CN112308815A

CN112308815A - Image display method, device, server, client and readable storage medium

Info

Publication number: CN112308815A
Application number: CN201910703297.0A
Authority: CN
Inventors: 寇家瑞; 卢文利
Original assignee: Beijing Kingsoft Cloud Network Technology Co Ltd; Beijing Kingsoft Cloud Technology Co Ltd
Current assignee: Beijing Kingsoft Cloud Network Technology Co Ltd; Beijing Kingsoft Cloud Technology Co Ltd
Priority date: 2019-07-31
Filing date: 2019-07-31
Publication date: 2021-02-02

Abstract

The embodiment of the application provides an image display method, an image display device, a server, a client and a readable storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining a reference image and an image to be evaluated, determining target evaluation indexes corresponding to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and the corresponding relation between the preset image scene and the target key object and the evaluation indexes, sending the target evaluation indexes to a client, and displaying the reference image, the image to be evaluated and the target evaluation indexes in a preset evaluation page by the client. Based on the above processing, the validity of the image quality evaluation result can be improved.

Description

Image display method, device, server, client and readable storage medium

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image display method, an image display apparatus, a server, a client, and a readable storage medium.

Background

With the rapid development of computer technology, images tend to have higher and higher resolution, and the requirements of users on the image quality of the images are higher and higher. In one mode, an original image (which may be referred to as a reference image) may be processed by using an image processing algorithm to obtain a processed image (which may be referred to as an image to be evaluated). Then, an evaluator can evaluate the image quality of the processed image to be evaluated relative to the reference image by observing the image pictures of the reference image and the image to be evaluated.

In the related art, the image quality of the image to be evaluated can be evaluated according to different evaluation indexes. For example, the image quality of the image to be evaluated relative to the reference image may be evaluated according to evaluation indexes such as overall subjective effect, color saturation, edge sharpness, and the like.

However, in the related art, the same evaluation index is used for the image quality evaluation of the images to be evaluated including different image frames, which may result in that the evaluation result may not effectively represent the image quality of the images to be evaluated, that is, the effectiveness of the image quality evaluation result is low.

Disclosure of Invention

An object of the embodiments of the present application is to provide an image display method, an image display apparatus, a server, a client, and a readable storage medium, which can improve the effectiveness of an image quality evaluation result. The specific technical scheme is as follows:

in order to achieve the above object, an embodiment of the present application discloses an image display method, including:

acquiring a reference image and an image to be evaluated;

determining a target evaluation index corresponding to a target image scene and a target key object according to the target image scene represented by an image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, wherein the target image is the reference image and/or the image to be evaluated, and the key object is an interested area in the image picture;

and sending the target evaluation index to a client so that the client displays the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Optionally, before determining a target evaluation index corresponding to a target image scene and a target key object according to a target image scene represented by an image picture of the target image, the target key object in the image picture, and a preset correspondence between the image scene, the key object, and the evaluation index, the method further includes:

determining a first image scene and a first key object represented by an image picture of the reference image, and a second image scene and a second key object represented by an image picture of the image to be evaluated;

determining whether the content of the reference image is consistent with the content of the image to be evaluated according to the first image scene, the first key object, the second image scene and the second key object; and under the condition of consistent determination, executing the step of determining target evaluation indexes corresponding to the target image scene and the target key objects according to the target image scene represented by the image picture of the target image, the target key objects in the image picture and the corresponding relationship between the preset image scene, the preset key objects and the evaluation indexes.

Optionally, the determining, according to the first image scene, the first key object, the second image scene, and the second key object, whether the content of the reference image and the content of the image to be evaluated are consistent includes:

judging whether the first image scene is the same as the second image scene or not, and whether the similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold or not;

if the first image scene is the same as the second image scene, and the similarity between the first key object and the second key object is greater than or equal to the preset similarity threshold, determining that the content of the reference image is consistent with the content of the image to be evaluated; and/or the presence of a gas in the gas,

and if the first image scene is different from the second image scene and/or the similarity between the first key object and the second key object is smaller than the preset similarity threshold, determining that the content of the reference image is inconsistent with the content of the image to be evaluated.

Optionally, after determining a target evaluation index corresponding to a target image scene and a target key object according to a target image scene represented by an image picture of the target image, the target key object in the image picture, and a preset correspondence between the image scene, the key object, and the evaluation index, the method further includes:

acquiring a plurality of evaluation grades corresponding to the target evaluation index;

and sending the plurality of evaluation levels to the client so that the client displays the plurality of evaluation levels in the preset evaluation page.

In a second aspect, to achieve the above object, an embodiment of the present application further discloses an image display method, including:

acquiring a reference image and an image to be evaluated;

receiving a target evaluation index sent by a server; the target evaluation index is an evaluation index which is determined by the server and corresponds to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, the target image is the reference image and/or the image to be evaluated, and the key object is an interested area in the image picture;

and displaying the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Optionally, the method further includes:

receiving a plurality of evaluation grades corresponding to the target evaluation index sent by the server;

and displaying the plurality of evaluation levels in the preset evaluation page.

