CN105808782B - Method and device for adding image tags - Google Patents

Abstract

The invention is applicable to the technical field of computers, and provides a method and a device for adding a picture label, wherein the method comprises the following steps: when the end of photo shooting is detected in the running process of a shooting process, a tag input area is presented, and tag information input by a user is acquired; adding the label information into the shot picture to generate a target picture; the method and the device have the advantages that the time information is obtained from the time process, the label information and the time information are written into the attribute information of the target picture, the target picture is stored according to the label information and the time information, the user-defined label information is added into the picture, the operation is convenient and fast, the label editing complexity of the picture is low, the user can input and store the label information in the picture, the narrative performance of the picture is improved, the user participation and the controllability are improved, meanwhile, the label information is written into the attribute information, the picture classification is facilitated, and the accuracy and the efficiency of later picture searching are improved.

Description

Method and device for adding image tags

technical field

The invention belongs to the technical field of computers, and in particular relates to a method and a device for adding picture tags.

Background technique

With the development of digital acquisition technology and computer technology, more and more pictures are stored in digital form, and users use pictures to record more information. Pictures are generally acquired from the outside world by imaging devices (such as cameras, mobile phones, or tablet computers, etc.), and converted into dot matrix data by means of sampling. The built-in photographing program in the existing mobile terminal or the photographing application program installed by the user adopts a default mode to automatically save the photographed picture after the photographing is completed. The default information of the photograph includes the photograph name, photograph format, photograph size, shooting location information, Attribute information such as shooting date and shooting model information cannot be edited by the user, which lacks a personalized experience, but you can go to the attribute to view the attributes of the picture. After transferring the picture to the computer, the user can check the attributes of the picture or modify it on the computer. Some attributes greatly increase the complexity of editing, the user's participation and controllability are low, and it is not convenient for later image search, which greatly reduces the accuracy and efficiency of image search.

Contents of the invention

The purpose of the present invention is to provide a method and device for adding picture tags, aiming to solve the problem of low user participation, low controllability, low accuracy of picture search and low picture search accuracy due to the high complexity of editing picture tags in the prior art. The problem of low efficiency.

In one aspect, the present invention provides a method for adding a picture tag, the method comprising:

When the end of photo shooting is detected during the running of the photo taking process, the tag input area is presented to obtain the tag information input by the user;

adding tag information to the photograph taken to generate a target picture;

Acquiring time information from a time course, writing the tag information and the time information into the attribute information of the target picture, and storing the target picture according to the tag information and the time information.

In another aspect, the present invention provides a device for adding a picture tag, the device comprising:

The tag input unit is used to display the tag input area when it is detected that the photo shooting ends during the running of the photo taking process, and obtain the tag information input by the user;

A tag adding unit, configured to add tag information to the photograph taken to generate a target image;

A tag storage unit, configured to acquire time information from a time course, write the tag information and the time information into the attribute information of the target picture, and store the target picture according to the tag information and the time information .

In the embodiment of the present invention, through the function of adding tags during shooting, an interface entry for users to add custom tags to photographed photos is provided, which realizes adding user-defined tag information to pictures, convenient operation, and photo tag editing The complexity is low, so that users can input and save tag information in photos, which increases the narrative of photos. It improves user participation and controllability, and at the same time writes label information into attribute information, which is convenient for picture classification and improves the accuracy and efficiency of post-picture search.

Description of drawings

Fig. 1 is the implementation flowchart of the method for adding picture tags provided by Embodiment 1 of the present invention;

Fig. 2 is a schematic diagram of adding a picture tag provided by Embodiment 1 of the present invention;

FIG. 3 is a flow chart of the implementation of the method for adding a picture tag provided in Embodiment 2 of the present invention;

FIG. 4 is a flow chart of the implementation of the method for adding image tags provided by Embodiment 3 of the present invention;

Fig. 5 is a structural diagram of an image tag adding device provided by Embodiment 4 of the present invention;

Fig. 6 is a schematic diagram of a picture tag adding system provided by an embodiment of the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

In the embodiment of the present invention, a device for adding a picture tag can be: a terminal including a camera such as a smart phone, a camera, or a portable device, or it can also be realized through a client module in the terminal, for example: a terminal built-in shooting software, a shooting application program, image processing client, etc.

