CN104484855B - The method and apparatus that picture is cut - Google Patents

Abstract

The invention discloses a method and device for cutting pictures, which mainly relate to the technical field of the Internet, and the main purpose is to adopt an appropriate cutting method for different pictures in time. The method includes: detecting the original picture to be cut, and detecting the characteristic elements contained in the original picture; selecting a cutting method for cutting the original picture according to the characteristic elements; cutting the original picture according to the cutting method to obtain the target picture . According to the present invention, before cutting the picture, the original picture is first detected, the characteristic elements contained therein are detected, and different cutting methods are used for cutting according to the difference of the characteristic elements, so as to ensure that the appropriate cutting method can be adopted in time for different pictures , so that the cropped target image meets the requirements.

Description

Method and device for image cropping

technical field

The present invention relates to the technical field of the Internet, in particular, to a method and device for cropping pictures.

Background technique

In the Internet field, it is usually necessary to crawl a large number of pictures on the Internet. Due to the different sizes of pictures on the Internet, it will be difficult for the size of the captured pictures to meet the requirements. At this time, the computer needs to automatically complete the cropping of the pictures so that the size of the pictures meets the needs.

For different pictures, since the contents displayed in the pictures are different, the parts that need to be cropped in the pictures are also different. However, the current cropping methods of thirds composition and golden ratio composition are all to crop the fixed position in the picture, so it is difficult to ensure that the effect of the cropped picture is satisfactory. Especially for some pictures that contain characters, the cutout methods of the prior art often make the cut out characters incomplete or incomplete, making the pictures unusable, or have to be cut out manually, which is inefficient and not widely used.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a method and device for cropping a picture that overcomes the above problems or at least partially solves the above problems.

According to one aspect of the present invention, a method for cropping a picture is provided, which includes: detecting the original picture to be cropped, and detecting the feature elements contained in the original picture; The cropping method of clipping the original picture; according to the clipping method, the original picture is cropped to obtain the target picture.

Optionally, in the foregoing method, the feature element includes a human face and/or a graphic symbol of a person.

Optionally, in the aforementioned method, detecting the original picture to be cropped and detecting the feature elements contained in the original picture specifically includes: detecting whether the human face is included in the original picture; When the human face is not included, it is detected whether the graphic mark is included in the original picture.

Optionally, the aforementioned method further includes: when the original picture does not contain the human face and the graphic logo, selecting a preset general cropping mode as the cropping mode for cropping the original picture.

Optionally, the aforementioned method, before selecting a cropping method for cropping the original picture according to the picture elements, further includes: when the human face is detected from the original picture, counting The number of faces; according to the picture element, select the cropping method for cutting the original picture, specifically including: when the number of faces in the original picture is 1, according to the face Select the corresponding cropping method.

Optionally, the aforementioned method further includes: when the number of faces in the original picture is greater than 1, selecting a preset general cropping mode as the cropping mode for cropping the original picture.

Optionally, in the aforementioned method, the feature elements are retained in the target picture.

According to another aspect of the present invention, there is also provided a device for cropping a picture, which includes: a feature element detection module, configured to detect the original picture to be cropped, and detect the feature elements contained in the original picture; the cropping method The selection module is configured to select a cropping method for cropping the original picture according to the characteristic elements; the cropping module is configured to crop the original picture according to the cropping method to obtain a target picture.

Optionally, in the aforementioned device, the feature element includes a human face and/or a graphic sign of a person.

Optionally, in the aforementioned device, the feature element detection module detects whether the original picture contains the human face; and when the original picture does not contain the human face, detects whether the original picture contains The graphic logo.

Optionally, in the aforementioned device, when the cropping mode selection module does not contain the human face and the graphic logo in the original picture, select a preset general cropping mode as the cropping method for cropping the original picture Way.

Optionally, in the aforementioned device, when the feature element detection module detects the human face from the original picture, it counts the number of the human faces; When the number of faces is 1, a corresponding cropping method is selected according to the faces.

Optionally, in the aforementioned device, the cropping mode selection module selects a preset general cropping mode as the cropping mode for cropping the original picture when the number of faces in the original picture is greater than 1.

Optionally, in the aforementioned apparatus, the feature element is retained in the target picture.

