WO2019137216A1

WO2019137216A1 - Image filtering method and apparatus

Info

Publication number: WO2019137216A1
Application number: PCT/CN2018/123903
Authority: WO
Inventors: 柳林东
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-01-09
Filing date: 2018-12-26
Publication date: 2019-07-18
Also published as: TW201931211A; CN108346139A

Abstract

The embodiments of the present application provide an image filtering method and apparatus. Said method comprises: acquiring a plurality of photographed alternative images, each alternative image comprising a plurality of target objects; extracting, from the alternative image, key features of each target object respectively, and performing photographing quality analysis on each alternative image according to the extracted key features, so as to obtain a photographing quality analysis result of the alternative image; and selecting, from a plurality of alternative images, a target image according to the photographing quality analysis result of each alternative image. Photographing quality analysis is performed on a plurality of alternative images, so as to determine, from the plurality of alternative images, a target image having a photographing quality satisfying a predetermined requirement, thereby improving the image filtering efficiency, reducing the time for a user to browse the plurality of alternative images one by one to select a target image, ensuring that an alternative image, which does not satisfy predetermined photographing quality requirements, is not taken as a target image, improving the accuracy of selecting the target image, improving the user experience.

Description

Image screening method and device

Technical field

The present application relates to the technical field of image recognition, and in particular, to an image screening method and apparatus.

Background technique

At present, in the social process of the user, for example, class reunion, etc., a large photo is usually taken as a memorial. However, the more people who take pictures, the more uncertain factors will increase. For example, in the photos taken, a participant may suddenly blink, exaggerated, suddenly slap, and other unqualified items. In order to avoid the situation where the image of the unqualified item is shared to the social platform and affect the image of the user, a plurality of images are often taken by the target object, and then the user browses the multiple images obtained one by one, and selects among the multiple images. A target image whose shooting quality meets the preset requirements.

It can be seen that in the process of selecting a target image from a plurality of images, the user needs to browse and select the target images one by one, which not only requires the user to spend a certain selection time, but also increases the selection difficulty. It is also possible that the image whose shooting quality does not meet the preset requirement is shared as a target image to the social platform due to the user's selection error, thereby causing a bad user experience.

Summary of the invention

An object of the embodiments of the present invention is to provide an image screening method and apparatus, which can improve image quality by determining a target image of a plurality of candidate images in a plurality of candidate images according to preset requirements. The efficiency reduces the time for the user to browse and select the target images one by one, and avoids the candidate image that does not meet the preset requirements as the target image due to the user's selection error, which improves the accuracy of the target image selection. , improved user experience.

To solve the above technical problem, the embodiment of the present application is implemented as follows:

An embodiment of the present application provides an image screening method, including:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

Extracting key features of each target object from the candidate image, performing a shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

And extracting key features of each target face from the candidate images, performing shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

An embodiment of the present application provides an image screening apparatus, including:

An alternative image acquisition module, configured to acquire a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

a shooting quality analysis module, configured to respectively extract key features of each target object from the candidate image, perform shooting quality analysis on each of the candidate images according to the extracted key features, to obtain the candidate image Shooting quality analysis results;

An alternative image acquisition module, configured to acquire a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

a shooting quality analysis module, configured to respectively extract key features of each target face from the candidate image, perform shooting quality analysis on each of the candidate images according to the extracted key features, to obtain the candidate Image quality analysis results;

And a target image selection module, configured to select a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.

An embodiment of the present application provides an image screening device, including: a processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to:

The embodiment of the present application provides a storage medium, including:

The image screening method and apparatus in the embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target objects; and extracts key features of each target object from the candidate images, respectively, according to the extracted The key feature performs the shooting quality analysis on each candidate image to obtain the shooting quality analysis result of the candidate image; and selects the target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image. By performing image quality analysis on multiple candidate images, the target image whose shooting quality meets the preset requirements is determined in multiple candidate images, thereby improving image screening efficiency and reducing the time for the user to browse and select the target images one by one. The candidate image that does not meet the preset requirements due to the user's selection error is avoided as the target image, which improves the accuracy of the target image selection and improves the user experience.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only It is a few embodiments described in the present application, and other drawings can be obtained from those skilled in the art without any inventive labor.

FIG. 1 is a schematic diagram of a first process of an image screening method according to an embodiment of the present application;

2 is a second schematic flowchart of an image screening method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a third process of an image screening method according to an embodiment of the present application;

4 is a fourth schematic flowchart of an image screening method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a fifth process of an image screening method according to an embodiment of the present application;

FIG. 6 is a sixth schematic flowchart diagram of an image screening method according to an embodiment of the present application;

FIG. 7 is a schematic diagram of an effect of one of candidate images in an image screening method according to an embodiment of the present application; FIG.

FIG. 7b is a schematic diagram showing the effect of the second candidate image in the image screening method according to the embodiment of the present application;

FIG. 7c is a schematic diagram of an effect of the third candidate image in the image screening method according to the embodiment of the present application;

FIG. 7 is a schematic diagram of the effect of the fourth candidate image in the image screening method according to the embodiment of the present application;

FIG. 8 is a schematic structural diagram of a module of an image screening apparatus according to an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an image screening device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following, in which the technical solutions in the embodiments of the present application are clearly and completely described. The embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope shall fall within the scope of the application.