The specific realization of the present invention is described in detail below in conjunction with specific embodiment:

Embodiment one:

Fig. 1 shows the implementation process of the picture adding method provided by Embodiment 1 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown. The method may include the following steps: S101-S103.

Step S101 , when it is detected that the photo shooting is finished during the running of the photo taking process, a tag input area is presented, and tag information input by the user is obtained.

As an optional implementation manner, the tag information input by the user in this embodiment of the present invention includes text information, language information, image information, etc., and is not specifically limited by this embodiment of the present invention. Specifically, the user can input text information through the virtual keyboard on the screen, and input audio information through the microphone, so that the terminal can obtain the tag information input by the user.

Application scenario example: the user opens the built-in camera software in the mobile terminal, enables the label mode in advance, and the user clicks the capture button to take a photo. At this time, the terminal is running the camera process and detects that the photo is taken, and the label is displayed on the display interface. In the input area, the label input area can be a text input box, a user voice input button, or an option to add image information, etc., then the user enters label information in the label input area, and then the terminal obtains the label information input by the user.

Step S102, adding label information to the photograph taken to generate a target picture.

As an optional implementation, the label information is added to the photos taken in the form of text, and the audio information entered by the user in the label area can be converted into text information. If the user enters image information in the label area, the image information will be added into the captured image. Take the example of adding tag information to the captured picture in the form of text for coding example, as follows: Create a function object to obtain the data stream from the source picture (taken picture), create a picture object and fill it with the source picture data, get Source image width, source image length, create a function object as the image operation container, create a drawing environment to draw the image, load the source image data stream into the image operation container, set the text font, color, etc., and write the note information Enter the image operation container and take effect, create the output file stream and image encoding object, perform image encoding, close the output file stream, and generate the target image.

Step S103, acquiring time information from the time course, writing the label information and time information into the attribute information of the target picture, and storing the target picture according to the label information and time information.

As an optional implementation, time information is obtained from the time course, such as year, month, day, hour, minute, and second, and the tag information and time information are written into the attribute information of the target picture, and the target picture is stored in a designated storage area, and according to the tag The information and time information classify and store target pictures. Specifically, pictures with tag information belonging to the same category may be classified into one category, and the pictures are stored in time order in this category.

Further optionally, step S102 adds tag information to the captured photo to generate a target image, which may specifically include: analyzing the captured photo, determining the location where the tag information is added in the photo according to the analysis result and the tag information, and adding The tag information is added to the determined adding location, presented to the user and allowed to edit the adding location.

Perform image analysis and processing on the captured pictures, extract the feature points of the pictures, analyze the SIFT (scale-invariant feature transform) features, color histograms, texture features, etc. of the pictures, and perform data analysis on the feature points of the pictures Clustering, to determine the category of each feature point, and then match it with the training library to determine the category of the picture, such as landscapes, people, buildings, animals, etc. The category of the picture is obtained by the image analysis process, and the adding position of the label information in the photo is determined, so that the label information is added to the determined adding position, presented to the user and allowed to edit the adding position.

Referring to FIG. 3 , which is a schematic diagram of adding a picture tag provided by Embodiment 1 of the present invention, the user enables the use tag function shown at 300 in the camera settings in advance. The user can input tag information in the tag input area 201, and then can add the tag information to the photo 200, and can also write the tag information into the attribute of the photo.

In the embodiment of the present invention, through the function of adding tags during shooting, an interface entry for users to add custom tags to photographed photos is provided, and a tag input area is presented, so that user-defined tag information can be added to photos, and the operation is convenient , the complexity of photo tag editing is low, so that users can input and save tag information in photos, which increases the narrative of photos. It improves user participation and controllability, and at the same time writes label information into attribute information, which is convenient for picture classification and improves the accuracy and efficiency of post-picture search.