Optionally, a plurality of target key objects are provided;

the method further comprises the following steps:

receiving a key object switching instruction, wherein the key object switching instruction is used for indicating switching from a first target key object to a second target key object;

and displaying an evaluation option aiming at the second target key object in the preset evaluation page, wherein the evaluation option comprises a target evaluation index corresponding to the second target key object.

Optionally, after receiving the key object switching instruction, the method further includes:

and marking the second target key object in the reference image and the image to be evaluated in a preset marking mode respectively.

Optionally, the method further includes:

when a unmark instruction is received, unmarking the second target key object.

In order to achieve the above object, an embodiment of the present application further discloses an image display device, including:

the acquisition module is used for acquiring a reference image and an image to be evaluated;

the system comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining a target evaluation index corresponding to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and the corresponding relation of a preset image scene, the preset key object and the evaluation index, the target image is the reference image and/or the image to be evaluated, and the key object is an interested area in the image picture;

and the first sending module is used for sending the target evaluation index to a client so that the client displays the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Optionally, the apparatus further comprises:

the processing module is used for determining a first image scene and a first key object represented by an image picture of the reference image, and a second image scene and a second key object represented by an image picture of the image to be evaluated;

Optionally, the processing module is specifically configured to determine whether the first image scene is the same as the second image scene, and whether a similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold;

Optionally, the apparatus further comprises:

the second sending module is used for acquiring a plurality of evaluation grades corresponding to the target evaluation index;

the receiving module is used for receiving the target evaluation index sent by the server; the target evaluation index is an evaluation index which is determined by the server and corresponds to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, the target image is the reference image and/or the image to be evaluated, and the key object is an interested area in the image picture;

and the display module is used for displaying the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Optionally, the apparatus further comprises:

the second display module is used for receiving a plurality of evaluation grades corresponding to the target evaluation indexes sent by the server;

Optionally, the number of the target objects is multiple;

the device further comprises:

the processing module is used for receiving a key object switching instruction, wherein the key object switching instruction is used for indicating switching from a first target key object to a second target key object;

Optionally, the apparatus further comprises:

and the marking module is used for marking the second target key object in the reference image and the image to be evaluated in a preset marking mode respectively.

Optionally, the apparatus further comprises:

and the unmarking module is used for unmarking the second target key object when a unmarking instruction is received.

In a fifth aspect, to achieve the above object, an embodiment of the present application further discloses a server, where the server includes a memory and a processor;

the memory is used for storing a computer program;

the processor is configured to implement the steps of the image display method according to the first aspect when executing the program stored in the memory.

In a sixth aspect, to achieve the above object, an embodiment of the present application further discloses a client, where the client includes a memory and a processor;

the memory is used for storing a computer program;

the processor is configured to implement the steps of the image display method according to the second aspect when executing the program stored in the memory.

In a seventh aspect, in order to achieve the above object, an embodiment of the present application further discloses a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the image display method according to the first aspect are implemented.

In an eighth aspect, in order to achieve the above object, an embodiment of the present application further discloses a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the image display method according to the second aspect are implemented.

In a ninth aspect, to achieve the above object, an embodiment of the present application further discloses a computer program product containing instructions, which when run on a computer, causes the computer to perform the steps of the image display method according to the first aspect.

Tenth aspect, in order to achieve the above object, an embodiment of the present application further discloses a computer program product containing instructions, which when run on a computer, causes the computer to perform the steps of the image display method according to the second aspect.

The embodiment of the application provides an image display method, a server can obtain a reference image and an image to be evaluated, a target evaluation index corresponding to a target image scene and a target key object is determined according to the target image scene and the target key object in the image picture represented by the image picture of the target image and the corresponding relation between the preset image scene and the target key object and the evaluation index, wherein the target image is the reference image and/or the image to be evaluated, the key object is an interested area in the image picture, the target evaluation index is sent to a client, and the client can display the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Based on the processing, an evaluator can evaluate the image quality of the image to be evaluated relative to the reference image according to the target evaluation index displayed in the preset evaluation page, and the target evaluation index is related to the image picture of the image, so that the evaluation result can effectively embody the image quality of the image to be evaluated relative to the reference image, and further, the effectiveness of the image quality evaluation result can be improved.

Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart of an image display method according to an embodiment of the present disclosure;

fig. 2 is a flowchart of an image display method according to an embodiment of the present disclosure;

fig. 3 is a schematic display diagram of a preset evaluation interface according to an embodiment of the present disclosure;

fig. 4 is a schematic display diagram of a preset evaluation interface according to an embodiment of the present disclosure;

fig. 5 is a schematic display diagram of a preset evaluation interface according to an embodiment of the present disclosure;

fig. 6 is a flowchart of an example of an image display method according to an embodiment of the present application;

fig. 7 is a schematic diagram of an evaluation flow provided in an embodiment of the present application;

fig. 8 is a structural diagram of an image display device according to an embodiment of the present application;

fig. 9 is a structural diagram of an image display device according to an embodiment of the present application;

fig. 10 is a block diagram of a server according to an embodiment of the present application;

fig. 11 is a structural diagram of a client according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In order to solve the problem of low effectiveness of an image quality evaluation result in the related art, the embodiment of the application provides an image display method, which can be applied to a server and a client. The client may display the image to allow an evaluator to evaluate the image quality.