The embodiment of the present application provides an image screening method and device. By performing image quality analysis on multiple candidate images of a target object, a target image whose shooting quality meets a preset requirement is determined in a plurality of candidate images, thereby improving image screening efficiency. The time for the user to browse and select the target image one by one is reduced, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, thereby improving the accuracy of the target image selection and improving. The user experience.

FIG. 1 is a first schematic flowchart of an image screening method according to an embodiment of the present disclosure. The method in FIG. 1 can be performed by a terminal device, which can be a mobile terminal such as a smart phone or a tablet computer, or a computer. A fixed terminal, as shown in FIG. 1, the method includes at least the following steps:

S101. Acquire a plurality of candidate images obtained by photographing, wherein each candidate image includes a plurality of target objects and each candidate image includes the same plurality of target objects, that is, the plurality of candidate images are for the same plurality of target objects at different times. The similarity between the two alternative images is relatively high; specifically, the multiple candidate images may be directly captured by the mobile terminal, or may be captured by a dedicated camera device, In the case of the imaging device, it is necessary to transmit a plurality of candidate images obtained by the imaging to the terminal device in advance.

S102, extracting key features of each target object from the candidate images, respectively performing shooting quality analysis on each candidate image according to the extracted key features, and obtaining a shooting quality analysis result of the candidate image; specifically, adopting a key feature extraction manner The quality of each candidate image is analyzed separately, and each candidate image corresponds to one shooting quality analysis result.

S103. Select a target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image.

In the embodiment provided by the present application, by performing image quality analysis on a plurality of candidate images, a target image whose shooting quality meets a preset requirement is determined in a plurality of candidate images, thereby improving image screening efficiency and reducing user browsing of multiple candidate images one by one. The time of the target image is selected, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience.

For each candidate image, after the key feature extraction is performed on the candidate image, for each of the extracted key features, the quality of each key feature needs to be separately analyzed, thereby obtaining the quality of the candidate image. The analysis result, specifically, as shown in FIG. 2, the above S102 extracts key features of each target object from the candidate images, and performs quality analysis on each candidate image according to the extracted key features to obtain the image quality of the candidate image. The results of the analysis include:

S1021: Extract, for each candidate image, key features of each target object from the candidate image; specifically, may select, for a candidate image that includes a different type of target object and a key feature of the target object that needs to be extracted. Correspondence between the two, for example, for the captured portrait photo, the key features may be facial features, such as eye features, mouth features, etc., in this case, for each candidate image, need to prepare Extracting the eye features of each portrait in the selected image also requires extracting the mouth features of each portrait from the candidate images.

S1022, performing quality evaluation and identification on each of the extracted key features, and obtaining a quality evaluation and recognition result; wherein the quality evaluation and recognition process is specifically: determining, for each key feature, whether the key feature has a preset shooting unqualified item, The key feature extracted is the condition of the eye feature, whether the eye feature of each person image has a closed eye phenomenon, and whether the extracted key feature is a mouth feature, and whether the mouth feature of each person image has a no-face band Smile phenomenon.

S1023: Determine a shooting quality analysis result of the candidate image according to the quality evaluation result of each key feature.

The S1023 determines the shooting quality analysis result of the candidate image according to the quality evaluation and recognition result of each key feature, and specifically includes:

The candidate image is weighted and scored according to the quality evaluation recognition result of each key feature, and the obtained scoring result is used as the shooting quality analysis result of the candidate image.

Specifically, the method for weighting the average value is used to evaluate the recognition result according to the quality of each key feature, and the shooting quality score of the candidate image is calculated, specifically: if the type of the extracted key features is multiple, according to various types of key features. The priority is set to the corresponding weight coefficient for the key feature, and the calculation formula of the shooting quality score of the candidate image is:

Where y represents the shooting quality score of the candidate image, A _i represents the weighting coefficient of the i-th key feature, x _i represents the number of abnormalities of the i-th key feature, and n represents the number of types of key features.

Among them, due to the abnormality of different types of key features, the degree of influence on the quality of shooting is different. For example, the closed eye phenomenon in portrait photos has a greater impact on the quality of shooting, while the phenomenon of no smile in portrait photos has less influence on the quality of shooting. Therefore, the weight coefficient corresponding to the eye feature may be greater than the weight coefficient corresponding to the mouth feature. At this time, the score of one eye feature abnormality in the candidate image needs to be deducted is greater than the one that needs to be deducted when the mouth feature is abnormal. The score, for example, the total score in the calculation formula of the photographing quality score of the above-described candidate image is set to 100 points, and it is recognized that one eye feature is abnormally deducted by one point, and that one time of the mouth feature is abnormally deducted by one point.

As shown in FIG. 3, the above S103 selects a target image from a plurality of candidate images according to the result of the image quality analysis of each candidate image, and specifically includes:

S1031, sorting the shooting quality of the plurality of candidate images according to the shooting quality analysis result of each candidate image; specifically, for the case where the scoring result is used as the shooting quality analysis result of each candidate image, according to the shooting quality score is large The quality of the shots of multiple candidate images is sorted in a small order.

