Image quality evaluation method, device, system, electronic device and storage medium

Abstract

Embodiments of the present application disclose an image quality evaluation method, device, system, electronic equipment and storage medium, and relate to the technical field of image processing. The method comprises: receiving an image quality evaluation request sent by a client and containing an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image; obtaining the to-be-evaluated image according to the image identifier of the to-be-evaluated image, and obtaining the reference image according to the image identifier corresponding to the reference image; evaluating the quality of the to-be-evaluated image relative to the reference image by calling an image quality evaluation tool to obtain an image quality evaluation result; and sending the image quality evaluation result to the client to enable the client to generate and display a result display page based on the image quality evaluation result. The technical scheme provided by the embodiments of the present application can solve the problems of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art, and can improve the accuracy and evaluation efficiency of image quality evaluation.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of image processing, and in particular to an image quality evaluation method, device, system, electronic device and storage medium. BACKGROUND

[0002] The application software of e-commerce carries a large number of images (such as pictures or videos) to show the information of the goods. In order to enable users to obtain better use experience, various application software all pursue to provide users with high-quality images with higher definition and stronger visual sense.

[0003] The prior art is to evaluate the image definition of the application software by artificial visual assessment. Although this method is simple and easy to implement, it has the following problems: 1. The artificial evaluation has low accuracy and is greatly affected by subjectivity. 2. The artificial evaluation has high limitations and cannot identify subtle differences. 3. The artificial evaluation cannot accurately give the quantitative results of the definition of pictures and videos, and is relatively arbitrary. 4. The artificial evaluation is low in efficiency and high in cost. Therefore, it is necessary to design an image quality evaluation method to improve the accuracy and evaluation efficiency of image quality evaluation. SUMMARY

[0004] Embodiments of the present application provide an image quality evaluation method, device, system, electronic device and storage medium to improve the accuracy and evaluation efficiency of image quality evaluation.

[0005] In a first aspect, embodiments of the present application provide an image quality evaluation method applied to a server, which comprises:

[0006] receiving an image quality evaluation request sent by a client and containing an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image;

[0007] obtaining the to-be-evaluated image according to the image identifier of the to-be-evaluated image, and obtaining the reference image according to the image identifier corresponding to the reference image;

[0008] evaluating the quality of the to-be-evaluated image relative to the reference image by calling an image quality evaluation tool to obtain an image quality evaluation result;

[0009] sending the image quality evaluation result to the client to enable the client to generate and display a result display page based on the image quality evaluation result.

[0010] In a second aspect, embodiments of the present application provide an image quality evaluation method applied to a client, which comprises:

[0011] when detecting an image quality evaluation trigger operation, obtaining an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image;

[0012] sending an image quality evaluation request to a server, the image quality evaluation request comprising an image identifier corresponding to the image to be evaluated and an image identifier corresponding to the reference image;

[0013] receiving an image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generating a result display page based on the image quality evaluation result, and displaying the result display page.

[0014] In a third aspect, an embodiment of the present application provides an image quality evaluation device integrated in a server, the device comprising:

[0015] a request receiving module configured to receive an image quality evaluation request sent by a client, the image quality evaluation request comprising an image identifier corresponding to the image to be evaluated and an image identifier corresponding to the reference image;

[0016] an image obtaining module configured to obtain the image to be evaluated according to the image identifier corresponding to the image to be evaluated, and obtain the reference image according to the image identifier corresponding to the reference image;

[0017] an image evaluation module configured to evaluate the quality of the image to be evaluated relative to the reference image by calling an image quality evaluation tool, to obtain an image quality evaluation result;

[0018] a result sending module configured to send the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result.

[0019] In a fourth aspect, an embodiment of the present application provides an image quality evaluation device integrated in a client, the device comprising:

[0020] an identifier obtaining module configured to, when detecting an image quality evaluation triggering operation, obtain an image identifier corresponding to the image to be evaluated and an image identifier corresponding to the reference image;

[0021] a request sending module configured to send an image quality evaluation request to a server, the image quality evaluation request comprising an image identifier corresponding to the image to be evaluated and an image identifier corresponding to the reference image;

[0022] a result display module configured to receive an image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generate a result display page based on the image quality evaluation result, and display the result display page.

[0023] In a fifth aspect, an embodiment of the present application provides an image quality evaluation system, comprising:

[0024] The client is configured to: acquire an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image when detecting an image quality evaluation trigger operation; send an image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image to a server; receive an image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generate a result display page based on the image quality evaluation result, and display the result display page;

[0025] The server is configured to: receive the image quality evaluation request, acquire the image to be evaluated according to the image identifier of the image to be evaluated, and acquire the reference image according to the image identifier corresponding to the reference image; evaluate the quality of the image to be evaluated relative to the reference image by calling an image quality evaluation tool to obtain an image quality evaluation result; and send the image quality evaluation result to the client.

