CN111339964B

CN111339964B - Image processing method and device, electronic equipment and storage medium

Info

Publication number: CN111339964B
Application number: CN202010130108.8A
Authority: CN
Inventors: 黄青虬; 杨磊; 黄怀毅; 吴桐; 林达华
Original assignee: Beijing Sensetime Technology Development Co Ltd
Current assignee: Beijing Sensetime Technology Development Co Ltd
Priority date: 2020-02-28
Filing date: 2020-02-28
Publication date: 2024-07-16
Anticipated expiration: 2040-02-28
Also published as: CN111339964A

Abstract

The disclosure relates to an image processing method and device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a target image to be identified; performing face recognition on the target image by using the trained face recognition model to obtain a face recognition result of the target image; the face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image. According to the embodiment of the disclosure, the face can be identified by using the face identification model with higher accuracy.

Description

Image processing method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of computer vision, and in particular relates to an image processing method and device, electronic equipment and a storage medium.

Background

With the development of electronic technology, more and more work can be completed by using electronic equipment, for example, the electronic equipment can be used for automatically identifying the face, so that convenience is provided for people. At present, the accuracy of the face recognition technology exceeds that of human eyes, and the face recognition technology is further provided with a reliability condition for popularization.

In general, face recognition techniques rely on a large amount of labeled training data. As the data volume of training data becomes larger, the cost of labeling the training data becomes higher. This brings a very large limitation to the practical application of face recognition technology.

Disclosure of Invention

The present disclosure proposes an image processing technique.

According to an aspect of the present disclosure, there is provided an image processing method including:

Acquiring a target image to be identified;

Performing face recognition on the target image by using the trained face recognition model to obtain a face recognition result of the target image; the face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image.

In one or more possible implementations, the method further includes:

And searching related information of the face in the target image according to the face recognition result of the target image under the condition that the accuracy of the face recognition result of the target image is larger than a preset accuracy threshold, wherein the related information comprises one or more of identity information, track information and person images.

In one or more possible implementations, obtaining an expanded sample pool includes:

acquiring a first image which is not marked in at least one detection image;

labeling at least one face image in the first image according to the face recognition result and the image description information of the first image;

and adding the marked face image as a training sample into a sample pool, and expanding the sample pool to obtain the expanded sample pool.

In one or more possible implementations, before the acquiring the first image that is not marked in the at least one detection image, the method further includes:

acquiring a second image in the at least one detection image, wherein the second image comprises a face image;

labeling the face image in the second image according to the image description information of the second image;

And constructing the sample pool by taking the face image marked in the second image as a training sample.

In one or more possible implementations, the acquiring a second image of the at least one detection image includes:

Determining a first number of face images included in the detection images and a second number of identity marks included in image description information of the detection images aiming at one detection image in the at least one detection image;

in the case where the first number is equal to 1 and the second number is equal to 1, the detection image is determined as a second image.

In one or more possible implementations, the labeling the face image in the second image according to the image description information of the second image includes:

extracting an identity mark included in the image description information of the second image;

And marking the face image in the second image by taking the extracted identity mark as a label of the face image in the second image.

In one or more possible implementations, the method further includes:

training the face recognition model by using the face images marked in the second image to obtain a primarily trained face recognition model;

And carrying out face recognition on the first image by using the face recognition model after preliminary training to obtain a face recognition result of the first image.

In one or more possible implementations, the labeling at least one face image in the first image according to the face recognition result and the image description information of the first image includes:

And labeling a face image in the first image according to the face recognition result of the face image and the image description information of the first image under the condition that the face recognition result of the face image meets the preset labeling condition.

In one or more possible implementations, the preset labeling conditions include:

the accuracy of the face recognition result is larger than a preset accuracy threshold; and the face recognition result is matched with the identity mark included in the image description information of the first image.

In one or more possible implementations, after labeling the face image that satisfies the labeling condition, the method further includes:

Determining a third number of face images which are not marked in the first image, and determining a fourth number of identity marks which are not matched with the face recognition result of the face images in the image description information;

and marking the unmarked face images by using the unmatched identity marks under the condition that the third number is equal to 1 and the fourth number is equal to 1.

In one or more possible implementations, the method further includes:

And training the face recognition model by using the training samples in the expanded sample pool, and returning to the step of acquiring the first image in the at least one detection image until the training samples in the sample pool are not increased any more, so as to obtain the face recognition model after training.

