CN113569676A

CN113569676A - Image processing method, image processing device, electronic equipment and storage medium

Info

Publication number: CN113569676A
Application number: CN202110805912.6A
Authority: CN
Inventors: 舒荣涛; 刘春秋; 谢洪彪
Original assignee: Beijing Sensetime Technology Development Co Ltd
Current assignee: Beijing Sensetime Technology Development Co Ltd
Priority date: 2021-07-16
Filing date: 2021-07-16
Publication date: 2021-10-29
Anticipated expiration: 2041-07-16
Also published as: WO2023284307A1; CN113569676B

Abstract

The method comprises the steps of responding to a first object identification instruction, obtaining a first object image and a target reference image of a target object acquired by local equipment, wherein the target reference image is obtained by updating a registration image based on the local object image, the registration image is an image of the target object acquired by remote equipment, and the registration image is used for object registration; and carrying out object recognition on the first object image based on the target reference image to obtain a first object recognition result. By utilizing the method and the device, the object identification accuracy, the passing rate and the application safety can be improved.

Description

Image processing method, image processing device, electronic equipment and storage medium

Technical Field

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

Background

With the development of computer vision technology, various applications based on image recognition are widely used, such as access control, attendance management, cash payment and the like based on face recognition. At present, the algorithm for face recognition matching in the related art is usually obtained by training based on images acquired by face recognition equipment. However, in practical applications, it often happens that the registered graph on the face recognition device and the graph to be recognized and matched come from different devices. For example, in a hotel, a factory, a dormitory, a campus, and other scenes, the usage mode of the face recognition device is often: a user uses an image on a mobile phone to remotely register in advance as a registration chart; then, when the face recognition device needs to be used, the user stands an image taken in front of the face recognition device as an object image. In such a scenario, due to differences among different devices, the optical properties of images such as brightness and definition of images shot by different devices are different, and thus, the problems of reduction of recognition accuracy, passing rate and application safety are brought.

Disclosure of Invention

The present disclosure provides an image processing method, an image processing apparatus, an electronic device, and a storage medium, which can improve object recognition accuracy, throughput, and application security in practical applications. The technical scheme of the disclosure is as follows:

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

responding to a first object identification instruction, acquiring a first object image and a target reference image of a target object acquired by local equipment, wherein the target reference image is obtained by updating a registration image based on the local object image, the registration image is an image of the target object acquired by remote equipment, and the registration image is used for object registration;

and carrying out object recognition on the first object image based on the target reference image to obtain a first object recognition result.

According to the technical scheme, the target reference image obtained by updating the registered image acquired by the remote equipment based on the local object image is combined to identify the object of the first object image to be identified acquired by the local equipment, so that the difference between different equipment can be effectively avoided, the acquired images have different optical attributes, and the object identification accuracy, the passing rate and the application safety are effectively improved.

Optionally, the target reference image includes at least one of:

selecting a first object image with the similarity with the registered image being more than or equal to a preset threshold value from the local object images;

selecting a first object image from the local object images, wherein the similarity between the first object image and the registered image is greater than or equal to a preset threshold value, and the image quality analysis result meets a preset quality condition;

the similarity between a first selected local object image and the registered image is greater than or equal to a preset threshold value, and the orientation information of the target object relative to the camera device is at least one object image with specified orientation information when the local object image is collected;

the similarity between the first local object image and the registered image is greater than or equal to a preset threshold value, and the time attribute information of the local object image during acquisition is matched with the acquisition time attribute information of the registered image;

the similarity between a first selected local object image and the registered image is greater than or equal to a preset threshold, the time when the local object image is acquired is the object image in a target time period, and the target time period is a time period when the execution frequency of preset operation is greater than or equal to a preset frequency;

selecting an object image with the highest similarity with the registered image from the local object images;

and selecting an object image having the highest sum of the similarity with the registered image and the weighted average of the corresponding numerical values of the biological detection results from the local object images.

According to the technical scheme, the registration image acquired by the remote equipment is updated by combining with at least one object image acquired by the local equipment, so that the flexibility of acquiring the target reference image can be improved on the basis of effectively ensuring the subsequent object identification passing rate and the application safety.

Optionally, the method further includes:

acquiring a second object image and the registration image of the target object acquired by the local equipment in response to a second object identification instruction, wherein the second object identification instruction is an object identification instruction triggered before the first object identification instruction;

carrying out object recognition on the second object image based on the registered image to obtain a second object recognition result;

and under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value, updating the registered image based on the second object image to obtain the target reference image.

According to the technical scheme, under the condition that the object image acquired by the local equipment is identified as the image of the target object, the registered image acquired by the remote equipment is updated based on the object image acquired by the local equipment, so that the subsequent object identification passing rate and the application safety can be effectively ensured.

Optionally, the performing object recognition on the second object image based on the registration image to obtain a second object recognition result includes:

carrying out optical attribute difference identification on the registered image and the second object image to obtain optical attribute difference information;

performing optical attribute correction on the registered image based on the optical attribute difference information to obtain a corrected image;

and carrying out object recognition on the second object image based on the corrected image to obtain a second object recognition result.

According to the technical scheme, under the condition that object identification needs to be carried out by combining the registered image acquired by the remote equipment, the optical attribute correction is carried out on the registered image and the second object image acquired by the local equipment, so that the optical attribute difference of the image caused by the equipment difference can be effectively reduced, and the object identification passing rate and the application safety are improved.

Optionally, the updating the registration image based on the second object image to obtain the target reference image includes:

replacing the registered image with the second object image to obtain the target reference image;

or the like, or, alternatively,

and taking the second object image and the registered image as the target reference image.

According to the technical scheme, the preset object image acquired by the non-local equipment is replaced by the object image acquired by the local equipment, or the object image acquired by the local equipment is added into the reference image for object identification, so that the optical attribute difference of the images acquired among different equipment can be effectively avoided, and the object identification accuracy, the passing rate and the application safety are improved.

