 may convert audio data received by the radio frequency unit 901 or the network module 902 or stored in the memory 909 into audio signals and output as sound. Also, the audio output unit 903 may also provide audio output related to a specific function performed by the mobile terminal 900 (eg, call signal reception sound, message reception sound, etc.). The audio output unit 903 includes a speaker, a buzzer, a receiver, and the like.

The input unit 904 is used to receive audio or video signals. The input unit 904 may include a graphics processor (Graphics Processing Unit, GPU) 9041 and a microphone 9042, and the graphics processor 9041 captures images of still pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode data is processed. The processed image frames may be displayed on the display unit 906 . The image frames processed by the graphics processor 9041 may be stored in the memory 909 (or other storage medium) or transmitted via the radio frequency unit 901 or the network module 902 . The microphone 9042 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via the radio frequency unit 901 for output in the case of a telephone call mode.

The mobile terminal 900 also includes at least one sensor 905, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 9061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 9061 and the proximity sensor when the mobile terminal 900 is moved to the ear. / or backlight. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (usually three axes), and can detect the magnitude and direction of gravity when stationary, and can be used to identify the posture of mobile terminals (such as horizontal and vertical screen switching, related games , magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; the sensor 905 may also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, Infrared sensors, etc., are not repeated here.

The display unit 906 is used to display information input by the user or information provided to the user. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

The user input unit 907 may be used to receive input numerical or character information, and generate key signal input related to user settings and function control of the mobile terminal. Specifically, the user input unit 907 includes a touch panel 9071 and other input devices 9072 . The touch panel 9071, also referred to as a touch screen, can collect touch operations by the user on or near it (such as the user's finger, stylus, etc., any suitable object or accessory on or near the touch panel 9071). operate). The touch panel 9071 may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the touch controller. To the processor 910, the command sent by the processor 910 is received and executed. In addition, the touch panel 9071 can be realized by various types of resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 9071 , the user input unit 907 may also include other input devices 9072 . Specifically, other input devices 9072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.

Further, the touch panel 9071 can be overlaid on the display panel 9061. When the touch panel 9071 detects a touch operation on or near it, it transmits it to the processor 910 to determine the type of the touch event, and then the processor 910 determines the type of the touch event according to the touch The type of event provides a corresponding visual output on the display panel 9061. Although in FIG. 9, the touch panel 9071 and the display panel 9061 are used as two independent components to realize the input and output functions of the mobile terminal, in some embodiments, the touch panel 9071 and the display panel 9061 may be integrated The input and output functions of the mobile terminal are implemented, which is not specifically limited here.

The interface unit 908 is an interface for connecting an external device to the mobile terminal 900 . For example, external devices may include wired or wireless headset ports, external power (or battery charger) ports, wired or wireless data ports, memory card ports, ports for connecting devices with identification modules, audio input/output (I/O) ports, video I/O ports, headphone ports, and more. The interface unit 908 may be used to receive input (eg, data information, power, etc.) from an external device and transmit the received input to one or more elements within the mobile terminal 900 or may be used between the mobile terminal 900 and the external Transfer data between devices.

The memory 909 may be used to store software programs as well as various data. The memory 909 may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of the mobile phone (such as audio data, phone book, etc.), etc. Additionally, memory 909 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The processor 910 is the control center of the mobile terminal, uses various interfaces and lines to connect various parts of the entire mobile terminal, runs or executes the software programs and/or modules stored in the memory 909, and calls the data stored in the memory 909. , perform various functions of the mobile terminal and process data, so as to monitor the mobile terminal as a whole. The processor 910 may include one or more processing units; preferably, the processor 910 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem The processor mainly handles wireless communication. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 910.

The mobile terminal 900 may also include a power supply 911 (such as a battery) for supplying power to various components. Preferably, the power supply 911 may be logically connected to the processor 910 through a power management system, so as to manage charging, discharging, and power consumption management through the power management system. and other functions.

In addition, the mobile terminal 900 includes some functional modules not shown, which will not be repeated here.

Preferably, an embodiment of the present invention further provides a mobile terminal, including a processor 910 , a memory 909 , a computer program stored in the memory 909 and running on the processor 910 , when the computer program is executed by the processor 910 The various processes of the above image screening method embodiments are implemented, and the same technical effect can be achieved. In order to avoid repetition, details are not repeated here.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above image screening method embodiments can be implemented, and the same technology can be achieved. The effect, in order to avoid repetition, is not repeated here. The computer-readable storage medium is, for example, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk, or an optical disk.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of the present invention, without departing from the spirit of the present invention and the scope protected by the claims, many forms can be made, which all belong to the protection of the present invention.

Claims (12)