According to an aspect of the present disclosure, there is also provided an image processing apparatus including:

the first acquisition module is used for acquiring a target image to be identified;

The recognition module is used for recognizing the face of the target image by using the trained face recognition model to obtain a face recognition result of the target image; the face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image.

In one or more possible implementations, the apparatus further includes:

The searching module is used for searching the related information of the face in the target image according to the face recognition result of the target image under the condition that the accuracy of the face recognition result of the target image is larger than a preset accuracy threshold, wherein the related information comprises one or more of identity information, whereabouts information and a person image.

In one or more possible implementations, the apparatus further includes:

The second acquisition module is also used for acquiring first images which are not marked in at least one detection image;

The labeling module is used for labeling at least one face image in the first image according to the face recognition result and the image description information of the first image;

The adding module is used for adding the marked face image into the sample pool as a training sample, and expanding the sample pool to obtain the expanded sample pool.

In one or more possible implementations, the second obtaining module is further configured to obtain a second image in the at least one detection image, where the second image includes a face image; the labeling module is further configured to label the face image in the second image according to the image description information of the second image; the adding module is further configured to construct the sample pool by using the face image marked in the second image as a training sample.

In one or more possible implementations, the second obtaining module is specifically configured to determine, for one detection image of the at least one detection image, a first number of face images included in the detection image and a second number of identities included in image description information of the detection image; in the case where the first number is equal to 1 and the second number is equal to 1, the detection image is determined as a second image.

In one or more possible implementation manners, the labeling module is specifically configured to extract an identity identifier included in the image description information of the second image; and marking the face image in the second image by taking the extracted identity mark as a label of the face image in the second image.

In one or more possible implementations, the apparatus further includes:

The first training module is used for training the face recognition model by using the face images marked in the second image to obtain a face recognition model after preliminary training; and carrying out face recognition on the first image by using the face recognition model after preliminary training to obtain a face recognition result of the first image.

In one or more possible implementation manners, the labeling module is specifically configured to label, for one face image in the first image, the face image according to a face recognition result of the face image and image description information of the first image, where it is determined that the face recognition result of the face image meets a preset labeling condition.

In one or more possible implementations, the preset labeling conditions include: the accuracy of the face recognition result is larger than a preset accuracy threshold; and the face recognition result is matched with the identity mark included in the image description information of the first image.

In one or more possible implementation manners, the labeling module is further configured to determine, after labeling the face images that meet the labeling condition, a third number of face images that are not labeled in the first image, and determine a fourth number of identity identifiers in the image description information that are not matched with a face recognition result of the face images; and marking the unmarked face images by using the unmatched identity marks under the condition that the third number is equal to 1 and the fourth number is equal to 1.

In one or more possible implementations, the apparatus further includes:

And the second training module is used for training the face recognition model by using the training samples in the expanded sample pool and returning to the step of acquiring the first image in the at least one detection image until the training samples in the sample pool are not increased any more, so as to obtain the face recognition model after training.

According to an aspect of the present disclosure, there is provided an electronic apparatus including:

A processor;

a memory for storing processor-executable instructions;

Wherein the processor is configured to: the above image processing method is performed.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described image processing method.

In the embodiment of the disclosure, the target image to be identified can be obtained, and then the face identification of the target image is performed by using the trained face identification model, so that the face identification result of the target image is obtained. The face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in the first image according to the face recognition result and the image description information of the first image. Therefore, the sample pool can be continuously expanded by automatically labeling the face image through the image description information, and further the face recognition model obtained through training of a large number of training samples in the sample pool has high accuracy, and an accurate face recognition result can be obtained.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.

Fig. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure.

Fig. 2 shows a flow chart of an extended sample cell process according to an embodiment of the present disclosure.

Fig. 3 shows an exemplary schematic diagram according to an embodiment of the present disclosure.

Fig. 4 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure.

Fig. 5 shows a block diagram of an example of an electronic device, according to an embodiment of the disclosure.

Fig. 6 shows a block diagram of an example of an electronic device, according to an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

According to the image processing scheme provided by the embodiment of the disclosure, the target image to be identified can be obtained, and then the face recognition of the target image is performed by using the trained face recognition model, so that the face recognition result of the target image is obtained. The face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image. By the method, the face recognition model obtained by training the automatically marked training sample can be used for carrying out face recognition on the target image, and a face recognition result with high accuracy is obtained.