Optionally, the updating the registered image based on the second object image under the condition that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold, and obtaining the target reference image includes:

under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value, carrying out image quality analysis on the second object image to obtain an image quality analysis result;

under the condition that the image quality analysis result meets a preset quality condition, updating the registered image based on the second object image to obtain the target reference image;

or the like, or, alternatively,

under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value, carrying out object orientation identification on the second object image to obtain an object orientation identification result;

under the condition that the object orientation identification result meets at least one preset orientation condition, updating the registered image based on the second object image to obtain the target reference image;

or the like, or, alternatively,

acquiring acquisition time attribute information of the registered image under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value;

and under the condition that the current time attribute information is matched with the acquisition time attribute information, updating the registered image based on the second object image to obtain the target reference image.

Or the like, or, alternatively,

acquiring historical operation trigger time corresponding to the target object under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold, wherein the historical operation trigger time is trigger time for triggering the preset operation based on the object identification result corresponding to the target object;

determining a target time period based on the historical operation trigger time, wherein the target time period is a time period when the execution frequency of the preset operation is greater than or equal to a preset frequency;

and under the condition that the current time is in a target time period, updating the registered image based on the second object image to obtain the target reference image.

According to the technical scheme, under the condition that the second object image acquired by the local equipment is identified as the image of the target object, the reference image is screened by combining at least one dimension of the image quality of the second object image, the corresponding azimuth information, the acquisition time attribute information, the operation habit and the like, so that the quality of the target reference image can be effectively improved.

Optionally, the method further includes:

responding to a third object identification instruction, and acquiring a third object image and the registration image of the target object acquired by the local equipment;

performing object recognition on the third object image based on the registered image to obtain a third object recognition result;

comparing the third object identification result with the second object identification result to obtain a comparison result;

updating the target reference image based on the third object image in a case where the comparison result indicates that the degree of similarity between the third object image and the registered image is greater than the degree of similarity between the second object image and the registered image.

According to the technical scheme, the target reference image is continuously updated by selecting the object image with higher similarity with the registered image from the object images acquired by the local equipment, so that the quality of the reference image serving as the identification target object can be better improved.

Optionally, the method further includes:

acquiring a first target image of the target object acquired by the local equipment within a preset time period and a fourth object identification result between the first target image and the registration image;

performing living body detection on the first target image to obtain a living body detection result;

screening out a second target image from the first target image based on the fourth object recognition result and the living body detection result;

and updating the registered image based on the second target image to obtain the target reference image.

According to the technical scheme, the target reference image is selected by combining the object identification result and the living body detection result of the object image acquired by the local equipment within a period of time, so that the image of the real object can be better ensured to be acquired, and the image quality is better ensured.

Optionally, the method further includes:

acquiring a third target image of the target object acquired by the local equipment in the current updating period based on a preset updating frequency;

and updating the target reference image based on the image meeting the preset condition in the third target image.

According to the technical scheme, the target reference image is continuously updated according to the preset updating frequency, so that the similarity between the target reference image and the target object can be better ensured, and the image quality of the target reference image is effectively improved.

Optionally, the updating the target reference image based on the image satisfying the preset condition in the third target image includes:

replacing the target reference image by an image meeting the preset condition in the third target image;

or the like, or, alternatively,

and adding the image meeting the preset condition in the third target image into the target reference image.

According to the technical scheme, in the process of updating the target reference image by using the object image acquired by the local equipment in the current updating period, the target reference image can be updated in a mode of replacing the target reference image or adding the object image of which the current updating period meets the preset condition into the target reference image, and the quality of the target reference image can be effectively improved while the diversity of the updating mode of the target reference image is increased.

Optionally, in a case that the target reference image includes a plurality of images, the method further includes:

displaying the plurality of images;

in response to triggering a confirmation instruction based on at least one of the plurality of images, updating the target reference image based on the at least one image to which the confirmation instruction corresponds.

According to the technical scheme, the target reference image is displayed to the user, so that the user can select and confirm the target reference image, and the quality of the target reference image can be better ensured.

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

the first image acquisition module is configured to execute and respond to a first object identification instruction, and acquire a first object image and a target reference image of a target object acquired by local equipment, wherein the target reference image is obtained by updating a registration image based on the local object image, the registration image is an image of the target object acquired by remote equipment, and the registration image is used for object registration;

a first object recognition module configured to perform object recognition on the first object image based on the target reference image, resulting in a first object recognition result.

Optionally, the target reference image includes at least one of:

Optionally, the apparatus further comprises:

a second image acquisition module configured to execute the first image acquisition module to acquire a second object image of the target object and the registration image acquired by the local device in response to a second object identification instruction, wherein the second object identification instruction is an object identification instruction triggered before the first object identification instruction;

the second object recognition module is configured to perform object recognition on the second object image based on the registered image to obtain a second object recognition result;

and the first registered image updating module is configured to update the registered image based on the second object image to obtain the target reference image under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value.

Optionally, the second object identifying module includes:

an optical attribute difference recognition unit configured to perform optical attribute difference recognition on the registration image and the second object image, resulting in optical attribute difference information;

an optical attribute correction unit configured to perform optical attribute correction on the registration image based on the optical attribute difference information, resulting in a corrected image;

an object recognition unit configured to perform object recognition on the second object image based on the corrected image, resulting in the second object recognition result.

Optionally, the first registration image updating module includes:

a first registration image updating unit configured to perform replacement of the registration image with the second object image, resulting in the target reference image;

or the like, or, alternatively,

a second registration image updating unit configured to perform the setting of the second object image and the registration image as the target reference image.

Optionally, the first registration image updating module includes:

an image quality analysis unit configured to perform image quality analysis on the second object image to obtain an image quality analysis result in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registered image is equal to or greater than a preset threshold;

a third registration image updating unit configured to update the registration image based on the second object image to obtain the target reference image if the image quality analysis result satisfies a preset quality condition;

or the like, or, alternatively,

an object orientation recognition unit configured to perform object orientation recognition on the second object image to obtain an object orientation recognition result in a case where the second object recognition result indicates that the similarity between the second object image and the registration image is greater than or equal to a preset threshold;

a fourth registered image updating unit configured to update the registered image based on the second object image to obtain the target reference image if the object orientation recognition result satisfies at least one preset orientation condition;

or the like, or, alternatively,

a capture time attribute acquisition unit configured to perform acquisition of capture time attribute information of the registration image in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registration image is equal to or greater than a preset threshold;

a fifth registered image updating unit configured to perform updating of the registered image based on the second object image to obtain the target reference image in a case where the current time attribute information matches the acquisition time attribute information.