S1032, selecting a preset number of candidate images as the target image according to the order of shooting quality from high to low. Specifically, the higher the shooting quality score of the candidate image, the higher the shooting quality of the candidate image, the candidate image. The more advanced the sorting is, the specific image with the highest shooting quality can be used as the target image. In this case, the preset number is equal to 1, and multiple candidate images with the highest shooting quality can be used as the target image. The preset number is greater than or equal to 2, so that the user can select an alternative image as the target image according to actual needs.

Further, in consideration of the possibility that all the candidate images do not meet the preset shooting quality condition, in order to ensure the quality of the final determined target image, based on this, the above S1032 selects the pre-order according to the order of the shooting quality from high to low. After setting the number of candidate images as the target image, it also includes:

Determining whether the selected shooting quality of the at least one target image meets the preset condition; specifically, determining whether the shooting quality score of each target image is greater than a preset threshold.

If not, generate prompt information suggesting that the user re-photograph; specifically, if the shooting quality score of each target image is less than a preset threshold, indicating that all candidate images do not meet the preset shooting quality condition, at this time, a prompt is required The user re-photographs, and then performs the shooting quality analysis on the candidate image obtained by the latest shooting, and determines whether the candidate image obtained by the latest shooting meets the preset shooting quality condition according to the obtained shooting quality analysis result until at least one matching pre-selection is selected. Set the target image of the shooting quality condition to select an alternative image with better shooting quality.

Further, as shown in FIG. 4, the foregoing S103, after selecting the target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image, further includes:

S104. When the image sharing request is detected, recommend the selected target image to the user. Specifically, after selecting the target image from the plurality of candidate images, the user may select the candidate image when sharing the candidate image on the social platform. The target image is recommended to the user, so that the quality of the image shared by the user meets the preset requirement, and the user is prevented from sharing the image whose shooting quality does not meet the preset requirement to the social platform, thereby avoiding a bad user experience.

The image screening method in the embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target objects; and extracts key features of each target object from the candidate images, respectively, according to the extracted key features. Performing shooting quality analysis on each candidate image to obtain a shooting quality analysis result of the candidate image; and selecting a target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image. By performing image quality analysis on multiple candidate images, the target image whose shooting quality meets the preset requirements is determined in multiple candidate images, thereby improving image screening efficiency and reducing the time for the user to browse and select the target images one by one. The candidate image that does not meet the preset requirements due to the user's selection error is avoided as the target image, which improves the accuracy of the target image selection and improves the user experience.

The image filtering method described in the above-mentioned FIG. 1 to FIG. 4 is based on the same technical concept. Another embodiment of the present application further provides an image screening method, and FIG. 5 is the fifth image filtering method provided by the embodiment of the present application. The process flow diagram can also be executed by the terminal device. The terminal device can be a mobile terminal such as a smart phone or a tablet computer, or can be a fixed terminal such as a computer. As shown in FIG. 5, the process includes:

S501. Acquire a plurality of candidate images obtained by shooting, where each candidate image includes multiple target faces and each candidate image includes the same multiple target faces; specifically, for a multi-person group photo application scenario, Each candidate image includes multiple participants who participate in the photo session.

S502, extracting key features of each target face from the candidate images, respectively performing shooting quality analysis on each candidate image according to the extracted key features, and obtaining a shooting quality analysis result of the candidate image; specifically, based on face recognition technology According to the method of key feature extraction, the quality of each candidate image is analyzed separately, and each candidate image corresponds to a shooting quality analysis result.

S503. Select a target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image.

In the embodiment provided by the present application, by performing image quality analysis on a plurality of candidate images, a target image whose shooting quality meets a preset requirement is determined in a plurality of candidate images, thereby improving image screening efficiency and reducing user browsing of multiple candidate images one by one. And select the time of the target image, and avoid the candidate image that does not meet the preset requirement as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience, especially for multi-person In the application scenario of the group photo, the more people participate in the photo shooting, the more difficult it is for the user to browse and select the target images one by one, so the image screening method can greatly reduce the difficulty of selecting the target image. Greatly improve the accuracy of target image selection.

For each candidate image, after performing key feature extraction on the candidate image, taking the eye feature of the target face as an example, for each extracted eye feature of each target face, it is necessary to separately The eye feature is subjected to shooting quality analysis, and the shooting quality analysis result of the candidate image is obtained. Specifically, as shown in FIG. 6 , the above S502 respectively extracts key features of each target face from the candidate image, according to the extracted The key features are used to analyze the quality of each candidate image, and the results of the quality analysis of the candidate image are obtained, including:

S5021. For each candidate image, extract at least an eye feature of each target face from the candidate image.

S5022: determining, according to the extracted eye features, an abnormal number of eye opening degrees in the candidate image that does not meet the preset eye opening degree; specifically, determining the target according to the degree of opening of each eye feature Whether there is a closed eye phenomenon on the face, if the closed eye phenomenon is found, the number of abnormalities for the eye feature is increased by one.

S5023: Determine a shooting quality analysis result of the candidate image according to the determined abnormal number.

It should be noted that, in the specific implementation, it is also possible to extract the mouth features of each target face at the same time, or extract other key feature features of each target face, which are all within the protection scope of the present application.