In the related art, a face recognition model is obtained by training a large number of training samples with labels. Some implementations are to obtain training samples by means of manual labeling, but training the face recognition model requires a large number of training samples, so that the manual labeling consumes a large amount of human resources. Some implementations are ways in which the face recognition model is trained by combining a partially labeled training sample with a training sample labeled, i.e., semi-supervised training. However, the semi-supervised training method still needs to manually label part of training samples, and training the face recognition model by using unlabeled training samples cannot guarantee the accuracy of the face recognition model, and is greatly limited in practical application. According to the embodiment of the disclosure, the human face recognition model can be obtained by training the training sample with automatic labeling, so that the training sample can be added under the condition of no need of manual labeling, the performance of the human face recognition model is improved, the human face recognition model after training is utilized to carry out human face recognition on the target image, and the human face recognition result with high accuracy can be obtained.

The technical scheme provided by the embodiment of the disclosure can be applied to the expansion of application scenes such as face recognition, neural network training, sample pool expansion, security monitoring and the like, and the embodiment of the disclosure is not limited to the expansion. For example, people in multimedia stories, such as actors in movies, television shows, etc., may be identified. For another example, a person in the monitoring screen may be identified, such as searching the monitoring video for a video segment containing the occurrence of a suspect.

Fig. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure. The image processing method may be performed by a terminal device, a server, or other type of electronic device, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like. In some possible implementations, the image processing method may be implemented by way of a processor invoking computer readable instructions stored in a memory. The image processing method of the embodiment of the present disclosure will be described below taking an electronic device as an execution subject.

Step S11, obtaining a target image to be identified.

In the embodiment of the disclosure, the electronic device may have an image acquisition function, and may acquire a target image to be identified by performing image acquisition on a scene. Or the electronic device may obtain the target image to be identified from another device, for example, the electronic device may obtain one or more target images to be identified from a device such as a camera device, a monitoring device, or a network server. The target image may have a face image therein, so that the target image to be recognized may be understood as an image waiting for face recognition.

Step S12, performing face recognition on the target image by using the trained face recognition model to obtain a face recognition result of the target image; the face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image.

In the embodiment of the disclosure, the acquired target image can be input into a face recognition model after training, and the face recognition model is utilized to perform face recognition on the target image, so that a face recognition result is output by the face recognition model. The face recognition result may be an identity corresponding to the face in the target image, for example, a name, a certificate number, etc. The face recognition model is obtained by training based on training samples in the expanded sample pool, the training samples of the face recognition model are face images which are automatically marked, a large number of face images can be automatically marked through the face recognition result of the first image and the image description information, so that human resources are saved, and the sample pool of the face recognition model is provided with a large number of training samples with marks. The face recognition model obtained by training a large number of labeled training samples has higher face recognition performance and can obtain accurate face recognition results.

In one possible implementation manner, in the case that the accuracy of the face recognition result of the target image is greater than a preset accuracy threshold, relevant information of the face in the target image is searched according to the face recognition result of the target image, and the relevant information comprises one or more of identity information, whereabouts information and a person image.

In this implementation manner, the face recognition model may further output accuracy of the face recognition result, so that after the face recognition result of the target image is obtained, the accuracy of the face recognition result of the target image may be compared with a preset accuracy threshold to determine whether the face recognition result of the target image is reliable. Under the condition that the accuracy of the face recognition result of the target image is larger than a preset accuracy threshold, the obtained face recognition result of the target image can be considered to be accurate, and further, the related information of the face in the target image can be searched in the database according to the face recognition result of the target image, so that more information of the face in the target image can be obtained. Wherein the related information comprises one or more of identity information, whereabouts information and character images.

For example, in the case that the accuracy of the face recognition result of the target image is greater than the preset accuracy threshold, the identity information of the face in the target image may be obtained according to the face recognition result of the target image, for example, information such as an identity card number, a work, an age, an address, etc. may be obtained, so that more detailed information of the person to which the face belongs may be further obtained. For example, in the security scene, the track information of the person to which the face belongs in the target image can be obtained according to the face recognition result of the target image, for example, the action route, the frequent place, the last place and the like of the person to which the face belongs in the target image, so that the person to which the face belongs in the target image can be tracked, security personnel can be assisted in processing cases, and the case handling efficiency is improved.