Or the like, or, alternatively,

a historical operation trigger time acquiring unit configured to acquire a historical operation trigger time corresponding to the target object when the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold, wherein the historical operation trigger time is a trigger time for triggering the preset operation based on the object recognition result corresponding to the target object;

a target time period determination unit configured to perform determination of a target time period based on the historical operation trigger time, the target time period being a time period in which an execution frequency of the preset operation is greater than or equal to a preset frequency;

a sixth registration image updating unit configured to update the registration image based on the second object image to obtain the target reference image if the current time is within a target time period.

Optionally, the apparatus further comprises:

a third image acquisition module configured to execute acquiring, in response to a third object recognition instruction, a third object image and the registration image of the target object acquired by the local device;

a third object recognition module configured to perform object recognition on the third object image based on the registration image, resulting in a third object recognition result;

an object recognition result comparison module configured to perform a comparison between the third object recognition result and the second object recognition result to obtain a comparison result;

a first target reference image updating module configured to perform updating the target reference image based on the third object image in a case where the comparison result indicates that the degree of similarity between the third object image and the registered image is greater than the degree of similarity between the second object image and the registered image.

Optionally, the apparatus further comprises:

the data acquisition module is configured to acquire a first target image of the target object acquired by the local device within a preset time period and a fourth object recognition result between the first target image and the registration image;

a living body detection module configured to perform living body detection on the first target image to obtain a living body detection result;

a target image screening module configured to perform screening of a second target image from the first target image based on the fourth object recognition result and the living body detection result;

a second registered image updating module configured to perform updating the registered image based on the second target image, resulting in the target reference image.

Optionally, the apparatus further comprises:

a third target image obtaining module configured to obtain a third target image of the target object, which is acquired by the local device in a current update period, based on a preset update frequency;

a second target reference image updating module configured to perform updating of the target reference image based on an image satisfying a preset condition in the third target image.

Optionally, the second target reference image updating module includes:

a first target reference image updating unit configured to perform replacement of the target reference image with an image satisfying the preset condition in the third target image;

or the like, or, alternatively,

a second target reference image updating unit configured to perform addition of an image satisfying the preset condition in the third target image to the target reference image.

Optionally, in a case that the target reference image includes a plurality of images, the apparatus further includes:

an image presentation module configured to perform presenting the plurality of images;

a third target reference image update module configured to perform, in response to triggering a confirmation instruction based on at least one of the plurality of images, updating the target reference image based on the at least one image to which the confirmation instruction corresponds.

According to another aspect of the embodiments of the present disclosure, there is provided an electronic device including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of any of the above.

According to another aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of the above-mentioned embodiments of the present disclosure.

According to another aspect of the embodiments of the present disclosure, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the method of any of the above-mentioned of the embodiments of the present disclosure.

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.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a flow diagram illustrating an image processing method according to an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a pre-fetching of a target reference image according to an exemplary embodiment;

FIG. 3 is a flow diagram illustrating object recognition of a second object image based on a registration image to obtain a second object recognition result, according to an example embodiment;

FIG. 4 is a flow diagram illustrating updating a target reference image in accordance with an exemplary embodiment;

FIG. 5 is a flow diagram illustrating another pre-fetching of a target reference image in accordance with an exemplary embodiment;

FIG. 6 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment;

FIG. 7 is a block diagram illustrating an electronic device for image processing in accordance with an exemplary embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In a specific embodiment, the image processing method provided in the embodiment of the present disclosure may be applied to a terminal, optionally, the terminal may include but is not limited to an access control device, an attendance device, a cash register device, and the like, optionally, the access control device, the attendance device, the cash register device, and the like are provided with a camera device, optionally, the camera device may be a camera device integrated with the terminal, and may also be a split camera device connected in a wired or wireless manner.

Fig. 1 is a flowchart illustrating an image processing method according to an exemplary embodiment, which is used in a terminal, as shown in fig. 1, and specifically, the image processing method includes:

s101: in response to the first object recognition instruction, a first object image and a target reference image of a target object acquired by the local device are acquired.

In practical applications, the first object recognition instruction may be triggered based on different triggering operations in combination with different requirements of practical applications. In an alternative embodiment, the first object recognition instruction may be triggered based on an acquisition operation of the target object; for example, a button for triggering shooting of a face image of a user is arranged on the access control device, and accordingly, the operation of acquiring the face image of the user can be executed by triggering a camera device on the access control device through pressing the button, and correspondingly, the first object identification instruction can be triggered while the camera device executes the operation of acquiring the face image of the user, so that local equipment can be called to acquire a first object image (including an image of a target object) of the target object, and a target reference image can also be acquired.

In a specific embodiment, the target reference image is obtained by updating a registration image based on the local object image, specifically, the registration image is an image of a target object acquired by the remote device, and the registration image may be used for object registration. In particular, the local object image may be an object image acquired by the local device. In practical applications, the target reference image may be obtained in advance, that is, obtained before the first object recognition instruction is triggered, and stored in a corresponding database or cache, and after the first object recognition instruction is triggered, the target reference image is read from the corresponding database or cache. Specifically, the target reference image may be a reference image for identifying the target object. In a specific embodiment, an object image satisfying a preset condition in the local object image may be selected to update the registration image, so as to obtain the target object image. Accordingly, the target reference image (i.e., the object image satisfying the preset condition) may include at least one of:

selecting an object image, wherein the similarity between a first image and a registered image is greater than or equal to a preset threshold value, and the image quality analysis result meets a preset quality condition;

the similarity between a first image selected from the local object images and the registered image is greater than or equal to a preset threshold value, and the orientation information of the target object relative to the camera device is at least one object image of appointed orientation information when the local object images are collected;

selecting a first object image which has similarity with the registered image greater than or equal to a preset threshold value and is matched with the acquisition time attribute information of the registered image according to the time attribute information during the acquisition of the local object image;

the similarity between a first image selected from the local object images and the registered image is greater than or equal to a preset threshold, the time when the local object images are collected is the object image in a target time period, and the target time period is a time period when the execution frequency of preset operation is greater than or equal to a preset frequency;

and selecting the object image with the highest sum of the similarity with the registered image and the weighted average of the corresponding numerical values of the living body detection results from the local object images.