The S5023 determines the shooting quality analysis result of the candidate image according to the determined abnormal number, which specifically includes:

The weight of the shooting quality of the candidate image is weighted and scored according to the determined number of abnormalities;

The obtained scoring result is taken as the result of the photographing quality analysis of the candidate image.

Specifically, the method for weighting the average value is used to calculate the shooting quality score of the candidate image according to the number of abnormalities for each key feature, specifically: taking the extracted key features including the eye feature and the mouth feature of the target face as an example. According to the priority of the eye feature and the mouth feature, the weight coefficient of the eye feature and the weight coefficient of the mouth feature are respectively set, and the calculation formula of the shooting quality score of the candidate image is: y=total score-(β×a +μ×b), where y represents the shooting quality score of the candidate image, β represents the weighting coefficient of the eye feature, μ represents the weighting coefficient of the mouth feature, a represents the number of abnormalities in the appearance of the eye feature, and b represents the mouth. The number of abnormalities in which the feature appears.

Among them, due to the abnormality of different types of key features, the degree of influence on the quality of shooting is different. For example, the closed eye phenomenon in portrait photos has a greater impact on the quality of shooting, while the phenomenon of no smile in portrait photos has less influence on the quality of shooting. Therefore, the weight coefficient corresponding to the eye feature may be greater than the weight coefficient corresponding to the mouth feature. At this time, the score of one eye feature abnormality in the candidate image needs to be deducted is greater than the one that needs to be deducted when the mouth feature is abnormal. The score, for example, the total score in the calculation formula of the photographing quality score of the above-described candidate image is set to 100 points, and it is recognized that the eye feature is abnormally deducted by 1 point, that is, the weight coefficient of the eye feature is 1.0, and the mouth is recognized once. The feature of the part is abnormally deducted by 0.5 points, that is, the weight coefficient of the mouth feature is 0.5.

The S503 selects the target image from the plurality of candidate images according to the result of the image quality analysis of each candidate image, and specifically includes:

According to the scoring result of each candidate image, the candidate image with the highest score is taken as the target image.

Specifically, for the case where the scoring result is used as the result of the photographing quality analysis of each candidate image, the photographing quality of the plurality of candidate images is sorted in descending order of the photographing quality score, and the photographing quality score of the candidate image is higher. The higher the shooting quality of the candidate image, the higher the ranking of the candidate images. In the specific implementation, the candidate image with the highest shooting quality score can be used as the target image, or the shooting quality score can be changed from large to small. The order selects a plurality of candidate images that are ranked first as the target image, so that the user can select an alternative image as the target image according to actual needs.

Further, considering that there may be a case where all the candidate images do not meet the preset shooting quality condition, in order to ensure the quality of the final determined target image, based on the above, the score according to the scoring result of each candidate image is the highest. After the candidate image is used as the target image, it also includes:

Determining whether the shooting quality score of the selected target image is greater than a preset threshold; wherein the preset threshold may be a system default or may be obtained according to a user setting request.

In the embodiment provided by the present application, after detecting a continuous shooting operation on a plurality of target faces, the shooting quality analysis is automatically performed on the plurality of candidate images obtained by the shooting, and the shooting quality of all the candidate images is found to be inconsistent. The preset condition automatically reminds the user to take a photo again, so that during the photographing process, the captured image is automatically analyzed for the quality of the captured image. Once the quality of all the candidate images is found to meet the preset conditions, the photo is taken at this time. The personnel have not been disbanded, and can continue to take new alternative images, so as to avoid finding an ideal photo of the photos in the subsequent image sharing process, and then solve the problem that the people who participated in the big photo album have been disbanded and cannot continue to shoot new ones. The problem with the alternate image.

Further, after the S503 selects the target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image, the method further includes:

When the image sharing request is detected, the selected target image is recommended to the user. For example, if it is determined that the user needs to select one of the plurality of candidate images to share with the circle of friends or the group of friends, the selected target image may be recommended to the user, so that the quality of the image shared by the user meets the preset. It is required to prevent users from sharing images whose shooting quality does not meet the preset requirements on the social platform, thereby avoiding a bad user experience.

For example, for an application scene of a multi-person group photo, as shown in FIGS. 7a to 7d, four candidate images are captured, and each candidate image includes nine target faces, specifically:

In FIG. 7a, key features of each target face (such as eye features and mouth features) are extracted from the candidate images, and the quality of each candidate image is analyzed according to the extracted key features, and it is known that the eye features appear. The number of abnormalities is 2 (ie, left 1 and left 2 in the rear row), and the number of abnormalities in the mouth feature is 3 (ie, front left 1, left 3, and right 1). If the above scoring mechanism is followed, the candidate image The result of the photographing quality analysis is that the photographing quality score is: y=100-(1.0×2+0.5×3)=96.5.

In FIG. 7b, key features of each target face (such as eye features and mouth features) are extracted from the candidate images, and the quality of each candidate image is analyzed according to the extracted key features, and it is known that the eye features appear. The number of abnormalities is 2 (ie, left 1 and left 2 in the rear row), and the number of abnormalities in the mouth feature is 1 (ie, 1 in the front row). If the scoring mechanism is used, the result of the shooting quality analysis of the candidate image is The shooting quality score is: y = 100 - (1.0 × 2 + 0.5 × 1) = 97.5.