Carry out image analysis on the captured pictures, determine the adding position of the label information in the picture based on the analysis results and label information, and support user re-editing at the same time, realizing different positions for label information display according to the label information entered by the user and different picture types The shape makes the addition of picture tags more intelligent, avoiding the situation of fixing the position and covering the main picture screen.

Embodiment two:

Figure 2 shows the implementation process of the picture adding method provided by the second embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown. The method may include the following steps:

S301, running a photographing process.

S302, judging whether the photographing is finished, if yes, execute step S303, if not, return to step S302.

S303, judging whether to start the label mode for the first time, if the judgment result is yes, execute step S304, if the judgment result is no, execute step S306.

S304, presenting a blank label input area.

S305. Obtain tag information input by the user in the blank tag input area.

S306. Read historical tag information of historical photographing event records.

S307, displaying the read historical tag information in the tag input area.

S308. Obtain a confirmation result of the label information displayed in the label input area by the user.

As an optional implementation, image analysis and processing are performed on the captured pictures, the analysis and processing results are matched with historical tag information recorded in historical photographing events, and the matched historical tag information is displayed in the tag input area according to the degree of matching correlation. Extract the feature points of the picture, analyze the SIFT feature, color histogram, texture feature, etc. of the picture, perform data clustering on the feature points of the picture, determine the category to which each feature point belongs, and then match it with the training database to determine the picture belongs to Categories such as Landscape, People, Buildings, Animals, etc. The category of the picture is obtained by image analysis and processing, and then matched with the historical tag information recorded in the historical photo event, such as the scenery corresponding to the historical tag information related to play, etc. Furthermore, it can also be displayed in the label input area according to the degree of matching association, for example, the one with the highest degree of matching association is displayed at the front.

S309, adding tag information to the captured photo to generate a target picture.

S310. Obtain the geographic location information at the current moment.

S311. Determine, according to the label information input by the user, a display position and display interface elements of the geographic location information in the photo.

S312. Add the geographic location information to the photo.

As an optional implementation manner, geographic location information may be added to the photo, for example, the geographic location information is added to the photo in area 201 as shown in FIG. 2 . Corresponding to different tag information input by the user, different geographic location information display states can be matched, and different geographic location information display templates are matched in advance for different types of tag information, such as cartoon version, aesthetic version of geographic location information display template, etc. Furthermore, the user can also edit, modify, replace or delete the status of the geographic location information in S311.

S313. Generate a target picture.

S314. Display the target picture including tag information and/or geographic location information on a display screen.

S315. Acquire time information from the time course.

S316. Write the tag information and time information into the attribute information of the target picture.

S317. Store the target picture according to the tag information and time information.

In the embodiment of the present invention, through the function of adding tags during shooting, an interface entry for users to add custom tags to photographed photos is provided, and a tag input area is presented, so that user-defined tag information can be added to photos, and the operation is convenient , the complexity of photo tag editing is low, so that users can input and save tag information in photos, which increases the narrative of photos. It improves user participation and controllability, and at the same time writes label information into attribute information, which is convenient for picture classification and improves the accuracy and efficiency of post-picture search.

Form a memory function for the tag information added in the history, and display the historical tag information in the tag input area. The user can directly select one of the historical tag information, or modify the selected historical tag information, which greatly reduces the complexity of photo tag editing. .

Image analysis is performed on the captured pictures, and the analysis results are matched with historical label information, that is, historical label information is recommended for the captured pictures, and recommendations are made according to the matching correlation degree, thereby increasing the flexibility and intelligence of automatic label display, and improving the suitability.

The geographic location information is displayed in the captured pictures, and the display status of the geographic location information matches the label information input by the user, that is, the geographic location information will show different display forms with different label information of the user, which increases the interest of the image label display sex.

Embodiment three:

Figure 4 shows the implementation process of the picture adding method provided by the third embodiment of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown. The method may include the following steps:

S401. When it is detected that the photo shooting is finished during the operation of the photo taking process, a tag input area is presented to acquire tag information input by the user.