The face recognition model in the embodiment of the disclosure is obtained by training based on training samples in an expanded sample pool, and the expanded sample pool provides a large number of training samples for the face recognition model. The procedure for obtaining the expanded cuvette will be described below.

FIG. 2 shows a flow chart of an extended sample cell process according to an embodiment of the present disclosure, which may include the steps of:

step S21, obtaining first images which are not marked in at least one detection image.

In the embodiment of the disclosure, the detected image may have a face image therein, and the detected image is divided according to whether the face image in the detected image has a label, where the detected image having one or more unlabeled face images may be a first image. The detected image may be derived from an advertisement, a poster, a movie or a television show, an album, etc., and typically has corresponding image description information. The image description information may be a text description of the detected image, for example, in the case where the detected image is a movie episode, the image description information may be a movie character, a scenario introduction, or the like.

And S22, labeling at least one face image in the first image according to the face recognition result and the image description information of the first image.

In the embodiment of the disclosure, face recognition can be performed on the face image in the first image to obtain face recognition results of one or more face images, and one face image can correspond to one face recognition result. The face recognition result may be an identity corresponding to a face in the face image, for example, a name, a certificate number, etc. In some implementations, in a case where one or more face images in the first image cannot be identified, the corresponding face recognition result may be null or an identifier indicating that the face cannot be identified, and embodiments of the disclosure do not limit specific implementations. According to the face recognition result of the face images in the first image and the image description information of the first image, the labels of one or more face images in the first image can be determined, so that the one or more face images in the first image can be marked. For example, the face recognition result of a face image and the image description information of the first image may be matched, and when the face recognition result of the face image is matched with the image description information of the first image, the face recognition result of the face image may be used as a label of the face image, and the face image may be labeled. The fact that the face recognition result is matched with the image description information of the first image can be understood that the image description information of the first image includes the face recognition result.

Here, the face image in the first image may be recognized using a face recognition model. The face recognition model can be obtained by training samples in a sample pool, wherein the training samples in the sample pool can be obtained by manual labeling or automatic labeling. The automatic labeling manner will be described below, and will not be described again here.

And S23, adding the labeled face image as a training sample into a sample pool, and expanding the sample pool, wherein the training sample in the expanded sample pool is used for training the face recognition model so as to obtain the face recognition model after training.

In the embodiment of the disclosure, the labeled face image can be added into the sample pool as a training sample, the training sample in the sample pool can be used for training the face recognition model, and the sample pool can be expanded by continuously adding the labeled face image into the sample pool as the training sample. And then training the face recognition model by using the training samples in the expanded sample pool to obtain the face recognition model after training. By continuously expanding the training samples in the sample pool, the face recognition model can have a large number of training samples, so that the accuracy of the face recognition model after training can be improved.

In the embodiment of the disclosure, the training samples in the sample pool can be expanded to improve the accuracy of the face recognition model. Here, the initial sample cell may also be obtained by means of automatic labeling. The process of obtaining training samples in an initial sample pool is described below in one implementation.

In one possible implementation manner, a second image in the at least one detection image may be acquired, where the second image includes a face image, then the face image in the second image is labeled according to image description information of the second image, and then the face image labeled in the second image is used as a training sample to construct a sample pool.

In this implementation, a second image having one face image among the plurality of detection images may be acquired. For a second image with one face image, a label of the face image in the second image may be determined according to image description information of the second image, for example, a person name in the image description information of the second image may be used as a label of the face image in the second image. And then labeling the face image in the second image by using the determined label, wherein the labeled face image can be used as a training image and a sample pool is constructed. By the method, the face images in the second image can be marked according to the image description information of the second image, so that a sample pool for training the face recognition model can be automatically constructed, and human resources are saved.

In one example of the present implementation, for one of the at least one detection image, a first number of face images included in the detection image and a second number of identity identifiers included in image description information of the detection image are determined. In the case where the first number is equal to 1 and the second number is equal to 1, the detection image is determined as the second image.

In this example, the number of face images included in the detection image may be determined by face detection for one of the at least one detection image, and the number of face images included in the detection image may be the first number. The number of the identity marks included in the image description information of the detection image may be determined by performing identity mark detection on the image description information of the detection image, and the number of the identity marks included in the image description information may be the second number. In the case where the first number is equal to 1 and the second number is equal to 1, that is, in the case where the detected image includes only one face image and, at the same time, only one identification is included in the image description information of the detected image, the detected image may be regarded as the second image. In this way, the second image in the detection image can be quickly determined.