In FIG. 7c, key features of each target face (such as eye features and mouth features) are extracted from the candidate images, and the quality of each candidate image is analyzed according to the extracted key features, and it is known that the eye features appear. The number of abnormalities is 0, and the number of abnormalities of the mouth feature is 1 (ie, the left side of the front row is 1). If the above scoring mechanism is followed, the shooting quality analysis result of the candidate image is the shooting quality score: y=100-( 1.0×0+0.5×1)=99.5.

In FIG. 7d, key features of each target face (such as eye features and mouth features) are extracted from the candidate images, and the quality of each candidate image is analyzed according to the extracted key features, and it is known that the eye features appear. The number of abnormalities is 2 (ie, left 1 and left 2 in the rear row), and the number of abnormalities in the mouth feature is 2 (ie, left 1 and right 1 in the front row). If the scoring mechanism is used, the quality of the candidate image is taken. The result of the analysis is that the photographing quality score is: y=100-(1.0×2+0.5×2)=97.0.

Based on the photographing quality scores of the respective alternative images in FIGS. 7a to 7d, the photographing quality score of the candidate image shown in FIG. 7c is the highest, and therefore, the candidate image shown in FIG. 7c is taken as the target image.

The image screening method in the embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target faces; and extracts key features of each target face from the candidate images, respectively, according to the extracted The key feature performs the shooting quality analysis on each candidate image to obtain the shooting quality analysis result of the candidate image; and selects the target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image. By performing image quality analysis on multiple candidate images, the target image whose shooting quality meets the preset requirements is determined in multiple candidate images, thereby improving image screening efficiency and reducing the time for the user to browse and select the target images one by one. Avoiding the candidate image that does not meet the preset requirements as the target image due to the user's selection error, improving the accuracy of the target image selection and improving the user experience, especially for the application scene of multi-person photo group, The more people who participate in the big photo taking, the more difficult it is for the user to browse and select the target images one by one. Therefore, the image screening method can greatly reduce the difficulty of selecting the target image and greatly improve the accuracy of the target image selection. .

It should be noted that another embodiment of the present application and the embodiment of the present application are based on the same inventive concept. Therefore, the specific implementation of the embodiment may refer to the implementation of the foregoing method, and the repeated description is not repeated.

The image screening method described in the above-mentioned FIG. 1 to FIG. 6 is based on the same technical concept. The embodiment of the present application further provides an image screening device. FIG. 8 is a schematic diagram of a module composition of an image screening device according to an embodiment of the present application. The apparatus is configured to perform the image screening method described in FIG. 1 to FIG. 6. As shown in FIG. 8, the apparatus includes: an alternative image acquisition module 801, a shooting quality analysis module 802, and a target image selection module 803, and an alternative image acquisition module 801. The shooting quality analysis module 802 and the target image selection module 803 are sequentially connected.

In a specific embodiment, the candidate image acquisition module 801 is configured to acquire a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

The shooting quality analysis module 802 is configured to extract key features of each target object from the candidate images, perform shooting quality analysis on each of the candidate images according to the extracted key features, to obtain the candidate. Image quality analysis results;

The target image selection module 803 is configured to select a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.

Optionally, the foregoing shooting quality analysis module 802 is specifically configured to:

Extracting key features of each target object from the candidate image for each of the candidate images;

Performing quality evaluation and identification on each of the extracted key features to obtain a quality evaluation and recognition result;

A result of the photographing quality analysis of the candidate image is determined based on the quality evaluation recognition result.

Optionally, the foregoing shooting quality analysis module 802 is further specifically configured to:

And performing weighting addition scoring on the candidate image according to the quality evaluation recognition result, and using the obtained scoring result as a shooting quality analysis result of the candidate image.

Optionally, the target image selection module 803 is specifically configured to:

Sorting the shooting quality of the plurality of candidate images according to the shooting quality analysis result of each of the candidate images;

A preset number of candidate images are selected as the target image in descending order of shooting quality.

Optionally, the foregoing apparatus further includes:

a prompting module, configured to: after selecting a preset number of candidate images as the target image in order of high to low shooting quality, determining whether the selected shooting quality of the at least one target image meets a preset condition; , generating a prompt message suggesting that the user re-photograph.

Optionally, the foregoing apparatus further includes:

A recommendation module is configured to recommend the selected target image to the user when the image sharing request is detected.

An image screening apparatus in an embodiment of the present invention acquires a plurality of candidate images obtained by photographing, wherein each candidate image includes a plurality of target objects; and extracts key features of each target object from the candidate images, respectively, according to the extracted key The feature performs a shooting quality analysis on each candidate image to obtain a shooting quality analysis result of the candidate image; and selects a target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image. By performing image quality analysis on multiple candidate images, the target image whose shooting quality meets the preset requirements is determined in multiple candidate images, thereby improving image screening efficiency and reducing the time for the user to browse and select the target images one by one. The candidate image that does not meet the preset requirements due to the user's selection error is avoided as the target image, which improves the accuracy of the target image selection and improves the user experience.