The server can obtain a reference image and an image to be evaluated, and determine a target evaluation index corresponding to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, and further send the target evaluation index to the client, and correspondingly, the client can display the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

Based on the processing, an evaluator can evaluate the image quality of the image to be evaluated relative to the reference image according to the target evaluation index displayed in the preset evaluation page through the client, and the target evaluation index is related to the image picture of the image, so that the evaluation result can effectively reflect the image quality of the image to be evaluated relative to the reference image, and further, the effectiveness of the image quality evaluation result can be improved.

Referring to fig. 1, fig. 1 is a flowchart of an image display method provided by an embodiment of the present application, where the method may be applied to a server, and the method may include the following steps:

s101: and acquiring a reference image and an image to be evaluated.

The reference image and the image to be evaluated may be images of the same type, for example, both the reference image and the image to be evaluated are picture images, or both the reference image and the image to be evaluated are video images.

In one implementation, an image may be processed based on an image processing algorithm, in order to determine a processing effect of the image processing algorithm, an evaluator may determine image quality of the processed image relative to the image before processing, the reference image may be the image before processing, and correspondingly, the image to be evaluated may be the processed image.

The evaluator can input the reference image and the image to be evaluated to the client, and correspondingly, the client can send the reference image and the image to be evaluated to the server.

S102: and determining target evaluation indexes corresponding to the target image scene and the target key objects according to the target image scene represented by the image picture of the target image, the target key objects in the image picture and the corresponding relationship between the preset image scene, the preset key objects and the evaluation indexes.

The target image is a reference image and/or an image to be evaluated, and the key object is an interested area in an image picture.

The image scene is used to represent a scene corresponding to the image picture, for example, if a person and a football are displayed in the image picture of one image, the image scene represented by the image picture of the image may be a football match scene; if a game character is displayed in the image frame of one image, the image scene represented by the image frame of the image may be a game scene.

The key objects can represent areas in the image frame where the human eyes are mainly concentrated, for example, if the image scene of an image is a football match scene, the key objects in the image can include a football in the image frame; if the image scene of one image is a game scene, the key objects in the image can include game characters manipulated by a player in the image picture.

In one implementation, the server may store a corresponding relationship between the image scene, the key object, and the evaluation index, where the corresponding relationship may be preset, and different image scenes may be combined with different key objects and may correspond to different evaluation indexes. The evaluation index is used for evaluating the quality of the image scene and/or the key object, for example, the evaluation index may be, but is not limited to, overall subjective effect, deblurring, information richness, color saturation, edge sharpness, and the like.

For example, the image scene is a football match scene, the key objects include a football, and because the moving speed of the football in the football match scene is high, the image areas corresponding to the key objects are more prone to the occurrence of picture blurring, so the corresponding evaluation indexes can include overall subjective effect, deblurring, information richness and color saturation, and in the same image scene, the target evaluation indexes corresponding to different key objects can be the same or different.

For another example, the image scene is a game scene, the key objects include game characters operated by a player, and for the image, the evaluator browsing the image may pay more attention to the details of the key objects, so the corresponding evaluation indexes may include overall subjective effect, edge sharpness, brightness improvement, and noise suppression contrast.

In actual operation, the image scenes of a reference image and an image to be evaluated, which are needed to be evaluated by an evaluator, are the same, and key objects in the reference image and the image to be evaluated are also the same.

After the server acquires the reference image and the image to be evaluated, the server can query the corresponding relationship among the image scene (namely the target image scene) and the key object (namely the target key object) of the target image according to the image scene (namely the target image scene) and the key object of the target image and the evaluation index, determine the evaluation index (namely the target evaluation index) corresponding to both the target image scene and the target key object, and effectively embody the image quality of the image to be evaluated relative to the reference image according to the evaluation result obtained by the target evaluation index. In addition, one or more target evaluation indexes may be determined.

In one implementation, the server may determine a target image scene according to an AI (Artificial Intelligence) algorithm model; and determining a target key object according to a ROI (Region Of Interest) detection algorithm.

It can be understood that, if the reference image and the image to be evaluated are not two images before and after being processed based on the image processing algorithm, image scenes of the reference image and the image to be evaluated may not be the same, and a difference between key objects in the images is large, at this time, an evaluator may not be able to evaluate the image quality of the image to be evaluated relative to the reference image.

Optionally, before S102, the method may further include the following steps:

the method comprises the steps of firstly, determining a first image scene and a first key object represented by an image picture of a reference image, and determining a second image scene and a second key object represented by an image picture of an image to be evaluated.

After the server acquires the reference image and the image to be evaluated, the server may determine, according to the image picture of the reference image and the image picture of the image to be evaluated, an image scene (i.e., a first image scene) represented by the image picture of the reference image and a key object (i.e., a first key object) in the image picture, and an image scene (i.e., a second image scene) represented by the image picture of the image to be evaluated and a key object (i.e., a second key object) in the image picture, respectively.

The determined first key object may be one or more, and the determined second key object may be one or more.

And step two, determining whether the content of the reference image is consistent with the content of the image to be evaluated according to the first image scene, the first key object, the second image scene and the second key object, and executing S102 under the condition of determining consistency.