In addition, it should be noted that the local device may be the terminal provided with the camera device integrated with the terminal or separated from the terminal.

In practical applications, the target object may be different according to different practical application scenarios, for example, in an application scenario that needs face recognition, the target object may be a face of a certain user; for example, in an application scenario requiring iris-based recognition, the target object may be an iris of a certain user; for example, in an application scenario requiring fingerprint-based identification, the target object may be a fingerprint of a certain user. Accordingly, different types of target objects can also adopt different types of camera devices to acquire corresponding object images.

In an optional embodiment, the method may further include: optionally, assuming that the target reference image is an object image with a similarity between a first selected local object image and the reference image being greater than or equal to a preset threshold, as shown in fig. 2, the step of obtaining the target reference image in advance may include:

s201: and acquiring a second object image registration image of the target object acquired by the local equipment in response to the second object identification instruction.

S203: carrying out object recognition on the second object image based on the registered image to obtain a second object recognition result;

s205: and under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value, updating the registered image based on the second object image to obtain a target reference image.

In a particular embodiment, the local object image may be an object image acquired by a local device. In some embodiments, the second object recognition instruction may be an object recognition instruction triggered before the first object recognition instruction. Specifically, when the second object recognition instruction is triggered, the reference image as the recognition target object may be the above-mentioned registered image.

In practical application, after the second object identification instruction is triggered, the operation of acquiring the second object image of the target object and the registration image of the target object, which are acquired by the local device, is executed, and the registration image is updated based on the second object image to obtain a target reference image; corresponding operations can be executed based on the second object recognition result in combination with actual application requirements, for example, operations of opening a door control, inputting attendance information, paying and the like are executed under the condition that the second object recognition result indicates that the similarity between the second object image and the registration image is greater than or equal to a preset threshold value.

In an embodiment of the present specification, the second object recognition result may be a similarity between the registration image and the second object image. Accordingly, the performing object recognition on the second object image based on the registered image to obtain the second object recognition result may include calculating a similarity between the second object image and the registered image. Alternatively, the similarity between images may include, but is not limited to, euclidean distance, manhattan distance, cosine distance, etc. between images.

In a specific embodiment, the preset threshold may be set in combination with the requirement for the object identification accuracy and the requirement for the object identification passing rate in practical application, specifically, the higher the requirement for the object identification accuracy is, the higher the preset threshold is, and correspondingly, the lower the object identification passing rate is; conversely, the lower the requirement on the object identification precision, the lower the preset threshold value, and correspondingly, the higher the object identification pass rate is.

In a specific embodiment, in a case that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to the preset threshold, it may be determined that an object in the second object image is a target object, and accordingly, the registered image may be updated based on the second object image to obtain the target reference image.

In the above embodiment, when the object image acquired by the local device is identified as the image of the target object, the preset object image acquired by the non-local device is updated based on the object image acquired by the local device, so that the subsequent object identification throughput and the application security can be effectively ensured.

In an alternative embodiment, in a case that object recognition needs to be performed in combination with a registration image acquired by a remote device, the optical property correction may be performed on the registration image to reduce an optical property difference between an image acquired by a local device and an image acquired by the remote device, and accordingly, as shown in fig. 3, performing object recognition on the second object image based on the registration image to obtain a second object recognition result may include:

s301: carrying out optical attribute difference identification on the registered image and the second object image to obtain optical attribute difference information;

s303: performing optical attribute correction on the registered image based on the optical attribute difference information to obtain a corrected image;

s305: and carrying out object recognition on the second object image based on the corrected image to obtain a second object recognition result.

In a particular embodiment, the optical property difference information may characterize the difference in optical properties of the registered image relative to the second object image. Alternatively, the optical properties may include, but are not limited to, sharpness, brightness, etc. of the image.

In an alternative embodiment, the optical property correction may be performed on the registered image in combination with histogram equalization, image distribution, and the like. In a specific embodiment, performing object recognition on the second object image based on the corrected image to obtain the second object recognition result may include calculating a similarity between the second object image and the corrected image, and using the similarity as a specific refinement of the second object recognition result, which is not described herein again.

In the above embodiment, when the object identification needs to be performed in combination with the registered image acquired by the remote device, the optical attribute correction is performed on the registered image and the second object image acquired by the local device, so that the optical attribute difference of the image caused by the device difference can be effectively reduced, and the object identification throughput and the application safety are improved.

In an optional embodiment, the updating the registration image based on the second object image to obtain the target reference image includes:

and replacing the registered image with the second object image to obtain a target reference image.

In an alternative embodiment, the registration image may be directly replaced with a second object image of the target object acquired by the local device, and the second object image may be used as a reference image for subsequent object recognition.

In the above embodiment, the preset object image acquired by the non-local device is replaced by the object image acquired by the local device, so that the optical property difference of the images acquired among different devices can be effectively avoided, and the object identification accuracy, the passing rate and the application safety are further improved.

the second object image and the registration image are taken as target reference images.

In the above embodiment, the object image acquired by the local device is added to the reference image for object identification, so that the object identification accuracy, the passing rate and the application safety can be improved.