S402. Add tag information to the captured photo to generate a target picture.

S403, performing word segmentation processing on the label information input by the user, extracting keywords, matching label types, and classifying target pictures according to the label types.

In the specific implementation, word segmentation is performed on the tag information input by the user, keywords are extracted, the extracted keywords are paired with the keywords corresponding to the tag type template, and the tag type corresponding to the tag information input by the user is determined, so that according to the matched tag Type classifies the target image. For example, match the target picture to the tag type "play" according to the tag information "a family visits XXX scenic spot".

S404. Acquire time information from the time course, write the tag information and time information into the attribute information of the target picture, and classify and store the target pictures according to the tag information and time information.

S405. When receiving a picture search command from the user, match the picture search command with tag information of the target picture, determine a tag type corresponding to the picture search command, and present the matching result to the user.

In the specific implementation, the user can search for pictures in the terminal, enter keywords in the search box, and the terminal receives the user's picture search command. The tag information of the pictures is matched to determine the tag type corresponding to the image search command, and then the image corresponding to the tag type is presented to the user. Further, the order of corresponding pictures may also be displayed according to the degree of matching relevance.

In the embodiment of the present invention, through the function of adding tags during shooting, an interface entry for users to add custom tags to photographed photos is provided, which realizes adding user-defined tag information to pictures, convenient operation, and photo tag editing The complexity is low, so that users can input and save tag information in photos, which increases the narrative of photos. It improves user participation and controllability, and at the same time writes label information into attribute information, which is convenient for picture classification and improves the accuracy and efficiency of post-picture search.

Those of ordinary skill in the art can understand that all or part of the steps in the method of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage Media such as ROM/RAM, magnetic disk, optical disk, etc.

Embodiment four:

Fig. 5 shows the structural diagram of the picture tag adding device provided by Embodiment 4 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including: a tag input unit 501, a tag adding unit 502 and Label storage unit 503 .

The tag input unit 501 is configured to present a tag input area and acquire tag information input by the user when it is detected that the photo shooting is finished during the running of the photo taking process.

As an optional implementation manner, the tag information input by the user in this embodiment of the present invention includes text information, language information, image information, etc., and is not specifically limited by this embodiment of the present invention. Specifically, the user can input text information through the virtual keyboard on the screen, and input audio information through the microphone, so that the label input unit 501 can obtain the label information input by the user.

Application scenario example: The user opens the built-in camera software in the mobile terminal, enables the label mode in advance, and the user clicks the capture button to take a photo. At this time, the camera process is running and the photo shooting is detected, and the label input will be displayed on the display interface. area, the tag input area can be a text input box, a user voice input button, or an option to add image information, etc., then the user inputs tag information in the tag input area, and then the tag input unit 501 obtains the tag information input by the user.

As an optional implementation manner, the label input unit 501 may include a judging subunit, a first input subunit, or a second input subunit.

The judging subunit is used to judge whether to start the label mode for the first time when the photographing process is running.

The first input subunit is configured to present a blank label input area when the judging result of the judging subunit is yes.

The second input subunit is used to read the historical label information of the historical photographing event record when the judgment result of the judging subunit is No, display the read historical label information in the label input area, and obtain the user's display of the label input area. The confirmation result of the label information, which is the label information entered by the user.

Further, the second input subunit is specifically used to: perform image analysis and processing on the captured pictures, match the analysis and processing results with the historical tag information recorded in the historical photographing events, and display the matched historical tags in the tag input area according to the degree of matching correlation information.

As an optional implementation, the second input subunit performs image analysis and processing on the captured pictures, matches the analysis and processing results with the historical label information recorded in the historical photographing events, and displays the matching information in the label input area according to the degree of matching correlation. Historical label information. Extract the feature points of the picture, analyze the SIFT feature, color histogram, texture feature, etc. of the picture, perform data clustering on the feature points of the picture, determine the category to which each feature point belongs, and then match it with the training database to determine the picture belongs to Categories such as Landscape, People, Buildings, Animals, etc. The category of the picture is obtained by image analysis and processing, and then matched with the historical tag information recorded in the historical photo event, such as the scenery corresponding to the historical tag information related to play, etc. Furthermore, it can also be displayed in the label input area according to the degree of matching association, for example, the one with the highest degree of matching association is displayed at the front.