In another specific embodiment, the candidate image obtaining module 801 is configured to acquire a plurality of captured images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

The photographing quality analysis module 802 is configured to extract key features of each target face from the candidate images, perform shooting quality analysis on each of the candidate images according to the extracted key features, and obtain the preparation The quality of the image quality analysis of the selected image;

Extracting at least an eye feature of each target face from the candidate image for each of the candidate images;

Determining, according to each of the extracted eye features, an abnormal number of eye opening degrees in the candidate image that does not meet a predetermined eye opening degree;

A photographing quality analysis result of the candidate image is determined according to the abnormal number.

Performing weighting and scoring the shooting quality of the candidate image according to the abnormal number;

According to the scoring result of each of the candidate images, the candidate image with the highest score is taken as the target image.

Optionally, the foregoing apparatus further includes:

a prompting module, configured to determine whether a shooting quality score of the target image is greater than a preset threshold after the candidate image having the highest score is used as the target image according to the scoring result of each of the candidate images; if not, Generate a prompt message suggesting that the user take a photo again.

An image screening apparatus in another embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target faces; and extracts key features of each target face from the candidate images, respectively, according to the extraction The key features are obtained for each of the candidate images to obtain a quality analysis result of the candidate image, and the image quality analysis result of the candidate image is obtained; and the target image is selected from the plurality of candidate images according to the shooting quality analysis result of each candidate image. By performing image quality analysis on multiple candidate images, the target image whose shooting quality meets the preset requirements is determined in multiple candidate images, thereby improving image screening efficiency and reducing the time for the user to browse and select the target images one by one. Avoiding the candidate image that does not meet the preset requirements as the target image due to the user's selection error, improving the accuracy of the target image selection and improving the user experience, especially for the application scene of multi-person photo group, The more people who participate in the big photo taking, the more difficult it is for the user to browse and select the target images one by one. Therefore, the image screening method can greatly reduce the difficulty of selecting the target image and greatly improve the accuracy of the target image selection. .

Further, corresponding to the method shown in FIG. 1 to FIG. 6 , based on the same technical concept, the embodiment of the present application further provides an image screening device, which is used to perform the image screening method described above, as shown in FIG. 9 . .

The image filtering device may vary considerably depending on configuration or performance, and may include one or more processors 901 and memory 902 in which one or more storage applications or data may be stored. Among them, the memory 902 can be short-term storage or persistent storage. An application stored in memory 902 may include one or more modules (not shown), each of which may include a series of computer executable instructions in an image filtering device. Still further, the processor 901 can be arranged to communicate with the memory 902 to execute a series of computer executable instructions in the memory 902 on the image filtering device. The image screening device may also include one or more power sources 903, one or more wired or wireless network interfaces 904, one or more input and output interfaces 905, one or more keyboards 906, and the like.

In a specific embodiment, the image screening device includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and one or more programs can include one or more modules, and each The modules can include a series of computer executable instructions in an image filtering device, and are configured to be executed by one or more processors. The one or more programs are included for performing the following computer executable instructions:

Optionally, when the computer-executable instructions are executed, the extracting key features of each target object from the candidate images respectively, and performing shooting quality on each of the candidate images according to the extracted key features. Analysis, obtaining the result of the photographing quality analysis of the candidate image, comprising:

Optionally, when the computer-executable instructions are executed, determining the shooting quality analysis result of the candidate image according to the quality evaluation identification result, including:

Optionally, when the computer-executable instructions are executed, the selecting the target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images comprises:

Optionally, the computer executable instructions, when executed, further comprise instructions for: executing the following computer executable instructions:

After selecting a preset number of candidate images as the target image in order of shooting quality from high to low, determining whether the selected shooting quality of the at least one target image meets a preset condition;

If not, generate a prompt message suggesting that the user re-photograph.

After the target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images, the selected target image is recommended to the user when the image sharing request is detected.

The image screening device in an embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target objects; and extracts key features of each target object from the candidate images, respectively, according to the extracted key The feature performs a shooting quality analysis on each candidate image to obtain a shooting quality analysis result of the candidate image; and selects a target image from the plurality of candidate images according to the shooting quality analysis result of each candidate image. It can be seen that, by using the image screening device in the embodiment of the present application, the quality of the plurality of candidate images is analyzed, and the target image whose shooting quality meets the preset requirement is determined in the plurality of candidate images, thereby improving image screening efficiency and reducing user-to-multiple The candidate images are browsed one by one and the time of the target image is selected one by one, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience.

In another specific embodiment, an image screening device includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and one or more programs can include one or more modules, and Each module can include a series of computer executable instructions in an image filtering device, and configured to be executed by one or more processors. The one or more programs include instructions for:

Optionally, when the computer executable instructions are executed, the key features of each target face are respectively extracted from the candidate image, and each candidate image is captured according to the extracted key features. Quality analysis, obtaining the result of the photographing quality analysis of the candidate image, including:

Optionally, when the computer executable instructions are executed, determining, according to the abnormal number, a shooting quality analysis result of the candidate image, including:

Optionally, the computer executable instructions, when executed, also include instructions for performing the following computer executables:

After determining, according to the scoring result of each of the candidate images, the candidate image having the highest score as the target image, determining whether the shooting quality score of the target image is greater than a preset threshold;

If not, generate a prompt message suggesting that the user re-photograph.