According to the above technical solutions, it can be known that the method and device for image cropping of the present invention have at least the following advantages:

According to the technical solution of the present invention, before cutting the picture, the original picture is first detected, the characteristic elements contained therein are detected, and different cutting methods are used to cut according to the difference of the characteristic elements, so as to ensure that different pictures can be used in time. The cropping method makes the cropped target image meet the requirements.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

Fig. 1 shows the flowchart of the method for cropping a picture according to an embodiment of the present invention;

Fig. 2 shows the flowchart of the method for cropping a picture according to an embodiment of the present invention;

Fig. 3 shows a flowchart of a method for cropping a picture according to an embodiment of the present invention;

Fig. 4 shows a block diagram of an apparatus for cropping a picture according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

As shown in Fig. 1, a kind of method of picture clipping is provided in one embodiment of the present invention, and it comprises:

Step 110: Detect the original picture to be cropped, and detect the feature elements contained in the original picture. In this embodiment, there is no limitation on the types of feature elements, which include but not limited to faces of people and graphic signs, for example, signs of commodities and enterprises.

Step 120: Select a cropping method for cropping the original image according to the characteristic elements. In this embodiment, there is no restriction on the cropping method. For example, if the characteristic element in a photo of a person is its face, the corresponding cropping method is to crop the image containing the face; the characteristic element in the product logo image is a graphic that serves as a sign or background color, copy the entire content of the picture to a certain area for cropping, and fill the remaining area when copying the picture with the background color.

Step 130, cropping the original picture according to the cropping method to obtain the target picture. According to the technical solution of this embodiment, before cutting the picture, the original picture is first detected, the characteristic elements contained in it are detected, and different cutting methods are used to cut according to the difference of the characteristic elements, so as to ensure that different pictures can be used in time An appropriate cropping method makes the cropped target image meet the requirements.

Further, feature elements are retained in the target image. This is because usually the characteristic elements are an important part of the original picture, for example, the face in the picture of a person, the figure or background color that plays a marking role in the picture of a graphic logo, all of which must be preserved.

According to Figure 1, the news photo of person A is detected, and based on the face recognition technology, the face of person A can be detected; when cutting the photo, the area where the face of person A is located is cut out from the photo, and the rest is discarded; The cropped picture has the face of the person A, which is beneficial to indicate the identity of the person A and matches the news of the person A.

As shown in Figure 2, a method for cropping a picture is provided in one embodiment of the present invention, which includes:

Step 210, detecting whether the original picture contains a human face.

Step 220, when the original picture contains a human face, select a cropping method for cropping the original picture according to the human face.

Step 230, when the original picture does not contain a human face, detect whether the original picture contains a graphic mark. In this embodiment, the human face has a higher detection priority than the graphic mark, because the picture with the human face and the graphic mark at the same time usually mainly presents the human face, so the human face is preferentially detected for further detection. cropped.

Step 240, when the original picture contains a graphic logo, select a cropping method for cropping the original picture according to the graphic logo.

Step 250, when the original picture does not contain a human face or graphic logo, select a preset general cropping mode as a cropping mode for cropping the original picture. In this embodiment, there is no limit to the general cropping method, and a cropping method that can adapt to more types of pictures is provided here: the original picture is compressed proportionally according to the minimum compression ratio, and the calculation formula of the minimum zoom ratio is as follows:

min_scale=MIN(width _src /width _dst ,height _src /height _dst )

Suppose the width and height of the uncompressed original picture are width _src and height _src respectively; the width and height of the target picture are width _dst and height _dst respectively. The surrounding pixels in the scaled picture that exceed the range of the target picture are cropped to obtain the target picture. This cropping method is beneficial to crop the non-important edge parts of the original picture.

It should be noted that each of the above formulas is not the only formula for implementing the present invention, and is only used as an implementation manner of the embodiment. Technicians can make appropriate changes to the formula according to business needs, such as adding constants or variables or coefficients, etc., which still fall within the protection scope of the present invention.

Step 260, cropping the original picture according to the cropping method to obtain the target picture.

According to Figure 2, in a photo of a star news report, a star gets off the vehicle, and the vehicle has a car logo. Obviously, the focus of the photo is the star; at this time, face detection is first performed based on face recognition technology, and If the star’s face is found, then the star’s face can be cut out during cropping, and the star can be identified in the cropped picture, which matches the news report.

As shown in Figure 3, a method for cropping a picture is provided in one embodiment of the present invention, which includes:

Step 310, detecting whether the original picture contains a human face.