The tag adding unit 502 is configured to add tag information to the captured photo to generate a target image.

As an optional implementation, the label information is added to the photos taken in the form of text, and the audio information entered by the user in the label area can be converted into text information. If the user enters image information in the label area, the image information will be added into the captured image. Take the example of adding tag information to the captured picture in the form of text for coding example, as follows: Create a function object to obtain the data stream from the source picture (taken picture), create a picture object and fill it with the source picture data, get Source image width, source image length, create a function object as the image operation container, create a drawing environment to draw the image, load the source image data stream into the image operation container, set the text font, color, etc., and write the note information Enter the image operation container and take effect, create the output file stream and image encoding object, perform image encoding, close the output file stream, and generate the target image.

Further optionally, the label adding unit 502 is specifically used for:

Analyze the photos taken, determine the adding position of the tag information in the photo according to the analysis result and the tag information, add the tag information to the determined adding position, present it to the user and allow the user to edit the adding position.

As an optional implementation manner, geographic location information may be added to the photo. Corresponding to different tag information input by the user, different geographic location information display states can be matched, and different geographic location information display templates are matched in advance for different types of tag information, such as cartoon version, aesthetic version of geographic location information display template, etc. Furthermore, the user can also edit, modify, replace or delete the status of the geographic location information.

The label storage unit 503 is configured to obtain time information from the time course, write the label information and time information into the attribute information of the target picture, and store the target picture according to the label information and time information.

As an optional implementation, time information is obtained from the time course, such as year, month, day, hour, minute, and second, and the tag information and time information are written into the attribute information of the target picture, and the target picture is stored in a designated storage area, and according to the tag The information and time information classify and store target pictures. Specifically, pictures with tag information belonging to the same category may be classified into one category, and the pictures are stored in time order in this category.

Further optionally, the device provided in the embodiment of the present invention may further include: a location acquiring unit, a location adding unit, and a display unit.

The position obtaining unit is used to obtain the geographic location information at the current moment during the operation of the photographing process.

The position adding unit is configured to determine the display position and display interface elements of the geographic location information in the photo according to the tag information input by the user, add the geographic location information to the photo, and generate a target image.

The display unit is used for displaying the target picture including label information and/or geographic location information on a display screen.

In the specific implementation, image analysis and processing are performed on the captured pictures, the feature points of the pictures are extracted, SIFT features, color histograms, texture features, etc. are analyzed on the pictures, data clustering is performed on the feature points of the pictures, and each feature point is determined category, and then match it with the training library to determine the category of the picture, such as landscapes, people, buildings, animals, etc. The category of the picture is obtained by the image analysis process, and the adding position of the label information in the photo is determined, so that the label information is added to the determined adding position, presented to the user and allowed to edit the adding position.

Further optionally, the device provided in the embodiment of the present invention further includes a search unit.

The tag storage unit 503 is specifically configured to: perform word segmentation processing on tag information input by the user, extract keywords, match tag types, and classify target pictures according to tag types.

The search unit is configured to match the image search command with tag information of the target image when receiving the user's image search command, determine the tag type corresponding to the image search command, and present the matching result to the user.

In an embodiment of the present invention, a device for adding a picture tag is provided, including a tag input unit, a tag adding unit, and a tag storage unit, and the tag input sheet is used to present a tag input area when it is detected that the photo shooting is completed during the running of the photo taking process , to obtain the tag information input by the user; the tag adding unit is used to add the tag information to the photo taken to generate the target picture; the tag storage unit is used to obtain the time information from the time course, and write the tag information and time information into the target picture attribute information, and store the target picture according to tag information and time information. Through the function of adding tags during shooting, it provides an interface entry for users to add custom tags to the photos taken, presents the tag input area, and realizes adding user-defined tag information to photos. The operation is convenient and the photo tag editing is complicated. Low, allowing users to enter and save tag information in photos, increasing the storytelling of photos. It improves user participation and controllability, and at the same time writes label information into attribute information, which is convenient for picture classification and improves the accuracy and efficiency of post-picture search.