In one implementation, after determining the first image scene, the first key object, the second image scene, and the second key object, the server may determine whether the image scenes of the reference image and the image to be evaluated are the same according to the first image scene and the second image scene, determine whether the key objects of the reference image and the image to be evaluated are the same according to the first key object and the second key object, and further determine whether the content of the reference image and the content of the image to be evaluated are the same according to the determination result.

If the images are consistent, the reference image and the image to be evaluated are possibly two images before and after the image processing algorithm, and the evaluator can evaluate the image quality of the image to be evaluated relative to the reference image.

If the images are inconsistent, the evaluator may not evaluate the image quality of the image to be evaluated relative to the reference image, and the server may also send an image replacement reminding message to the client to remind the evaluator to replace the reference image and/or the image to be evaluated.

Optionally, the method for determining whether the content of the reference image is consistent with the content of the image to be evaluated may include the following steps:

step 1, judging whether a first image scene is the same as a second image scene or not, and whether the similarity between a first key object and a second key object is greater than or equal to a preset similarity threshold or not.

And 2, if the first image scene is the same as the second image scene, and the similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold, determining that the content of the reference image is consistent with the content of the image to be evaluated.

And 3, if the first image scene is different from the second image scene and/or the similarity between the first key object and the second key object is smaller than a preset similarity threshold, determining that the content of the reference image is inconsistent with the content of the image to be evaluated.

Wherein the preset similarity threshold can be set by a technician according to experience.

When the server judges that the first image scene is the same as the second image scene and the similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold, the server indicates that the contents of the image pictures of the first key object and the second key object are the same, and only the difference of the image quality exists, namely, the reference image and the image to be evaluated may be two images before and after the processing based on the image processing algorithm respectively.

Correspondingly, the server can determine the target evaluation index, so that an evaluator can evaluate the image quality of the image to be evaluated relative to the reference image based on the target evaluation index.

In addition, when the server determines that the first image scene is different from the second image scene, or when the server determines that the similarity between the first key object and the second key object is smaller than a preset similarity threshold, or when the server determines that the first image scene is different from the second image scene and the similarity between the first key object and the second key object is smaller than the preset similarity threshold, it indicates that the contents of the image pictures of the first key object and the second key object are different, and the evaluator may not evaluate the image quality of the image to be evaluated relative to the reference image, and the server may send an image replacement reminding message to the client to remind the evaluator to replace the reference image and/or the image to be evaluated.

In one implementation, if there is one first key object and one second key object, the server may determine the similarity between the first key object and the second key object based on different dimensions. For example, the dimensions employed by the server may include at least one of: the shape of the key object, the color of the key object, the texture of the key object, and the location of the key object in the image.

For example, the server may determine the similarity of the first key object and the second key object in each dimension, and further, may use an average value of the obtained similarities of the multiple dimensions as the similarity of the first key object and the second key object.

In another implementation, if the number of the first key objects is multiple, the number of the second key objects is also multiple, and the number of the first key objects is the same as the number of the second key objects. Then, the server may determine the similarity between each first key object and the corresponding second key object, and further determine whether the content of the reference image is consistent with the content of the image to be evaluated according to the magnitude relationship between the obtained average value of the multiple similarities and the preset similarity threshold.

S103: and sending the target evaluation index to the client so that the client displays the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

After determining the target evaluation index, the server may send the determined target evaluation index to the client.

Correspondingly, the client can display the reference image, the image to be evaluated and the target evaluation index in the preset evaluation page for the evaluation personnel to browse.

When browsing the display content in the preset evaluation page, the evaluator can evaluate the image quality of the image to be evaluated relative to the reference image by comparing the image frames of the reference image and the image to be evaluated based on the target evaluation index, and then the client can obtain the evaluation result input by the evaluator.

Therefore, based on the method of the embodiment of the application, an evaluator can evaluate the image quality of the image to be evaluated relative to the reference image according to the target evaluation index displayed in the preset evaluation page, and the target evaluation index is related to the image picture of the image, so that the evaluation result can effectively reflect the image quality of the image to be evaluated relative to the reference image, and further, the effectiveness of the image quality evaluation result can be improved.

Optionally, the server may further set different evaluation levels for the evaluators to select, according to the target evaluation index.

The method may further comprise the steps of: acquiring a plurality of evaluation grades corresponding to a target evaluation index; and sending the plurality of evaluation levels to the client so that the client displays the plurality of evaluation levels in a preset evaluation page.

The evaluation grade is used for representing the image quality of the reference image and the image to be evaluated on the target evaluation index.

The client can display a plurality of evaluation levels in a preset evaluation page, and an evaluator can evaluate the image quality of the image to be evaluated relative to the reference image according to the target evaluation index and by combining the evaluation levels.

For example, if the target evaluation index includes the overall subjective effect, the target evaluation level may include: the "good", "bad" and "almost" respectively indicate that the image to be evaluated is better than the reference image in the overall subjective effect, the image to be evaluated is not as good as the reference image in the overall subjective effect, and the image to be evaluated is as much as the reference image in the overall subjective effect. The subjective effect of the second key object relative to the first key object can be higher or lower than the overall subjective effect of the first key object.