Step 320, when a human face is detected from the original picture, count the number of human faces.

Step 330, when the number of faces in the original picture is 1, select the corresponding cropping method according to the faces.

Step 340, when the number of human faces in the original picture is greater than 1, select a preset general cropping mode as the cropping mode for cropping the original picture. In this embodiment, when the number of human faces is greater than 1, usually individual faces are not the main content, such as the situation of multiple people taking a photo, so it is not necessary to crop each person's face.

Step 350, when the original picture does not contain a human face, detect whether the original picture contains a graphic mark.

Step 360, when the original picture contains a graphic logo, select a cropping method for cropping the original picture according to the graphic logo.

When the original picture does not contain a human face or a graphic logo, go to step 340: select a preset general cropping mode as a cropping mode for cropping the original picture.

Step 370, crop the original picture according to the cropping method to obtain the target picture.

According to Figure 3, for a class group photo, after face detection, it is found that the number of faces is 20, then the general clipping strategy of the aforementioned embodiment is used for clipping, and the whole body parts of the 20 people in the cropped image are basically preserved .

As shown in Figure 4, an embodiment of the present invention provides a device for cropping a picture, which includes:

The characteristic element detection module 410 detects the original picture to be cropped, and detects the characteristic elements contained in the original picture. In this embodiment, there is no limitation on the types of feature elements, which include but not limited to faces of people and graphic signs, for example, signs of commodities and enterprises.

The cropping mode selection module 420 selects a cropping mode for cropping the original picture according to the characteristic elements. In this embodiment, there is no restriction on the cropping method. For example, if the characteristic element in a photo of a person is its face, the corresponding cropping method is to crop the image containing the face; the characteristic element in the product logo image is a graphic that serves as a sign or background color, copy the entire content of the picture to a certain area for cropping, and fill the remaining area when copying the picture with the background color.

The cropping module 430 is used to crop the original picture in a cropping manner to obtain the target picture. According to the technical solution of this embodiment, before cutting the picture, the original picture is first detected, the characteristic elements contained in it are detected, and different cutting methods are used to cut according to the difference of the characteristic elements, so as to ensure that different pictures can be used in time An appropriate cropping method makes the cropped target image meet the requirements.

Further, feature elements are retained in the target image. This is because usually the characteristic elements are an important part of the original picture, for example, the face in the picture of a person, the figure or background color that plays a marking role in the picture of a graphic logo, all of which must be preserved.

According to Figure 4, the news photo of person A is detected, and based on the face recognition technology, the face of person A can be detected; when cutting the photo, the area where the face of person A is located is cut from the photo, and the rest is discarded; The cropped picture has the face of the person A, which is beneficial to indicate the identity of the person A and matches the news of the person A.

An embodiment of the present invention provides a device for cropping a picture, which includes:

The feature element detection module 410 detects whether the original picture contains a human face.

The cropping mode selection module 420 selects a cropping mode for cropping the original picture according to the human face when the original picture contains a human face.

The feature element detection module 410 detects whether the original picture contains a graphic sign when the original picture does not contain a human face. In this embodiment, the human face has a higher detection priority than the graphic mark, because the picture with the human face and the graphic mark at the same time usually mainly presents the human face, so the human face is preferentially detected for further detection. cropped.

The cropping method selection module 420 selects a cropping method for cropping the original picture according to the graphic symbol when the original picture contains a graphic symbol.

The cropping mode selection module 420 selects a preset general cropping mode as the cropping mode for cropping the original picture when the original picture does not contain a human face or a graphic logo. In this embodiment, there is no limit to the general cropping method, and a cropping method that can adapt to more types of pictures is provided here: the original picture is compressed proportionally according to the minimum compression ratio, and the calculation formula of the minimum zoom ratio is as follows:

min_scale=MIN(width _src /width _dst ,height _src /height _dst )

Suppose the width and height of the uncompressed original picture are width _src and height _src respectively; the width and height of the target picture are width _dst and height _dst respectively. The surrounding pixels in the scaled picture that exceed the range of the target picture are cropped to obtain the target picture. This cropping method is beneficial to crop the non-important edge parts of the original picture.

It should be noted that each of the above formulas is not the only formula for implementing the present invention, and is only used as an implementation manner of the embodiment. Technicians can make appropriate changes to the formula according to business needs, such as adding constants or variables or coefficients, etc., which still fall within the protection scope of the present invention.