In one example of the implementation manner, under the condition that the face image in the second image is marked according to the image description information of the second image, the identity mark included in the image description information of the second image is extracted, and then the extracted identity mark is used as a label of the face image in the second image to mark the face image in the second image.

In this example, the second image may have a face image, and the image description information of the second image has an identity, so that the identity in the image description information may be considered to be the identity of the face image in the second image, so that the identity included in the image description information of the second image may be extracted, and then the extracted identity may be determined as a label of the face image in the second image, and the face image in the second image may be labeled by using the identity. In this way, the face image in the second image can be automatically marked through the image description information of the second image, so that the sample pool can be built by using the face image marked in the second image, and the automatic construction of the sample pool is realized.

In one example of this implementation, after labeling the face image in the second image, the face recognition model may be trained using the face image labeled in the second image, to obtain a face recognition model after preliminary training. And then, the face recognition of the first image can be carried out by utilizing the face recognition model after preliminary training, and the face recognition result of the first image is obtained.

In this example, the face recognition model may be trained by using the face image marked in the second image, that is, the face recognition model may be trained by using the training image in the primarily constructed sample pool, for example, the training image in the primarily constructed sample pool may be output to the face recognition model, the face recognition model may be used to perform face recognition on the training image, to obtain the face recognition result of the training image, then the face recognition result of the training image may be compared with the label of the training image to obtain the comparison result, and the network parameter of the face recognition model may be adjusted according to the comparison result, so that the face recognition result of the training image approaches to the label of the training image. And training the face recognition model by using the face images marked in the second image, so that the face recognition model after preliminary training can be obtained. After the face recognition model after the preliminary training is obtained, the face recognition of the first image can be performed by using the face recognition model after the preliminary training, and the face recognition result of the first image is obtained. In this way, the face image marked in the second image can be used for primarily training the face recognition model, and the face recognition model which is primarily trained is used for deducing other face images which do not enter the sample pool, namely, the face image in the first image is recognized, so that the recognition result of the face image in the first image can be accurately obtained.

In the embodiment of the disclosure, at least one face image may be labeled according to the face recognition results of the plurality of face images and the image description information of the first image. The process of labeling at least one face image in the first image is described below by way of one possible implementation.

In one possible implementation manner, for one face image of the plurality of face images in the first image, the face image may be labeled according to the face recognition result of the face image and the image description information of the first image, where it is determined that the face recognition result of the face image meets a preset labeling condition.

In this implementation manner, the face detection may be performed on a plurality of face images in the first image by using the face recognition model that is primarily trained, so as to obtain a face detection result of the plurality of face images. For one face image of the plurality of face images in the first image, whether the face recognition result of the face image meets the preset labeling condition can be judged according to the face recognition result of the face image and the image description information of the first image. And under the condition that the face recognition result of the face image meets the preset labeling condition, labeling the face image.

Here, the preset labeling conditions may include: the accuracy of the face recognition result is larger than a preset accuracy threshold, and the face recognition result is matched with the identity mark included in the image description information of the first image. Under the condition that whether the face identification result of the face image meets the preset labeling condition is judged, the accuracy of the face identification result can be compared with a preset accuracy threshold value, and whether the accuracy of the face identification result is larger than the accuracy threshold value is judged. Meanwhile, the face recognition result can be compared with the identity mark included in the image description information of the first image, and whether the face recognition result is matched with the identity mark included in the image description information of the first image or not is judged. When the accuracy of the face identification result of the face image is larger than a preset accuracy threshold, and the face identification result is matched with the identity identification included in the image description information of the first image, the face identification result of the face image can be determined to meet a preset labeling condition, the identity identification included in the image description information of the first image can be further determined to be a label of the face image, and the determined label can be utilized to label the face image. The preset accuracy threshold may be set according to an actual application scenario, for example, the accuracy threshold may be set to 0.85, 0.9, or the like. The face recognition model can output the face recognition result and the accuracy of the face recognition result, and the accuracy can represent the accuracy of the corresponding face recognition result. Generally, the higher the accuracy of the face recognition result is, the more accurate the face recognition result is, the lower the accuracy of the face recognition result is, and the more inaccurate the face recognition result is, so that whether the face recognition result is reliable can be judged by setting an accuracy threshold for the accuracy of the face recognition result.