Referring to fig. 2, fig. 2 is a flowchart of an image display method provided in an embodiment of the present application, where the method may be applied to a client, and the method may include the following steps:

s201: and acquiring a reference image and an image to be evaluated.

The reference image and the image to be evaluated may be images of the same type, for example, both the reference image and the image to be evaluated are picture images, or both the reference image and the image to be evaluated are video images. The evaluator can input the reference image and the image to be evaluated to the client.

For example, the client may display a "add reference image" button and a "add image to be evaluated" button in the display unit, then the evaluator may click the "add reference image" button and select an image before processing, then the evaluator may click the "add image to be evaluated" button and select a processed image, and then the client may obtain the reference image and the image to be evaluated uploaded by the evaluator.

S202: and receiving the target evaluation index sent by the server.

The target evaluation index is an evaluation index which is determined by the server and corresponds to the target image scene and the target key object according to the target image scene represented by the image picture of the target image, the target key object in the image picture and the corresponding relation between the preset image scene, the preset key object and the evaluation index, the target image is a reference image and/or an image to be evaluated, and the key object is an interested area in the image picture.

The key object in the reference image may be referred to as a first key object, and the key object in the image to be evaluated may be referred to as a second key object.

After the reference image and the image to be evaluated are obtained, the client may send the reference image and the image to be evaluated to the server, and then the server may determine the target evaluation index according to the reference image and the image to be evaluated, and the processing method of the server may refer to the detailed description in the above embodiments. Then, the server can send the determined target evaluation index to the client.

S203: and displaying the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

After receiving the target evaluation index sent by the server, the client can display the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page for the evaluation personnel to browse.

In addition, because the target evaluation indexes corresponding to different key objects in the same image scene may be the same or different, when the client receives the target evaluation index sent by the server, the target evaluation index corresponding to one of the target key objects may be displayed on a preset evaluation page, and subsequently, the client may update and display the target evaluation index corresponding to the target key object selected by the evaluator according to the target key object selected by the evaluator.

For example, the client may select one target key object from the plurality of target key objects according to a preset sequence, display a target evaluation index corresponding to the selected target key object on a preset evaluation page, and then update and display the target evaluation index corresponding to the target key object selected by the evaluator when the evaluator selects another target key object that needs to be evaluated.

Optionally, the method may further include the steps of: receiving a plurality of evaluation grades corresponding to a target evaluation index sent by a server; and displaying a plurality of evaluation levels in a preset evaluation page.

In one implementation, the server may further determine a plurality of evaluation levels corresponding to the target evaluation index, and send the evaluation levels to the client, and then the client may display the evaluation levels in a preset evaluation page.

For example, if the target evaluation index includes an overall subjective effect, the client may further display three evaluation levels, which are "good", "not good", and "almost", when displaying the reference image, the image to be evaluated, and the target evaluation index (i.e., the overall subjective effect), which may respectively indicate that the image to be evaluated is better than the reference image in the overall subjective effect, the image to be evaluated is not as good as the reference image in the overall subjective effect, and the image to be evaluated is as good as the reference image in the overall subjective effect. The subjective effect of the second key object relative to the first key object can be higher or lower than the overall subjective effect of the first key object.

In addition, the client may also use options with different numerical values to represent the evaluation level, see fig. 3, and fig. 3 is a display diagram of a preset evaluation interface provided in the embodiment of the present application.

In fig. 3, the evaluation key point represents a key object in an image, the reference image may be a left image, and the image to be evaluated may be a right image. As can be seen from fig. 3, the target evaluation indexes may include overall subjective effect, edge sharpness, noise suppression, contrast details, and color, and each target evaluation index corresponds to an option having five values.

For example, for a target evaluation index of the overall subjective effect, the option corresponding to the numerical value 1 may indicate that the overall subjective effect of the second key object is larger than the aberration of the first key object, and the difference is larger; the option corresponding to the numerical value 2 can indicate that the overall subjective effect of the second key object is smaller than that of the first key object in aberration; the option corresponding to the numerical value 3 may indicate that the overall subjective effect of the second key object is substantially as much as the first key object; the option corresponding to the numerical value 4 can indicate that the overall subjective effect of the second key object is better than that of the first key object, and the difference is smaller; the option corresponding to the value 5 may indicate that the overall subjective effect of the second key object is better than that of the first key object, and the difference is larger.

The evaluator can then compare the image quality of the second key object with the corresponding image quality of the first key object and select the option of the corresponding numerical value.

Accordingly, the client can obtain the target evaluation level input by the evaluator. And the target evaluation grade is determined by evaluating the image quality of the second key object relative to the first key object based on the target evaluation index.

For example, if the evaluator selects the option of the numerical value 3 for the target evaluation index, which is the overall subjective effect, the client determines that the overall subjective effect of the second key object is substantially similar to the first key object based on the human eye feeling of the evaluator.

In addition, the client may also display the name of the target key object, for example, in fig. 3, the target key object includes: the client can display a target key object between an evaluation content area (namely an area displaying the reference image and the image to be evaluated) and an evaluation index area (namely an area displaying a target evaluation index), and the area can be called an evaluation prompt area.

Optionally, the first key object is the same as the second key object, and there are a plurality of first key objects, then the method may further include the following steps:

step one, receiving a key object switching instruction.