The cropping module 430 crops the original picture in a cropping manner to obtain the target picture.

According to Figure 4, in a photo of a star news report, a star gets off the vehicle, and the vehicle has a car logo. Obviously, the focus of the photo is the star; at this time, face detection is first based on face recognition technology, and If the star’s face is found, then the star’s face can be cut out during cropping, and the star can be identified in the cropped picture, which matches the news report.

An embodiment of the present invention provides a device for cropping a picture, which includes:

The feature element detection module 410 detects whether the original picture contains a human face, and counts the number of human faces when a human face is detected from the original picture.

The cropping mode selection module 420, when the number of faces in the original picture is 1, selects the corresponding cropping mode according to the faces.

The cropping mode selection module 420 selects a preset general cropping mode as the cropping mode for cropping the original picture when the number of human faces in the original picture is greater than 1. In this embodiment, when the number of human faces is greater than 1, usually individual faces are not the main content, such as the situation of multiple people taking a photo, so it is not necessary to crop each person's face.

The feature element detection module 410 detects whether the original picture contains a graphic sign when the original picture does not contain a human face.

The cropping method selection module 420 selects a cropping method for cropping the original picture according to the graphic symbol when the original picture contains a graphic symbol.

The cropping mode selection module 420 selects a preset general cropping mode as the cropping mode for cropping the original picture when the original picture does not contain a human face or a graphic logo.

The cropping module 430 is used to crop the original picture in a cropping manner to obtain the target picture.

According to Figure 4, for a class group photo, after face detection, it is found that the number of faces is 20, then the general cutting strategy of the aforementioned embodiment is used for cutting, and the whole body parts of the 20 people in the cut picture are basically preserved .

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components in the image cropping apparatus according to the embodiment of the present invention. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims (8)

1. A method for image cropping, comprising: Detecting the original picture to be cropped, and detecting the feature elements contained in the original picture, including: the feature elements include at least the face and/or graphic logo of the person; Detecting whether the human face is included in the original picture; when the human face is not included in the original picture, detecting whether the graphic mark is included in the original picture; Selecting a cropping method for cropping the original picture according to the characteristic elements; When the original picture does not contain the human face and the graphic logo, a preset general cropping method is selected as a cropping method for cutting the original picture, and the preset general cropping method includes at least: The original picture is proportionally scaled according to the minimum scaling ratio, and then the pixels around the scaled picture that exceed the range of the target picture are cut out; The original picture is cropped according to the cropping manner to obtain a target picture. 2. The method according to claim 1, wherein, before selecting a cropping method for clipping the original picture according to the picture element, further comprising: When detecting the human face from the original picture, counting the number of the human faces; According to the picture element, select a cropping method for clipping the original picture, specifically including: When the number of the human face in the original picture is 1, a corresponding cropping manner is selected according to the human face. 3. The method according to any one of claims 1-2, further comprising: When the number of faces in the original picture is greater than 1, a preset general cropping mode is selected as the cropping mode for cropping the original picture. 4. The method of claim 1, wherein, The feature element is reserved in the target picture. 5. A device for cropping pictures, comprising: A feature element detection module, configured to detect the original picture to be cropped, and detect the feature elements contained in the original picture, the feature elements include at least the face and/or graphic logo of the person; The feature element detection module detects whether the original picture contains the human face; and when the original picture does not contain the human face, detects whether the original picture contains the graphic sign; A cropping mode selection module, configured to select a cropping mode for cropping the original image according to the characteristic elements; When the original picture does not contain the human face and the graphic logo, the cropping mode selection module selects a preset general cropping mode as the cropping mode for cropping the original picture, and the preset general The cropping method at least includes: proportionally scaling the original image according to the minimum zoom ratio, and then cropping the pixels around the zoomed image that exceed the range of the target image; A cropping module, configured to crop the original picture according to the cropping manner to obtain a target picture. 6. The device according to claim 5, wherein, when the feature element detection module also detects the human face from the original picture, count the number of the human faces; When the number of the human face in the original picture is 1, select the corresponding cropping method according to the human face. 7. The device according to any one of claims 5-6, wherein, when the number of faces in the original picture is greater than 1, the cropping mode selection module selects a preset general cropping mode as the Describes the cropping method for cropping the original image. 8. The device according to claim 5, wherein the characteristic element is retained in the target picture.