Form a memory function for the tag information added in the history, and display the historical tag information in the tag input area. The user can directly select one of the historical tag information, or modify the selected historical tag information, which greatly reduces the complexity of photo tag editing. .

Image analysis is performed on the captured pictures, and the analysis results are matched with historical label information, that is, historical label information is recommended for the captured pictures, and recommendations are made according to the matching correlation degree, thereby increasing the flexibility and intelligence of automatic label display, and improving the suitability.

The geographic location information is displayed in the captured pictures, and the display status of the geographic location information matches the label information input by the user, that is, the geographic location information will show different display forms with different label information of the user, which increases the interest of the image label display sex.

Carry out image analysis on the captured pictures, determine the adding position of the label information in the picture based on the analysis results and label information, and support user re-editing at the same time, realizing different positions for label information display according to the label information entered by the user and different picture types The shape makes the addition of picture tags more intelligent, avoiding the situation of fixing the position and covering the main picture screen.

In the embodiment of the present invention, each unit can be realized by corresponding hardware or software unit, and each unit can be an independent software and hardware unit, or can be integrated into one software and hardware unit, which is not used to limit the present invention.

The embodiment of the present invention also discloses a shooting terminal. The shooting terminal includes a camera, including the device shown in FIG. 5 ; the structure and function of the device can refer to the relevant description of the embodiment shown in FIG. 5 , and will not be repeated here. The input, addition, processing and storage of picture tags are performed on the shooting terminal itself, without external equipment or devices. It should be noted that the photographing terminal provided in this embodiment corresponds to the methods for adding picture tags shown in FIG. 1 and FIG. 3 , and is the subject of execution based on the methods for adding picture tags shown in FIGS. 1 to 3 .

The embodiment of the present invention also discloses a system for adding a picture label, as shown in FIG. 6 , which is a schematic structural diagram of a system for adding a picture label provided by the embodiment of the present invention. As shown in FIG. 6 , the image tag adding system provided by the embodiment of the present invention may include a shooting terminal 10 and a server 20 . Further, the target picture may be stored locally in the shooting terminal 10, or in the server 20, or in the cloud, etc., and is not limited by the embodiments of the present invention.

The photographing terminal 10 is configured to present a tag input area and acquire tag information input by the user when it detects that the photo shooting is finished during the running process of the photo shooting process. The photographing terminal uploads the photograph taken and the tag information input by the user to the server 20 . The server 20 is configured to add tag information to the photographed photos, generate a target picture, and present the target picture in the photographing terminal 10 . The shooting terminal obtains time information from the time course, writes the tag information and time information into the attribute information of the target picture, and stores the target picture according to the tag information and time information.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.

Claims (10)

1. a kind of adding method of picture tag, which is characterized in that the described method includes:

At the end of detecting photograph taking in process operational process of taking pictures, label input area is presented, obtains user's input Label information；

Label information is added in the photo of the shooting, generates Target Photo；

From time course acquisition time information, the label information, the temporal information are written to the attribute of the Target Photo In information, and the Target Photo is stored according to the label information and the temporal information,

In the photo that label information is added to the shooting, Target Photo is generated, comprising:

Image analysis processing is carried out to the picture of shooting, extracts the characteristic point of picture, data clusters are carried out to the characteristic point of picture, It determines classification belonging to each characteristic point, then is matched with training library, picture generic is determined, by label information and image Analysis handles to obtain the classification of picture, determines point of addition of the label information in photo, so that label information is added to really Fixed point of addition, and be presented to the user and user is allowed to edit point of addition.