In an optional embodiment, it is assumed that the target reference image is an object image which has a similarity between a first image selected from the local object images and the reference image greater than or equal to a preset threshold and satisfies a preset quality condition according to an image quality analysis result. Optionally, in a case that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold, updating the registered image based on the second object image, and obtaining the target reference image may include:

under the condition that the image quality analysis result meets a preset quality condition, updating a registered image based on a second object image to obtain a target reference image;

in a particular embodiment, there may be one or more of the indicators that may be used to measure image quality. Specifically, the setting may be performed in advance in conjunction with the actual application. In an alternative embodiment, assuming that the sharpness of the image is used as an index for measuring the image quality, the preset quality condition may include a preset sharpness threshold, and the preset sharpness threshold may be set in combination with the sharpness requirement of the target reference image in the actual application. Optionally, the performing image quality analysis on the second object image to obtain an image quality analysis result may include: and identifying the definition of the second object image to obtain the image definition. In a particular embodiment, the sharpness identifying of the image may include, but is not limited to, being implemented in conjunction with a laplacian algorithm. Optionally, under the condition that the image definition of the second object image is greater than the preset definition threshold, it may be determined that the image quality analysis result meets the preset quality condition.

In an optional embodiment, assuming that the number of objects in the image is used as an index for measuring image quality, correspondingly, the preset quality condition may include an object number threshold, and optionally, in a scene where a certain target object is identified, the target object is only included in the object image, which is more beneficial to accuracy of object identification, and optionally, the object number threshold may be 1. Correspondingly, the analyzing the image quality of the second object image to obtain the image quality analysis result may include identifying the number of objects in the second object image to obtain the number of objects. In a specific embodiment, the object detection may be performed on the second object image based on a pre-trained object detection network, so as to detect the number of objects in the second object image. Optionally, when the number of objects corresponding to the second object image is 1 (preset quality condition), it may be determined that the image quality analysis result satisfies the preset quality condition.

In the above embodiment, when the second object image acquired by the local device is identified as the image of the target object, the image quality of the second object image is combined, and when the quality of the second object image meets the preset quality condition, the preset object image acquired by the non-local device is updated based on the second object image, so that the quality of the target reference image can be effectively improved, and the object identification accuracy, the passing rate and the application safety can be better improved.

In an optional embodiment, it is assumed that the target reference image is an object image in which a similarity between a first selected local object image and a registered image is greater than or equal to a preset threshold, and orientation information of the target object relative to the camera device is at least one piece of specified orientation information when the local object image is acquired. Optionally, the updating the registered image based on the second object image under the condition that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to the preset threshold, and obtaining the target reference image may include:

and under the condition that the object orientation identification result meets at least one preset orientation condition, updating the registered image based on the second object image to obtain a target reference image.

In a specific embodiment, the object orientation recognition result may represent orientation information of the target object relative to the camera device when the second object image is captured. Optionally, the at least one preset orientation condition may be at least one orientation information of the target object relative to the camera device when the preset target reference image is acquired. In an optional embodiment, when a certain preset orientation condition is image acquisition, the orientation information of the target object relative to the camera device is positive (the target object is positive relative to the camera device); correspondingly, when the object orientation recognition result indicates that the second object image is acquired and the orientation information of the target object relative to the camera device is just opposite, the object orientation recognition result can be determined to meet at least one preset orientation condition.

In a specific embodiment, the object orientation recognition may be performed on the second object image in combination with a pre-trained object orientation recognition network to obtain an object orientation recognition result.

In some embodiments, multiple local device-acquired object images of different orientations may be selected as the target reference image. In a specific embodiment, taking the target object as a face as an example, it is assumed that a face facing left relative to the image capturing device, a face facing right relative to the image capturing device, and a face image of which the face is opposite to the image capturing device can be used as target reference images; correspondingly, when the object orientation recognition result indicates that the second object image is acquired, the registered image can be updated based on the second object image to obtain the target reference image under the condition that the orientation information of the target object relative to the camera device is that the face of the person faces to the left relative to the camera device, the face of the person faces to the right relative to the camera device or the face of the person is opposite to the camera device.

In the above embodiment, on the basis that the second object image acquired by the local device is identified as the image of the target object, the orientation information of the target object corresponding to at least one preset orientation condition with respect to the camera device is combined to select the object image acquired in the designated orientation to update the registered image, so that the quality of the acquired object image can be effectively ensured, and the object identification accuracy, the passing rate and the application safety can be better improved.

In an alternative embodiment, it is assumed that the target reference image is an object image which is selected from the local object images, has a similarity with the registration image greater than or equal to a preset threshold, and the time attribute information of the local object image at the time of acquisition is matched with the acquisition time attribute information of the registration image. Optionally, the updating the registered image based on the second object image under the condition that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to the preset threshold, and obtaining the target reference image may include:

and under the condition that the current time attribute information is matched with the acquisition time attribute information, updating the registered image based on the second object image to obtain a target reference image.

In a particular embodiment, the acquisition time attribute information may be information that can characterize the time at which the registration image was acquired. In a particular embodiment, the collection time attribute information may include, but is not limited to, a season of collection, a time period of collection (e.g., 9:00-11:00 am during the day), and the like.

In a specific embodiment, in order to better ensure the similarity between a reference image used as a recognition target object in an object image acquired by local equipment and a registered image, the acquisition time attribute information of the registered image may be combined; for example, the acquisition time attribute information of the initial reference object image is summer, and correspondingly, if the current time attribute information indicates that the current season is also summer, it may be determined that the current time attribute information matches the acquisition time attribute information of the registered image, and then the operation of updating the registered image based on the second object image is performed to obtain the target reference image.

In the above embodiment, the object images acquired by the local device are screened in combination with the matching condition between the acquisition time attribute information of the registered image and the current time attribute information, so that the similarity between the reference image used as the identification target object in the object images acquired by the local device and the registered image can be better ensured, and the object identification accuracy, the passing rate and the application safety can be better improved.