1. an image screening method, is characterized in that, comprises: Obtain a set of images to be screened obtained by continuously shooting the subject; obtaining the scoring feature corresponding to the set of images to be screened; extracting image features corresponding to the scoring features from each image of the to-be-screened image set; According to the scoring feature and the image feature corresponding to each of the images, scoring each of the images to obtain a scoring value of each of the images; According to each of the scoring values, a target image with a scoring value greater than or equal to a scoring threshold is selected from the set of images to be screened. 2. The method according to claim 1, wherein the step of acquiring the scoring feature corresponding to the set of images to be screened comprises: determining the shooting scene corresponding to the shooting object according to the to-be-screened image set; From a pre-stored image library, obtain a matching image whose heat value is greater than the heat value threshold and matches the shooting scene; extracting the first scoring feature in the matched image; The step of extracting image features corresponding to the scoring features from each image in the set of images to be screened includes: extracting a first image feature corresponding to the first scoring feature from each of the images; The step of scoring each of the images according to the scoring features and the image features corresponding to each of the images, and obtaining the scoring value of each of the images, includes: Comparing the first image feature corresponding to each of the images with the first scoring feature to obtain a comparison result; Based on the comparison results, a rating value for each of the images is determined. 3. The method according to claim 1, wherein the step of acquiring the scoring feature corresponding to the set of images to be screened comprises: Acquiring the second scoring feature set by the user for the to-be-screened image set, and the first scoring weight corresponding to the second scoring feature; The step of extracting image features corresponding to the scoring features from each image of the to-be-screened image set includes: extracting a second image feature corresponding to the second scoring feature from each of the images; The step of scoring each of the images according to the scoring features and the image features corresponding to each of the images, and obtaining the scoring value of each of the images, includes: According to the second scoring feature, scoring the second image feature corresponding to each of the images to obtain a first initial scoring value corresponding to each of the second image features; According to each of the first initial score values and each of the first score weights, a score value of each of the images is calculated. 4. The method according to claim 1, wherein the step of acquiring the scoring feature corresponding to the set of images to be screened comprises: obtaining an image scoring area selected by the user for each of said images; Obtain the third scoring feature set by the user for each of the image scoring regions, and the second scoring weight corresponding to the third scoring feature; The step of extracting image features corresponding to the scoring features from each image in the set of images to be screened includes: From the image scoring region corresponding to each of the images, extracting the region image feature corresponding to the third scoring feature; The step of scoring each of the images according to the scoring features and the image features corresponding to each of the images, and obtaining the scoring value of each of the images, includes: For each of the image scoring regions, the region image features are scored according to the third scoring feature to obtain a second initial scoring value; According to the second initial scoring value and the second scoring weight, a regional scoring value corresponding to the image scoring region is calculated and obtained, and the regional scoring value is used as the scoring value of the image. 5. The method according to claim 1, characterized in that, after the step of screening out target images with a score value greater than a score threshold from the set of images to be screened according to each of the score values, further comprising: The target image is saved, and other images other than the target image in the set of images to be screened are deleted. 6. An image screening device, comprising: an image set acquisition module, used for acquiring the to-be-screened image set obtained by continuously shooting the shooting object; a scoring feature acquisition module, configured to obtain scoring features corresponding to the to-be-screened image set; an image feature extraction module for extracting image features corresponding to the scoring features from each image in the to-be-screened image set; a scoring value acquisition module, configured to score each of the images according to the scoring feature and the image feature corresponding to each of the images, to obtain a scoring value of each of the images; A target image screening module, configured to screen out target images with a score greater than or equal to a score threshold from the set of images to be screened according to each of the score values. 7. The device according to claim 6, wherein the scoring feature acquisition module comprises: a shooting scene determination submodule, configured to determine the shooting scene corresponding to the shooting object according to the to-be-screened image set; A matching image acquisition sub-module, used for acquiring a matching image whose heat value is greater than the heat value threshold and matches the shooting scene from a pre-stored image library; a first feature extraction submodule for extracting the first scoring feature in the matching image; The image feature extraction module includes: a first image feature extraction sub-module for extracting a first image feature corresponding to the first scoring feature from each of the images; The scoring value acquisition module includes: a comparison result acquisition submodule, configured to compare the first image feature corresponding to each of the images with the first scoring feature to obtain a comparison result; The first score acquisition sub-module is configured to determine the score value of each of the images according to the comparison result. 8. The apparatus according to claim 6, wherein the scoring feature acquisition module comprises: The second feature setting submodule is used to obtain the second scoring feature set by the user for the to-be-screened image set, and the first scoring weight corresponding to the second scoring feature; The image feature extraction module includes: A second image feature extraction submodule, configured to extract a second image feature corresponding to the second scoring feature from each of the images; The scoring value acquisition module includes: a first initial score acquisition sub-module, configured to score the second image feature corresponding to each of the images according to the second scoring feature, to obtain a first initial score value corresponding to each of the second image features; The second score obtaining sub-module is configured to calculate and obtain the score value of each of the images according to each of the first initial score values and each of the first score weights. 9. The apparatus according to claim 6, wherein the scoring feature acquisition module comprises: A scoring area setting sub-module for obtaining the image scoring area selected by the user for each of the images; A third feature extraction sub-module, configured to obtain a third scoring feature set by the user for each of the image scoring regions, and a second scoring weight corresponding to the third scoring feature; The image feature extraction module includes: a regional feature extraction submodule for extracting regional image features corresponding to the third scoring feature from the image scoring region corresponding to each of the images; The scoring value acquisition module includes: A second initial score obtaining sub-module is configured to, for each of the image scoring regions, score the image features of the region according to the third scoring feature to obtain a second initial scoring value; A third score acquisition sub-module, configured to calculate and obtain the regional score value corresponding to the image score region according to the second initial score value and the second score weight, and use the regional score value as the score of the image value. 10. The apparatus of claim 6, wherein the apparatus further comprises: An image processing module, configured to save the target image and delete other images except the target image in the set of images to be screened. 11. A mobile terminal, characterized in that it comprises a processor, a memory and a computer program stored on the memory and running on the processor, the computer program being executed by the processor to achieve the right The steps of the image screening method of any one of claims 1 to 5. 12. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the image according to any one of claims 1 to 5 is realized Steps of the screening method.

Images