The key object switching instruction is used for indicating switching from a first target key object to a second target key object.

When the evaluator browses the reference image and the image to be evaluated, the image quality of each second key object relative to the corresponding first key object can be evaluated.

In one implementation, in the evaluation process, an evaluator may evaluate the key objects according to a preset key object arrangement sequence.

The key object arrangement order may be set by a technician according to experience, and may be an order from a large image area occupied by the key object to a small image area, or may be an order from top to bottom of the key object in the image screen, but is not limited thereto.

When receiving the key object switching instruction, the client may determine, according to the key object arrangement order, one key object in the first key object and a corresponding key object in the second key object as a second target key object.

For example, with respect to fig. 3, the key object arrangement order may be as shown in the figure: pattern, text, circle, cup. If the pattern in the current left reference image and the corresponding pattern in the right image to be evaluated are the first target key object, namely, the evaluating personnel currently evaluates the image picture corresponding to the pattern.

In an embodiment, when the client receives the key object switching instruction, it may determine that the text in the left reference image and the corresponding text in the right image to be evaluated are the second target key object.

In another implementation, the evaluator may also select a key object from the first key objects or select a key object from the second key objects as needed, and accordingly, the client may determine the second target key object according to the selection of the evaluator.

For example, the pattern in the current left reference image and the corresponding pattern in the right image to be evaluated are the first target key object, that is, the evaluator currently evaluates the image picture corresponding to the pattern.

When an evaluator needs to evaluate the image picture corresponding to the characters, the evaluator can directly click the image picture corresponding to the characters in the left reference image, or can directly click the image picture corresponding to the characters in the right image to be evaluated, and accordingly, the client can determine the characters in the left reference image and the corresponding characters in the right image to be evaluated as a second target key object.

And step two, displaying the evaluation options aiming at the second target key object in a preset evaluation page.

And the evaluation options comprise target evaluation indexes corresponding to the second target key objects.

When a plurality of target key objects are provided, the target evaluation index returned by the server may include a target evaluation index corresponding to each target key object, and one target key object may correspond to one target evaluation index or to a plurality of target evaluation indexes. The target evaluation indexes corresponding to different target key objects may be the same or different.

After the client determines the second target key object, the target evaluation index corresponding to the second target key object and the corresponding multiple evaluation levels can be displayed to update the evaluation index area, and furthermore, an evaluator can evaluate the image quality of the second target key object in the updated evaluation index area.

In addition, the client can mark a second target key object to remind the evaluator of the image area which needs to be evaluated currently, and the method can further include the following steps: and marking the second target key object in the reference image and the image to be evaluated in a preset marking mode respectively.

The preset marking mode may be set by a technician according to experience, for example, the target key object may be marked by a solid circle, or the target key object may be marked by a dotted circle.

In an implementation manner, referring to fig. 4, fig. 4 is a schematic display diagram of a preset evaluation interface provided in the embodiment of the present application.

After the second target key object is determined, the client may mark the second target key object in the reference image and the image to be evaluated respectively in the form of an implementation circle, so as to prompt an evaluator to evaluate the image quality of the second target key object.

Correspondingly, for the above example, after the evaluator evaluates the patterns in the reference image and the image to be evaluated, the evaluator may select to evaluate the image picture corresponding to the text, and at this time, the evaluator may click the image picture corresponding to the text in the evaluation content area; the evaluator can also click a rightward arrow of the evaluation prompt area to instruct the client to switch the current key object to be evaluated to the next key object in the key object arrangement sequence.

Correspondingly, the client may determine the characters in the reference image and the corresponding characters in the image to be evaluated, and the client may mark the image pictures corresponding to the determined characters as a key object that the evaluator needs to evaluate at present, as shown in fig. 5.

In addition, the evaluator may double click a mouse in the evaluation content area, or the evaluator may click a left arrow in the evaluation prompt area to instruct the client to switch the key object currently needing to be evaluated to the previous key object in the key object arrangement order.

In addition, in order to avoid influencing the evaluation of the image quality by the evaluator, the client may cancel marking the key object, and the method may further include the following steps: when a unmark instruction is received, unmarking the first target key object.

The client marks the second target key object, which may affect the evaluator to browse the image, so that the evaluator may select to cancel the mark when browsing the image. For example, the evaluator may click the "close prompt" button in the evaluation prompt area, and accordingly, the client may cancel marking the second target key object, and the "close prompt" button is updated to the "open prompt" button.

Referring to fig. 6, fig. 6 is a flowchart of an example of image display provided in an embodiment of the present application, where the method may include the following steps:

s601: and the server acquires the reference image and the image to be evaluated sent by the client.

S602: the server determines a first image scene and a first key object represented by the image picture of the reference image, and a second image scene and a second key object represented by the image picture of the image to be evaluated.

S603: the server determines whether the first image scene is the same as the second image scene, if not, S604 is performed, and if so, S605 is performed.

S604: and the server sends a reminding message for replacing the image to the client.

S605: the server judges whether the similarity between the first key object and the second key object is smaller than a preset similarity threshold, if so, the step S604 is executed, and if not, the step S606 is executed.