In an optional embodiment, it is assumed that the target reference image is an object image which is selected from the local object images, has a similarity with the registration image greater than or equal to a preset threshold, and is located in the target time period at the time of acquiring the local object image. Optionally, the updating the registered image based on the second object image under the condition that the second object recognition result indicates that the similarity between the second object image and the registered image is greater than or equal to the preset threshold, and obtaining the target reference image may include:

under the condition that the second object identification result indicates that the similarity between the second object image and the registered image is greater than or equal to a preset threshold value, acquiring historical operation trigger time corresponding to the target object, wherein the historical operation trigger time is trigger time for triggering preset operation based on the object identification result corresponding to the target object;

determining a target time period based on the historical operation trigger time, wherein the target time period is a time period when the execution frequency of the preset operation is greater than or equal to the preset frequency;

and under the condition that the current time is in the target time period, updating the registered image based on the second object image to obtain a target reference image.

In a specific embodiment, the historical operation triggering time is triggering time for triggering a preset operation based on an object identification result corresponding to a target object; the target time period is a time period in which the execution frequency of the preset operation is greater than or equal to the preset frequency. Specifically, the preset frequency may be preset in combination with an actual application scenario. The time period may be a certain time period within a preset period, and optionally, the preset period may be 0 to 24 points per day; the time from 0 monday to 24 monday of each week can be set according to practical application.

In practical application, for example, in an application scenario of attendance card punching based on face recognition, the operation of triggering and inputting attendance information by a user is often located in a fixed time period of a day, and correspondingly, in combination with historical operation trigger time, 7:30 to 9:00, and 17:00 to 18: 30 is the target time period, corresponding to a 7:30 to 9:00, and 17:00 to 18: in step 30, if the current time is within the target time period, the registered image may be updated based on the second object image, so as to obtain the target reference image.

In the above embodiment, by combining whether the acquisition time period of the object image is located in the target time period, the target reference image of the target object acquired by the local device can be selected conveniently in the peak time period of triggering the preset operation according to the habit of triggering the preset operation by the user, so that the difference between the subsequent target reference image and the object image to be identified due to different acquisition times is effectively reduced, and the object identification accuracy, the passing rate and the application safety are improved.

In an optional embodiment, assuming that the target reference image may be an object image selected from the local object images and having the highest similarity with the registered image, as shown in fig. 4, the method may further include:

s401: responding to the third object identification instruction, and acquiring a third object image and a registration image of the local equipment acquisition target object;

s403: carrying out object recognition on the third object image based on the registered image to obtain a third object recognition result;

s405: comparing the third object identification result with the second object identification result to obtain a comparison result;

s407: in a case where the comparison result indicates that the degree of similarity between the third object image and the registered image is greater than the degree of similarity between the second object image and the registered image, the target reference image is updated based on the third object image.

In a specific embodiment, the third object recognition instruction may be an object recognition instruction triggered after the second object recognition instruction. The object recognition result may be a similarity between the registered image and the third object image.

In a specific embodiment, in order to better improve the quality of the reference image as the identification target object, an object image with a higher similarity degree with the registered image can be selected from the object images acquired by the local equipment to continuously update the target reference image.

In practical application, after the third object identification instruction is triggered, the operation of acquiring the third object image and the registration image of the local device acquisition target object and updating the target reference image based on the third object image is executed; the third object image may also be subjected to object recognition based on the target reference image in combination with the actual application requirements, and corresponding operations may be performed based on the object recognition result, for example, operations such as opening the door access, entering attendance information, and the like may be performed when the object recognition result indicates that the similarity between the third object image and the target reference image is greater than or equal to the preset threshold.

In some embodiments, the performing, on the basis of the registered image, the object recognition on the third object image to obtain the specific refinement of the third object recognition result may refer to performing, on the basis of the registered image, the object recognition on the second object image to obtain the specific refinement of the second object recognition result, which is not described herein again.

In the above embodiment, the target reference image is continuously updated by selecting the object image with higher similarity to the registered image from the object images acquired by the local device, so that the quality of the reference image serving as the identification target object can be better improved.

In an optional embodiment, assuming that the target reference image is an object image with a highest sum of weighted averages of values corresponding to the similarity and the live body detection result with the registered image, which are selected from the local object images, as shown in fig. 5, the method may further include:

s501: acquiring a first target image of a target object acquired by local equipment within a preset time period and a fourth object identification result between the first target image and a registered image;

s503: performing living body detection on the first target image to obtain a living body detection result;

s505: screening out a second target image from the first target image based on the fourth object recognition result and the living body detection result;

s507: and updating the registered image based on the second target image to obtain a target reference image.

In a specific embodiment, the first target image may be an object image whose matching degree with the initial reference image is greater than or equal to a preset threshold value, among images of a target object acquired by a local device within a preset time period. Specifically, the preset time period may be a preset update cycle of the registered image. The fourth object recognition result may be a similarity between the registered image and the first target image.

In a specific embodiment, performing a biopsy on the first target image to obtain a biopsy result may include performing a biopsy on the first target image based on a pre-trained biopsy network to obtain a biopsy result. Specifically, the living body detection result may represent information on whether a living body (e.g., a real person) exists when the first target image is acquired. In practical applications, the living body detection result may be a probability that a living body exists when the first target image is acquired.

In a specific embodiment, the screening out the second target image from the first target image based on the fourth object recognition result and the living body detection result may include performing weighted average or addition on a value (similarity) corresponding to the object recognition result of any one of the first target images and a value (probability) corresponding to the living body detection result of the image, selecting an image with the highest weighted average value or added value as the second target image, and updating the registered image based on the second target image to obtain the target reference image. Specifically, the step of specifically refining the target reference image by updating the registered image based on the second target image may refer to the step of specifically refining the target reference image by updating the registered image based on the second target image, and details of the target reference image are not described herein again.

In addition, it should be noted that the respective weights corresponding to the fourth object recognition result and the living body detection result may be set according to practical application requirements.

Optionally, the registered image may also be updated to obtain the target reference image by using the first object image in the locally acquired object images, the sum of the values corresponding to the object identification result and the living body detection result, or the object image whose value after weighted average is greater than or equal to the preset value.

In some embodiments, the step of updating the registered image based on the second target image to obtain the specific refinement of the target reference image may refer to the step of updating the registered image based on the second target image to obtain the specific refinement of the target reference image, which is not described herein again.