An image screening device in another embodiment of the present application acquires a plurality of candidate images obtained by shooting, wherein each candidate image includes a plurality of target faces; and extracts key features of each target face from the candidate images, respectively, according to the extraction The key features are obtained for each of the candidate images to obtain a quality analysis result of the candidate image, and the image quality analysis result of the candidate image is obtained; and the target image is selected from the plurality of candidate images according to the shooting quality analysis result of each candidate image. It can be seen that, by using the image screening device in the embodiment of the present application, the quality of the plurality of candidate images is analyzed, and the target image whose shooting quality meets the preset requirement is determined in the plurality of candidate images, thereby improving image screening efficiency and reducing user-to-multiple The candidate images are browsed one by one and the time of the target image is selected one by one, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience, especially For the application scene of multi-person photo grouping, the more the number of people participating in the big photo taking, the more difficult it is for the user to browse and select the target images one by one, so the image screening method can greatly reduce the target image. The difficulty of selection greatly improves the accuracy of target image selection.

Further, corresponding to the method shown in FIG. 1 to FIG. 6 , based on the same technical concept, the embodiment of the present application further provides a storage medium for storing computer executable instructions. In a specific embodiment, the specific embodiment The storage medium may be a USB flash drive, an optical disk, a hard disk, or the like. The computer executable instructions stored in the storage medium can implement the following processes when executed by the processor:

Optionally, when the computer-executable instructions stored by the storage medium are executed by the processor, the extracting key features of each target object from the candidate images respectively, according to the extracted key features, each of the The candidate image is subjected to shooting quality analysis, and the shooting quality analysis result of the candidate image is obtained, including:

Optionally, when the computer-executable instructions stored by the storage medium are executed by the processor, determining the shooting quality analysis result of the candidate image according to the quality evaluation identification result, including:

Optionally, when the computer-executable instructions stored by the storage medium are executed by the processor, the selecting the target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images comprises:

Optionally, the computer executable instructions stored by the storage medium, when executed by the processor, further implement the following processes:

If not, generate a prompt message suggesting that the user re-photograph.

The computer executable instructions stored in the storage medium in the embodiment of the present application, when executed by the processor, acquire a plurality of captured candidate images, wherein each candidate image includes a plurality of target objects; and each target is extracted from the candidate images. The key features of the object are analyzed by taking the quality of each candidate image according to the extracted key features, and the shooting quality analysis result of the candidate image is obtained; and the target image is selected from the plurality of candidate images according to the shooting quality analysis result of each candidate image. It can be seen that, by using the storage medium in the embodiment of the present application, the quality of the plurality of candidate images is analyzed, and the target image whose shooting quality meets the preset requirement is determined in the plurality of candidate images, thereby improving the image screening efficiency and reducing the user's multiple options. The images are browsed one by one and the time of the target image is selected, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience.

In another specific embodiment, the storage medium may be a USB flash drive, an optical disk, a hard disk, or the like, and the computer executable instructions stored by the storage medium, when executed by the processor, can implement the following processes:

Optionally, when executed by the processor, the computer-executable instructions stored by the storage medium respectively extract key features of each target face from the candidate image, according to each of the extracted key features. Performing a shooting quality analysis on the candidate image to obtain a shooting quality analysis result of the candidate image, including:

Optionally, when the computer-executable instructions stored by the storage medium are executed by the processor, the determining, according to the abnormal number, the shooting quality analysis result of the candidate image, including:

If not, generate a prompt message suggesting that the user re-photograph.

The computer executable instructions stored in the storage medium in the embodiment of the present application, when executed by the processor, acquire a plurality of captured candidate images, wherein each candidate image includes a plurality of target faces; respectively extracting each candidate image from each of the candidate images The key features of the target face, the quality of each candidate image is analyzed according to the extracted key features, and the shooting quality analysis result of the candidate image is obtained; and the target is selected from the plurality of candidate images according to the shooting quality analysis result of each candidate image. image. It can be seen that, by using the storage medium in the embodiment of the present application, the quality of the plurality of candidate images is analyzed, and the target image whose shooting quality meets the preset requirement is determined in the plurality of candidate images, thereby improving the image screening efficiency and reducing the user's multiple options. The images are browsed one by one and the time of the target image is selected one by one, and the candidate image whose shooting quality does not meet the preset requirement is avoided as the target image due to the user's selection error, which improves the accuracy of the target image selection and improves the user experience, in particular, For the application scene of multi-person group photo shooting, the more people participate in the photo shooting, the more difficult it is for the user to browse and select the target images one by one, so the image screening method can greatly reduce the target image. Selecting the difficulty greatly improves the accuracy of the target image selection.

In the 1990s, improvements to a technology could clearly distinguish between hardware improvements (eg, improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (for process flow improvements). However, as technology advances, many of today's method flow improvements can be seen as direct improvements in hardware circuit architecture. Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented by hardware entity modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers program themselves to "integrate" a digital system on a single PLD without having to ask the chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, today, instead of manually making integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in programming development, but before compiling The original code has to be written in a specific programming language. This is called the Hardware Description Language (HDL). HDL is not the only one, but there are many kinds, such as ABEL (Advanced Boolean Expression Language). AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., are currently the most commonly used VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It should also be apparent to those skilled in the art that the hardware flow for implementing the logic method flow can be easily obtained by simply programming the method flow into the integrated circuit with a few hardware description languages.

The controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor. In the form of logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic. Those skilled in the art will also appreciate that in addition to implementing the controller in purely computer readable program code, the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding. The form of a microcontroller or the like to achieve the same function. Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component. Or even a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.

The system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

For the convenience of description, the above devices are described separately by function into various units. Of course, the functions of each unit may be implemented in the same software or software and/or hardware when implementing the present application.

Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system, or computer program product. Thus, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware. Moreover, the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block of the flowchart illustrations. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system, or computer program product. Thus, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment in combination of software and hardware. Moreover, the application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including storage devices.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

The above description is only an embodiment of the present application and is not intended to limit the application. Various changes and modifications can be made to the present application by those skilled in the art. Any modifications, equivalents, improvements, etc. made within the spirit and scope of the present application are intended to be included within the scope of the appended claims.

Claims

An image screening method, comprising:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

Extracting key features of each target object from the candidate image, performing a shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
The method according to claim 1, wherein said extracting key features of each target object from said candidate images respectively, and performing quality of each of said candidate images based on said extracted key features Analysis, obtaining the result of the photographing quality analysis of the candidate image, comprising:

Extracting key features of each target object from the candidate image for each of the candidate images;

Performing quality evaluation and identification on each of the extracted key features to obtain a quality evaluation and recognition result;

A result of the photographing quality analysis of the candidate image is determined based on the quality evaluation recognition result.
The method according to claim 2, wherein the determining a result of the photographing quality analysis of the candidate image according to the quality evaluation and recognition result comprises:

And performing weighting addition scoring on the candidate image according to the quality evaluation recognition result, and using the obtained scoring result as a shooting quality analysis result of the candidate image.
The method according to claim 1, wherein the selecting a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images comprises:

Sorting the shooting quality of the plurality of candidate images according to the shooting quality analysis result of each of the candidate images;

A preset number of candidate images are selected as the target image in descending order of shooting quality.
The method according to claim 4, wherein after selecting a preset number of candidate images as the target image in descending order of shooting quality, the method further comprises:

Determining whether the selected shooting quality of the at least one target image meets a preset condition;

If not, generate a prompt message suggesting that the user re-photograph.
The method according to claim 1, wherein the selecting the target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images further comprises:

When the image sharing request is detected, the selected target image is recommended to the user.
An image screening method, comprising:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

And extracting key features of each target face from the candidate images, performing shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
The method according to claim 7, wherein the extracting key features of each target face from the candidate images respectively, and capturing each of the candidate images according to the extracted key features Quality analysis, obtaining the result of the photographing quality analysis of the candidate image, including:

Extracting at least an eye feature of each target face from the candidate image for each of the candidate images;

Determining, according to each of the extracted eye features, an abnormal number of eye opening degrees in the candidate image that does not meet a predetermined eye opening degree;

A photographing quality analysis result of the candidate image is determined according to the abnormal number.
The method according to claim 8, wherein the determining the quality of the shooting quality analysis of the candidate image according to the number of abnormalities comprises:

Performing weighting and scoring the shooting quality of the candidate image according to the abnormal number;

The obtained scoring result is taken as the result of the photographing quality analysis of the candidate image.
The method according to claim 9, wherein the selecting a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images comprises:

According to the scoring result of each of the candidate images, the candidate image with the highest score is taken as the target image.
The method according to claim 10, further comprising: after the candidate image having the highest score as the target image, according to the scoring result of each of the candidate images, further comprising:

Determining whether a shooting quality score of the target image is greater than a preset threshold;

If not, generate a prompt message suggesting that the user re-photograph.
An image screening device, comprising:

An alternative image acquisition module, configured to acquire a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

a shooting quality analysis module, configured to respectively extract key features of each target object from the candidate image, perform shooting quality analysis on each of the candidate images according to the extracted key features, to obtain the candidate image Shooting quality analysis results;

And a target image selection module, configured to select a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
An image screening device, comprising:

An alternative image acquisition module, configured to acquire a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

a shooting quality analysis module, configured to respectively extract key features of each target face from the candidate image, perform shooting quality analysis on each of the candidate images according to the extracted key features, to obtain the candidate Image quality analysis results;

And a target image selection module, configured to select a target image from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
An image screening device, comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

Extracting key features of each target object from the candidate image, performing a shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
An image screening device, comprising:

Processor;

A memory arranged to store computer executable instructions that, when executed, cause the processor to:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

And extracting key features of each target face from the candidate images, performing shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.
A storage medium for storing computer executable instructions, wherein the executable instructions, when executed, implement the following processes:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target objects;

Extracting key features of each target object from the candidate image, performing a shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images based on the photographing quality analysis result of each of the candidate images.
A storage medium for storing computer executable instructions, wherein the executable instructions, when executed, implement the following processes:

Obtaining a plurality of candidate images obtained by shooting, wherein each of the candidate images includes a plurality of target faces;

And extracting key features of each target face from the candidate images, performing shooting quality analysis on each of the candidate images according to the extracted key features, to obtain a shooting quality analysis result of the candidate image;

A target image is selected from the plurality of candidate images according to the shooting quality analysis result of each of the candidate images.