S606: the server determines a target evaluation index corresponding to the target image scene and the target key object according to the target image scene represented by the image picture of the target image, the target key object in the image picture of the target image and the corresponding relation between the preset image scene, the preset key object and the evaluation index.

Wherein the target image is a reference image or an image to be evaluated.

S607: the server sends the target evaluation index and a plurality of evaluation levels corresponding to the target evaluation index to the client.

S608: the client displays the reference image, the image to be evaluated, the target evaluation index and a plurality of evaluation levels corresponding to the target evaluation index in a preset evaluation page.

S609: and the client acquires an evaluation result aiming at the first target key object and input by an evaluator.

S6010: the client receives a key object switching instruction.

S6011: and the client displays the evaluation options aiming at the second target key object in a preset evaluation page.

Referring to fig. 7, fig. 7 is a schematic diagram of an evaluation process according to an embodiment of the present application.

In fig. 7, a user may be understood as an evaluator in the embodiment of the present application, a front end may be understood as a client to which the evaluator logs in the embodiment of the present application, a back end may be understood as a server in the embodiment of the present application, and a database may be a storage space used by the server to store data.

The user can create an evaluation task aiming at the image to be evaluated and the reference image at the front end and upload the reference image and the image to be evaluated. The reference image and the image to be evaluated can be picture images or video images.

The front end can submit the picture/video to the back end, which is equivalent to that in the embodiment of the application, the client sends the reference image and the image to be evaluated to the server.

The back end can then hold the picture/video, and it can be understood that the server can store the reference image and the image to be evaluated locally.

In addition, the back end can also analyze the picture/video content, which is equivalent to that in the embodiment of the application, the server determines whether the content of the reference image is consistent with the content of the image to be evaluated according to the first image scene, the first key object, the second image scene and the second key object.

And if the contents of the two files are different, informing the client, namely in the embodiment of the application, if the contents of the reference image are inconsistent with the contents of the image to be evaluated, sending a reminding message of replacing the image to the client by the server.

Correspondingly, the front end can prompt that the evaluation task is failed to generate, remind the user that the file contents are different, and prompt the user to detect the file and upload the file again.

And if the contents of the two files are the same, the back end selects an index matched with the contents from the database, which is equivalent to that in the embodiment of the application, if the contents of the reference image are consistent with the contents of the image to be evaluated, the server determines a target evaluation index corresponding to the target image scene and the target key object according to the target image scene represented by the image picture of the target image, the target key object in the image picture and the preset corresponding relation between the image scene, the key object and the evaluation index.

Furthermore, the back end can return the picture/video, the point to be evaluated and the index to the front end, which is equivalent to that in the embodiment of the application, the server sends the target evaluation index aiming at the reference image and the image to be evaluated and a plurality of evaluation grades to the client.

Then, the front end can generate an evaluation task and display an evaluation page, evaluation points and indexes to a user, which is equivalent to that in the embodiment of the application, the client displays a reference image, an image to be evaluated, a target evaluation index and a corresponding evaluation grade in a preset evaluation page.

In addition, the back end can update the training set based on machine learning in an asynchronous message mode, and it can be understood that the server can update the corresponding relation between the preset image scene, the key object and the evaluation index through machine learning, so as to further improve the effectiveness of the evaluation result obtained when the image quality is subsequently evaluated.

Corresponding to the embodiment of the method in fig. 1, referring to fig. 8, fig. 8 is a structural diagram of an image display apparatus provided in an embodiment of the present application, where the apparatus may include:

an obtaining module 801, configured to obtain a reference image and an image to be evaluated;

the determining module 802 is configured to determine a target evaluation index corresponding to a target image scene and a target key object according to a target image scene represented by an image picture of the target image, the target key object in the image picture, and a preset correspondence between the image scene, the key object, and the evaluation index, where the target image is a reference image and/or an image to be evaluated, and the key object is an area of interest in the image picture;

the first sending module 803 is configured to send the target evaluation index to the client, so that the client displays the reference image, the image to be evaluated, and the target evaluation index in a preset evaluation page.

Optionally, the apparatus further comprises:

the processing module is used for determining a first image scene and a first key object represented by an image picture of a reference image, and a second image scene and a second key object represented by an image picture of an image to be evaluated;

determining whether the content of the reference image is consistent with the content of the image to be evaluated according to the first image scene, the first key object, the second image scene and the second key object; and under the condition of consistent determination, determining target evaluation indexes corresponding to the target image scene and the target key objects according to the target image scene represented by the image picture of the target image, the target key objects in the image picture and the preset corresponding relation between the image scene, the key objects and the evaluation indexes.

if the first image scene is the same as the second image scene, and the similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold, determining that the content of the reference image is consistent with the content of the image to be evaluated; and/or the presence of a gas in the gas,

and if the first image scene is different from the second image scene and/or the similarity between the first key object and the second key object is smaller than a preset similarity threshold, determining that the content of the reference image is inconsistent with the content of the image to be evaluated.

Optionally, the apparatus further comprises:

and sending the plurality of evaluation levels to the client so that the client displays the plurality of evaluation levels in a preset evaluation page.