In the above embodiment, the target reference image is selected by combining the object recognition result and the living body detection result of the object image acquired by the local device within a period of time, so that the image of the real object can be better ensured to be acquired, and the image quality can be better ensured.

In an optional embodiment, the method may further include:

acquiring a third target image of a target object acquired by local equipment in a current updating period based on a preset updating frequency;

In a specific embodiment, the preset update frequency may be preset according to an actual application requirement, and the preset update frequency may be an update frequency of the target reference image. Specifically, the third target image may be an image of the target object acquired by the local device in the current update period. Specifically, for the specific refinement of the image satisfying the preset condition in the third target image, reference may be made to the specific refinement of the object image satisfying the preset condition when the target reference image is determined, and details are not repeated here.

In the above embodiment, the target reference image is continuously updated according to the preset updating frequency, so that the similarity between the target reference image and the target object can be better ensured, and the image quality of the target reference image is effectively improved.

In an optional embodiment, the updating the target reference image based on the object image satisfying the preset condition in the second target image may include:

replacing the target reference image by using the object image meeting the preset condition in the third target image;

or the like, or, alternatively,

and adding the object image meeting the preset condition in the third target image into the target reference image.

In an optional embodiment, the original target reference image may be directly replaced with a third target image of the target object acquired by the local device in the current update period, which meets a preset condition, so as to update the target reference image.

In another optional embodiment, a third target image of the target object acquired by the local device in the current update period, which meets a preset condition, may be added to the target reference image to update the target reference image; optionally, an upper limit of the number of images of the target reference image may be preset, and when the number of images of the target reference image reaches the upper limit of the number of images, the operation of adding the object image satisfying the preset condition in the third target image to the target reference image may be stopped.

In the above embodiment, in the process of updating the target reference image by using the object image acquired by the local device in the current update period, the target reference image may be updated by replacing the target reference image or adding the object image of which the current update period meets the preset condition to the target reference image, so that the quality of the target reference image can be effectively improved and the diversity of the update modes of the target reference image can be increased.

In addition, it should be noted that the preset conditions listed above are only one example, and in practical applications, more preset conditions may be set according to practical application requirements, or at least two examples of different preset conditions may be combined into a new preset condition, and so on.

In an optional embodiment, in the case that the target reference image includes a plurality of images, the method may further include: displaying a plurality of images; in response to triggering a confirmation instruction based on at least one of the plurality of images, the target reference image is updated based on the at least one image to which the confirmation instruction corresponds.

In practical application, in order to better ensure the quality of the target reference image, the target reference image may be displayed to a user, so that the user can confirm the selection of the target reference image.

In addition, under the condition that the target reference image comprises one image, the target reference image can be displayed for a user to confirm, and correspondingly, if a confirmation instruction is triggered based on the displayed target reference image, the image corresponding to the confirmation instruction can be used as the target reference image; otherwise, the target reference image can be acquired by combining the preset conditions again.

S103: and carrying out object recognition on the first object image based on the target reference image to obtain a first object recognition result.

In an alternative embodiment, the first object recognition result may be a similarity between the target reference image and the first object image.

Optionally, in a case that the target reference image includes a plurality of images, performing object recognition on the first object image based on the target reference image to obtain the first object recognition result may include performing object recognition on the first object image based on the plurality of images to obtain a plurality of sub-object recognition results; a first object recognition result is generated based on the plurality of sub-object recognition results. In an alternative embodiment, the plurality of sub-object recognition results may be added to obtain the first object recognition result; the weight information corresponding to the plurality of images may be set in advance, and the first object recognition result may be obtained by performing weighted average on the plurality of sub-object recognition results based on the weight information.

In a specific embodiment, in the case that the target reference image includes the second object image and the registration image, performing object recognition on the first object image based on the target reference image to obtain a first object recognition result may include: carrying out object recognition on the first object image based on the registration image to obtain a first sub-object recognition result; carrying out object recognition on the first object image based on the second object image to obtain a second sub-object recognition result; and determining a first object recognition result according to the first sub-object recognition result and the second sub-object recognition result.

In a specific embodiment, the object recognition is performed on the first object image based on the registered image to obtain the first sub-object recognition result, and the object recognition is performed on the first object image based on the second object image to obtain the specific refinement of the second sub-object recognition result.

In a specific embodiment, determining the first object recognition result according to the first sub-object recognition result and the second sub-object recognition result may include adding the first sub-object recognition result and the second sub-object recognition result to obtain the first object recognition result; the first sub-object recognition result and the second sub-object recognition result may be weighted and averaged based on preset weight information to obtain the first object recognition result.

In the above embodiment, when the target reference image includes a plurality of images, the object recognition is performed on the first object image based on the plurality of target reference images, so that the accuracy of the object recognition can be better ensured.

In an alternative embodiment, in the case that the first object recognition result indicates that the similarity between the first object image and the target reference image is greater than or equal to a preset threshold, a preset operation may be performed. Specifically, the preset operation may be different according to different actual application requirements, and specifically, the preset operation may include but is not limited to operations of opening an access control, entering attendance information, paying, and the like. Optionally, in a case that the first object recognition result indicates that the similarity between the first object image and the target reference image is smaller than the preset threshold, preset prompt information may be fed back so as to prompt the user to re-shoot the image of the target object.

As can be seen from the technical solutions provided by the embodiments of the present specification, in the present specification, when an object image acquired by local equipment is identified as an image of a target object, a registered image acquired by remote equipment is updated based on the object image acquired by the local equipment, so that subsequent object identification throughput and application security can be effectively ensured.

Fig. 6 is a block diagram illustrating an image processing apparatus according to an exemplary embodiment. Referring to fig. 6, the apparatus includes:

a first image obtaining module 610 configured to perform, in response to the first object recognition instruction, obtaining a first object image of the target object and a target reference image of the target object acquired by the local device, where the target reference image is obtained by updating a registration image based on the local object image, the registration image is an image of the target object acquired by the remote device, and the registration image is used for performing object registration;

and a first object recognition module 620 configured to perform object recognition on the first object image based on the target reference image, resulting in a first object recognition result.