The face image meeting the marking condition in the first image can be marked by determining whether the face recognition result of the face image in the first image meets the marking condition or not, so that after the face image meeting the marking condition in the first image is marked, the marked face image can be added into the sample pool as a training image, and the expansion of the sample pool is realized.

In one example of the implementation, after labeling the face images that meet the labeling condition, a third number of face images that are not labeled in the first image may be determined, and a fourth number of identities in the image description information that do not match the face recognition results of the plurality of face images may be determined. And under the condition that the third number is equal to 1 and the fourth number is equal to 1, marking the unmarked face images by using the unmatched identity marks.

In this example, after labeling the face images satisfying the labeling condition in the first image, the number of face images that are not labeled in the first image may be determined, and the number may be the third number. Accordingly, the number of the identities in the image description information of the first image, which does not match the face recognition results of the face images in the first image, may be determined, and the number may be the fourth number. Then, when the third number is equal to 1 and the fourth number is equal to 1, that is, when the number of face images not marked in the first image is one and the identity of the image description information of the first image, which is not matched with the face recognition results of the face images in the first image, is one, the identity of the image description information, which is not matched with the face recognition results of the face images in the first image, can be considered as the label of the face image not marked in the first image, and the marked face image is marked. In this way, the face image that is not marked in the first image can be marked.

In one possible implementation, the face recognition model is trained using training samples in the expanded sample pool, and the step of obtaining a first image including a plurality of face images in the at least one detected image is returned until the training samples in the sample pool are no longer increased.

In this implementation manner, the training samples in the sample pool after expansion can be utilized to train the face recognition model so as to improve the face recognition rate of the face recognition model, meanwhile, the step S11 can be returned to, the first image including a plurality of face images in the detected image can be obtained again, the training samples in the sample pool are continuously expanded until the training samples in the sample pool are not increased any more, in this way, the face images in the detected image can be automatically marked, the sample pool is continuously expanded, and the face recognition model obtained by the training samples in the sample pool after expansion can have higher face recognition accuracy.

Fig. 3 shows a block diagram of an example of image processing according to an embodiment of the disclosure. The image processing scheme provided by this example may include the steps of:

Step S301, a second image in the detection image is acquired.

Here, only one face image in the detected image may be determined by performing face detection on the detected image and identity detection on image description information of the detected image, and only one second image of the identity (e.g., a name) in the image description information may be determined.

Step S302, labeling the face image in the second image according to the description information of the second image, and constructing an initial sample pool by using the face image labeled in the second image.

Here, for the second image, only one face image is detected, and only one identity is mentioned in the image description information, it may be considered that the face image in the second image matches the identity in the image description information, that is, the label corresponding to the face image in the second image may be the identity only mentioned in the image description information. Further, an initial sample pool can be constructed by using the face image marked in the second image.

Step S303, training a face recognition model by using the initial sample pool, and carrying out face recognition on the first image which is not marked in the detection image by using the initially trained face recognition model to obtain a face recognition result.

Step S304, judging whether the accuracy of the face recognition result of the face image in the first image is larger than an accuracy threshold, and judging whether the face recognition result of the face image is matched with the identity in the image description information of the first image.

Step S305, when the accuracy of the face recognition result of the face image in the first image is greater than the accuracy threshold, and the face recognition result of the face image is matched with the identity in the image description information of the first image, taking the identity matched with the face recognition result as the label of the face image in the first image, and adding the face image marked in the first image into the sample pool.

Step S306, only one unlabeled face image is obtained, only a first image with an identity which is not matched with the face image in the image description information is obtained, the identity which is not matched with the face image in the image description information is used as a label of the unlabeled face image in the first image, and the labeled face image is added into the sample pool.

Here, after step S306 is performed, step S303 may be returned to further expand the training samples in the sample cell, and train the face recognition model on the basis of the expanded sample cell until the sample cell is no longer expanded. In this way, the face recognition model can be trained by using the identity mark in the image description and the face in the image, so that the face recognition model with higher accuracy (equivalent to the accuracy of the model obtained by using the full-label training sample) can be trained without additional manual labeling.

It will be appreciated that the above-mentioned method embodiments of the present disclosure may be combined with each other to form a combined embodiment without departing from the principle logic, and are limited to the description of the present disclosure.