Corresponding to the embodiment of the method in fig. 2, referring to fig. 9, fig. 9 is a block diagram of an image display apparatus provided in an embodiment of the present application, where the apparatus may include:

an obtaining module 901, configured to obtain a reference image and an image to be evaluated;

a receiving module 902, configured to receive a target evaluation index sent by a server; the target evaluation index is an evaluation index which is determined by the server and corresponds to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, the target image is a reference image and/or an image to be evaluated, and the key object is an interested area in the image picture;

the first display module 903 is configured to display the reference image, the image to be evaluated, and the target evaluation index in a preset evaluation page.

Optionally, the apparatus further comprises:

and displaying a plurality of evaluation levels in a preset evaluation page.

Optionally, the number of target objects is multiple;

the device still includes:

and displaying evaluation options aiming at the second target key object in a preset evaluation page, wherein the evaluation options comprise target evaluation indexes corresponding to the second target key object.

Optionally, the apparatus further comprises:

and the canceling marking module is used for canceling the marking of the second target key object when a canceling marking instruction is received.

The embodiment of the present application further provides a server, as shown in fig. 10, including a memory 1001 and a processor 1002;

a memory 1001 for storing a computer program;

the processor 1002 is configured to implement the image display method according to the embodiment of the present application when executing the program stored in the memory 1001.

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

determining a target evaluation index corresponding to a target image scene and a target key object according to the target image scene represented by an image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, wherein the target image is a reference image and/or an image to be evaluated, and the key object is an interested area in the image picture;

and sending the target evaluation index to the client so that the client displays the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

It should be noted that other implementation manners of the image display method are the same as those of the embodiment of the method, and are not described herein again.

The server may be provided with a communication interface for enabling communication between the server and another device.

An embodiment of the present application further provides a client, as shown in fig. 11, including a memory 1101 and a processor 1102;

a memory 1101 for storing a computer program;

the processor 1102 is configured to implement the image display method according to the embodiment of the present application when executing the program stored in the memory 1101.

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

receiving a target evaluation index sent by a server; the target evaluation index is an evaluation index which is determined by the server and corresponds to a target image scene and a target key object in the image picture according to the target image scene represented by the image picture of the target image, the target key object in the image picture and a preset corresponding relation between the image scene, the key object and the evaluation index, the target image is a reference image and/or an image to be evaluated, and the key object is an interested area in the image picture;

The client may be provided with a communication interface for enabling communication between the client and another device.

The processor, the communication interface, and the memory are configured to communicate with each other through a communication bus, where the communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

The embodiment of the present application further provides a computer-readable storage medium, in which instructions are stored, and when the computer-readable storage medium runs on a computer, the computer is enabled to execute the image display method provided by the embodiment of the present application.

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

Embodiments of the present application further provide a computer program product containing instructions, which when run on a computer, cause the computer to execute the image display method provided by the embodiments of the present application.

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

Specifically, the image display method includes:

acquiring a reference image and an image to be evaluated;

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus, the server, the client, the computer-readable storage medium, and the computer program product embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.

The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. An image display method, characterized in that the method comprises:

acquiring a reference image and an image to be evaluated;

2. The method according to claim 1, wherein before determining the target evaluation index corresponding to the target image scene and the target key object according to the target image scene represented by the image picture of the target image, the target key object in the image picture, and the preset corresponding relationship between the image scene, the key object and the evaluation index, the method further comprises:

3. The method of claim 2, wherein determining whether the content of the reference image and the content of the image to be evaluated are consistent according to the first image scene, the first key object, the second image scene, and the second key object comprises:

4. The method according to claim 1, wherein after determining a target evaluation index corresponding to the target image scene and the target key object according to the target image scene represented by the image picture of the target image, the target key object in the image picture, and the preset corresponding relationship between the image scene, the key object and the evaluation index, the method further comprises:

5. An image display method, characterized in that the method comprises:

acquiring a reference image and an image to be evaluated;

6. The method of claim 5, further comprising:

7. The method of claim 5, wherein the target key object is a plurality;

the method further comprises the following steps:

8. The method of claim 7, wherein after said receiving a key object switch instruction, the method further comprises:

9. The method of claim 8, further comprising:

when a unmark instruction is received, unmarking the second target key object.

10. An image display apparatus, characterized in that the apparatus comprises:

11. The apparatus of claim 10, further comprising:

12. The apparatus according to claim 11, wherein the processing module is specifically configured to determine whether the first image scene is the same as the second image scene, and whether a similarity between the first key object and the second key object is greater than or equal to a preset similarity threshold;

13. The apparatus of claim 10, further comprising:

14. An image display apparatus, characterized in that the apparatus comprises:

and the first display module is used for displaying the reference image, the image to be evaluated and the target evaluation index in a preset evaluation page.

15. The apparatus of claim 14, further comprising:

16. The apparatus of claim 14, wherein the target object is plural;

the device further comprises:

17. The apparatus of claim 16, further comprising:

18. The apparatus of claim 17, further comprising:

19. A server, comprising a memory and a processor;

the memory is used for storing a computer program;

the processor, when executing the program stored in the memory, implementing the method steps of any of claims 1-4.

20. A client comprising a memory and a processor;

the memory is used for storing a computer program;

the processor, when executing the program stored in the memory, implementing the method steps of any of claims 5-9.

21. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.

22. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any of the claims 5-9.