Optionally, the target reference image includes at least one of:

Optionally, the apparatus further comprises:

the second image acquisition module is configured to execute the first image acquisition module to respond to a second object identification instruction, and acquire a second object image and a registration image of the target object acquired by the local equipment, wherein the second object identification instruction is an object identification instruction triggered before the first object identification instruction;

Optionally, the second object identifying module includes:

an optical attribute correction unit configured to perform optical attribute correction of the registration image based on the optical attribute difference information, resulting in a corrected image;

and an object recognition unit configured to perform object recognition on the second object image based on the corrected image, resulting in a second object recognition result.

Optionally, the first registration image updating module includes:

a first registration image updating unit configured to perform replacement of the registration image with the second object image, resulting in a target reference image;

or the like, or, alternatively,

a second registration image updating unit configured to perform setting the second object image and the registration image as the target reference image.

Optionally, the first registration image updating module includes:

an image quality analysis unit configured to perform image quality analysis on the second object image to obtain an image quality analysis result in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registration image is equal to or greater than a preset threshold;

a third registered image updating unit configured to update the registered image based on the second object image to obtain a target reference image in a case where the image quality analysis result satisfies a preset quality condition;

or the like, or, alternatively,

an object orientation recognition unit configured to perform object orientation recognition on the second object image to obtain an object orientation recognition result in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registration image is equal to or greater than a preset threshold;

a fourth registered image updating unit configured to update the registered image based on the second object image to obtain a target reference image in a case where the object orientation recognition result satisfies at least one preset orientation condition;

or the like, or, alternatively,

an acquisition time attribute acquisition unit configured to perform acquisition of acquisition time attribute information of the registration image in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registration image is equal to or greater than a preset threshold value;

and the fifth registration image updating unit is configured to update the registration image based on the second object image under the condition that the current time attribute information is matched with the acquisition time attribute information to obtain the target reference image.

Or the like, or, alternatively,

a historical operation trigger time acquisition unit configured to acquire a historical operation trigger time corresponding to the target object in a case where the second object recognition result indicates that the similarity between the second object image and the registration image is greater than or equal to a preset threshold, the historical operation trigger time being a trigger time for triggering a preset operation based on the object recognition result corresponding to the target object;

a target time period determination unit configured to perform determination of a target time period based on the historical operation trigger time, the target time period being a time period in which an execution frequency of a preset operation is equal to or greater than a preset frequency;

and a sixth registered image updating unit configured to perform updating the registered image based on the second object image to obtain the target reference image in a case where the current time is within the target time period.

Optionally, the apparatus further comprises:

the third image acquisition module is configured to execute the third object image and the registration image of the local equipment acquisition target object in response to the third object identification instruction;

a third object recognition module configured to perform object recognition on a third object image based on the registration image, resulting in a third object recognition result;

Optionally, the apparatus further comprises:

the data acquisition module is configured to acquire a first target image of a target object acquired by local equipment within a preset time period and a fourth object recognition result between the first target image and a registered image of the target object;

the living body detection module is configured to perform living body detection on the first target image to obtain a living body detection result;

and the second registered image updating module is configured to update the registered image based on the second target image to obtain the target reference image.

Optionally, the apparatus further comprises:

the third target image acquisition module is configured to acquire a third target image of a target object acquired by local equipment in a current update period based on a preset update frequency;

and the second target reference image updating module is configured to update the target reference image based on the image meeting the preset condition in the third target image.

Optionally, the second target reference image updating module includes:

a first target reference image updating unit configured to perform replacement of the target reference image with an image satisfying a preset condition in the third target image;

or the like, or, alternatively,

and a second target reference image updating unit configured to perform addition of an image satisfying a preset condition in the third target image to the target reference image.

Optionally, in a case where the target reference image includes a plurality of images, the apparatus further includes:

an image presentation module configured to perform presenting a plurality of images;

a third target reference image update module configured to perform, in response to triggering a confirmation instruction based on at least one of the plurality of images, updating the target reference image based on the at least one image corresponding to the confirmation instruction.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 7 is a block diagram illustrating an electronic device for image processing, which may be a terminal, according to an exemplary embodiment, and an internal structure thereof may be as shown in fig. 7. The electronic device comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method of image processing. The display screen of the electronic equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the electronic equipment, an external keyboard, a touch pad or a mouse and the like.

Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and does not constitute a limitation on the electronic devices to which the disclosed aspects apply, as a particular electronic device may include more or less components than those shown, or combine certain components, or have a different arrangement of components.

In an exemplary embodiment, there is also provided an electronic device including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the image processing method as in the embodiments of the present disclosure.

In an exemplary embodiment, there is also provided a storage medium having instructions that, when executed by a processor of an electronic device, enable the electronic device to perform an image processing method in an embodiment of the present disclosure.

In an exemplary embodiment, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the image processing method in the embodiments of the present disclosure.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An image processing method, comprising:

2. The image processing method of claim 1, wherein the target reference image comprises at least one of:

3. The image processing method according to claim 1 or 2, characterized in that the method further comprises:

4. The image processing method according to claim 3, wherein the performing object recognition on the second object image based on the registration image to obtain a second object recognition result comprises:

5. The image processing method of claim 3, wherein the updating the registration image based on the second object image to obtain the target reference image comprises:

or the like, or, alternatively,

6. The image processing method according to claim 3, wherein, in a case where the second object recognition result indicates that the degree of similarity between the second object image and the registered image is greater than or equal to a preset threshold, updating the registered image based on the second object image to obtain the target reference image comprises:

or the like, or, alternatively,

under the condition that the current time attribute information is matched with the acquisition time attribute information, updating the registered image based on the second object image to obtain the target reference image;

or the like, or, alternatively,

7. The image processing method according to claim 3, characterized in that the method further comprises:

8. The image processing method according to claim 1 or 2, characterized in that the method further comprises:

9. An image processing apparatus characterized by comprising:

10. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the image processing method of any one of claims 1 to 8.

11. A computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable an image processing device to perform the image processing method of any one of claims 1 to 8.