2. the method as described in claim 1, which is characterized in that described to detect photograph taking in process operational process of taking pictures At the end of, label input area is presented, obtains the label information of user's input, comprising:

Judge whether to open label mode for the first time when taking pictures process operation；

If so, the label input area of blank is presented；

The history tab information of logout if it is not, reading history is taken pictures, shows the reading in the label input area History tab information obtains the confirmation for the label information that user shows the label input area as a result, to be confirmed as user defeated The label information entered.

3. method according to claim 2, which is characterized in that it is described read history take pictures logout history tab letter Breath, shows the history tab information of the reading in the label input area, comprising:

Image analysis processing is carried out to the picture of the shooting, analysis and processing result and the history are taken pictures the going through of logout History label information is matched, and shows the matched history tab letter in the label input area according to the matching degree of association Breath.

4. the method as described in claim 1, which is characterized in that in the photo that label information is added to the shooting, After generating Target Photo, the method also includes:

In process operational process of taking pictures, the geographical location information at current time is obtained；

Display position of the geographical location information in the photo and display circle are determined according to the label information that user inputs The geographical location information is added in the photo by surface element, generates the Target Photo；

Display includes the Target Photo of the label information and/or the geographical location information on the display screen.

5. the method as described in claim 1, which is characterized in that described to be stored according to the label information and the temporal information The Target Photo includes:

Word segmentation processing is carried out to the label information of user input, keyword is extracted, matches tag types, according to tag types Classify to Target Photo；

After storing the Target Photo according to the label information and the temporal information, the method also includes:

In the picture searching order for receiving user, by the progress of the label information of picture searching order and the Target Photo Match, determines the corresponding tag types of picture searching order, and matching result is presented to the user.

6. a kind of adding set of picture tag, which is characterized in that described device includes:

At the end of for detecting photograph taking in process operational process of taking pictures, label input area is presented in label input unit Domain obtains the label information of user's input；

Label adding unit generates Target Photo for label information to be added in the photo of the shooting；

Tag memory cell, for from time course acquisition time information, institute to be written in the label information, the temporal information It states in the attribute information of Target Photo, and stores the Target Photo according to the label information and the temporal information,

The label adding unit is specifically used for:

Image analysis processing is carried out to the picture of shooting, extracts the characteristic point of picture, data clusters are carried out to the characteristic point of picture, It determines classification belonging to each characteristic point, then is matched with training library, picture generic is determined, by label information and image Analysis handles to obtain the classification of picture, determines point of addition of the label information in photo, so that label information is added to really Fixed point of addition, and be presented to the user and user is allowed to edit point of addition.

7. device as claimed in claim 6, which is characterized in that the label input unit includes:

Judgment sub-unit, for judging whether to open label mode for the first time when taking pictures process operation；

First input subelement, is when being for the judging result in the judgment sub-unit, the label that blank is presented is defeated Enter region；

When second input subelement for the judging result in the judgment sub-unit is no, reads history and take pictures logout History tab information, show the history tab information of the reading in the label input area, obtain user to the mark The confirmation for the label information that label input area is shown is as a result, be confirmed as the label information of user's input.

8. device as claimed in claim 7, which is characterized in that the second input subelement is specifically used for: to the shooting Picture carry out image analysis processing, the take pictures history tab information of logout of analysis and processing result and the history is carried out Matching shows the matched history tab information in the label input area according to the matching degree of association.

9. device as claimed in claim 7, which is characterized in that described device further include:

Position acquisition unit, for obtaining the geographical location information at current time in process operational process of taking pictures；

Position adding unit, the label information for being inputted according to user determine the geographical location information in the photo Display position and display interface element, the geographical location information is added in the photo, generates the Target Photo；

Display unit, for being shown on the display screen including described in the label information and/or the geographical location information Target Photo.

10. device as claimed in claim 7, which is characterized in that described device further includes search unit；

The tag memory cell is specifically used for: word segmentation processing carried out to the label information of user input, extracts keyword, Tag types are matched, are classified according to tag types to Target Photo；

Described search unit is used in the picture searching order for receiving user, by picture searching order and the Target Photo Label information matched, determine the corresponding tag types of picture searching order, and matching result is presented to the user.