In addition, the disclosure further provides an apparatus, an electronic device, a computer readable storage medium, and a program, where the foregoing may be used to implement any one of the image processing methods provided in the disclosure, and corresponding technical schemes and descriptions and corresponding descriptions referring to method parts are not repeated.

It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.

Fig. 4 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure, as shown in fig. 4, the apparatus including:

a first acquiring module 41, configured to acquire a target image to be identified;

The recognition module 42 is configured to perform face recognition on the target image by using the trained face recognition model, so as to obtain a face recognition result of the target image; the face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one face image in a first image according to the face recognition result and the image description information of the first image.

In one or more possible implementations, the apparatus further includes:

the accuracy of the face recognition result is larger than a preset accuracy threshold; and

And the face recognition result is matched with the identity mark included in the image description information of the first image.

In one or more possible implementations, the apparatus further includes:

In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.

Fig. 5 is a block diagram illustrating an apparatus 800 for observing behavior control, according to an example embodiment. For example, apparatus 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 5, apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the apparatus 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the apparatus 800 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, an orientation or acceleration/deceleration of the device 800, and a change in temperature of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including computer program instructions executable by processor 820 of apparatus 800 to perform the above-described methods.

The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured as the method described above.

The electronic device may be provided as a terminal, server or other form of device.

Fig. 6 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, electronic device 1900 may be provided as a server. Referring to FIG. 6, electronic device 1900 includes a processing component 1922 that further includes one or more processors and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by processing component 1922. The application programs stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, processing component 1922 is configured to execute instructions to perform the methods described above.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1932, including computer program instructions executable by processing component 1922 of electronic device 1900 to perform the methods described above.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as SMALLTALK, C ++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An image processing method, comprising:

Acquiring a target image to be identified;

Performing face recognition on the target image by using the trained face recognition model to obtain a face recognition result of the target image; the human face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one human face image in a first image according to the human face recognition result and the image description information of the first image;

wherein, obtain the sample cell after expanding, include:

acquiring a second image in at least one detection image, wherein the detection image has corresponding image description information, the image description information is a text description of the detection image, and the second image comprises a face image;

constructing the sample pool by taking the face image marked in the second image as a training sample;

acquiring a first image which is not marked in at least one detection image;

2. The method according to claim 1, wherein the method further comprises:

3. The method of claim 1, wherein the acquiring a second image of the at least one detected image comprises:

4. The method according to claim 1, wherein the labeling the face image in the second image according to the image description information of the second image includes:

5. The method according to any one of claims 1 to 4, further comprising:

6. The method according to any one of claims 1 to 5, wherein labeling at least one face image in the first image according to the face recognition result and the image description information of the first image includes:

7. The method of claim 6, wherein the preset labeling conditions comprise:

8. The method according to claim 6 or 7, characterized in that after labeling the face image satisfying the labeling condition, the method further comprises:

9. The method according to any one of claims 1 to 8, further comprising:

10. An image processing apparatus, comprising:

The recognition module is used for recognizing the face of the target image by using the trained face recognition model to obtain a face recognition result of the target image; the human face recognition model is obtained by training based on training samples in an expanded sample pool, and the training samples in the expanded sample pool are obtained by labeling at least one human face image in a first image according to the human face recognition result and the image description information of the first image;

wherein the apparatus further comprises:

The adding module is used for adding the marked face image as a training sample into a sample pool, expanding the sample pool and obtaining the expanded sample pool;

The second acquisition module is further configured to acquire a second image in at least one detection image, where the detection image has corresponding image description information, the image description information is a text description of the detection image, and the second image includes a face image;

The labeling module is further configured to label the face image in the second image according to the image description information of the second image;

The adding module is further configured to construct the sample pool by using the face image marked in the second image as a training sample.

11. The apparatus of claim 10, wherein the apparatus further comprises:

12. The apparatus according to claim 10, wherein the second obtaining module is specifically configured to determine, for one of the at least one detected image, a first number of face images included in the detected image and a second number of identities included in image description information of the detected image; in the case where the first number is equal to 1 and the second number is equal to 1, the detection image is determined as a second image.

13. The apparatus according to claim 10 or 12, wherein the labeling module is specifically configured to extract an identity identifier included in the image description information of the second image; and marking the face image in the second image by taking the extracted identity mark as a label of the face image in the second image.

14. The apparatus according to any one of claims 10 to 13, further comprising:

15. An electronic device, comprising:

A processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 9.

16. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 9.