[0026] In a sixth aspect, an electronic device is provided, and the electronic device includes:

[0027] one or more processors;

[0028] a storage device configured to store one or more programs;

[0029] When the one or more programs are executed by the one or more processors, the one or more processors implement the image quality evaluation method described in any of the embodiments of the present application.

[0030] In a seventh aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, which, when executed by a processor, implements the image quality evaluation method described in any of the embodiments of the present application.

[0031] The embodiments of the present application provide an image quality evaluation method, device, system, electronic device, and storage medium. In the method, an image quality evaluation request containing an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image is received from a client; the image to be evaluated is acquired according to the image identifier of the image to be evaluated, and the reference image is acquired according to the image identifier corresponding to the reference image; the quality of the image to be evaluated relative to the reference image is evaluated by calling an image quality evaluation tool to obtain an image quality evaluation result; and the image quality evaluation result is sent to the client, so that the client generates and displays a result display page based on the image quality evaluation result. The embodiments of the present application automatically acquire the image to be evaluated and the reference image by the server and evaluate the quality of the image to be evaluated, which can solve the problems of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art, and can improve the accuracy and efficiency of image quality evaluation.

[0032] It should be understood that the matters described in this section are not intended to identify key or essential features of the embodiments of the application, nor are they used to limit the scope of the application. Other features of the application will be apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0033] The accompanying drawings are used to better understand the present application, and do not constitute a limitation on the present application. Among them:

[0034] Figure 1 The first flowchart of the image quality evaluation method provided by the embodiment of the application;

[0035] Figure 2 The second flowchart of the image quality evaluation method provided by the embodiment of the application;

[0036] Figure 3 The third flowchart of the image quality evaluation method provided by the embodiment of the application;

[0037] Figure 4 The schematic diagram of the image evaluation trigger interface provided by the embodiment of the application;

[0038] Figure 5 The fourth flowchart of the image quality evaluation method provided by the embodiment of the application;

[0039] Figure 6A The schematic diagram of the image upload interface provided by the embodiment of the application;

[0040] Figure 6B The schematic diagram of the resource management page provided by the embodiment of the application;

[0041] Figure 6C The schematic diagram of the task management page provided by the embodiment of the application;

[0042] Figure 6D The schematic diagram of the evaluation result comparison chart of the image to be evaluated provided by the embodiment of the application;

[0043] Figure 7A The signaling interaction schematic diagram of the image quality evaluation provided by the embodiment of the application;

[0044] Figure 7B The execution schematic diagram of the image quality evaluation provided by the embodiment of the application;

[0045] Figure 8 The first structure schematic diagram of the image quality evaluation device provided by the embodiment of the application

[0046] Figure 9 The second structure schematic diagram of the image quality evaluation device provided by the embodiment of the application;

[0047] Figure 10 is a structural schematic diagram of an electronic device for implementing the embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in a clear and complete manner with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0049] Embodiment one

[0050] Figure 1 A first flowchart of an image quality evaluation method provided by the embodiments of the present application, the embodiment can be applicable to the case of evaluating the quality of an image to be evaluated. The image quality evaluation method provided by the embodiment can be executed by the image quality evaluation device provided by the fifth embodiment of the present application. The device can be realized by software and / or hardware, and integrated in a server for executing the method.

[0051] Referring to Figure 1 , the method of the embodiment includes but is not limited to the following steps:

[0052] S110, receiving an image quality evaluation request sent by a client and containing an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image.

[0053] The image to be evaluated is an image after the reference image is uploaded to the application software; the reference image is an image after a product is photographed. The image to be evaluated is a picture, and the reference image is a picture; or the image to be evaluated is a video, and the reference image is a video. The image quality evaluation at least includes image definition evaluation.

[0054] In the embodiments of the present application, when a user wants to evaluate the quality of the image to be evaluated compared with the reference image, the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image can be selected in the image evaluation triggering interface of the client, and then the client sends the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image in the image quality evaluation request to the server. The server receives the image quality evaluation request sent by the client.

[0055] Optionally, the image quality evaluation request can include an image identifier corresponding to the image to be evaluated and an image identifier corresponding to the reference image. When the server receives the image quality evaluation request, an image quality evaluation task including the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image is created based on the image quality evaluation request.

[0056] Optionally, the image quality evaluation request can include multiple image identifiers corresponding to multiple images to be evaluated and an image identifier corresponding to a reference image. When the server receives the image quality evaluation request, N image quality evaluation tasks corresponding to the multiple images to be evaluated are created based on the image quality evaluation request. N is the number of image identifiers corresponding to the images to be evaluated in the image quality evaluation request. Each image quality evaluation task includes an image identifier corresponding to a different image to be evaluated in the image quality evaluation request and an image identifier corresponding to the reference image. That is, one image quality evaluation task includes an image identifier of one image to be evaluated and an image identifier of one reference image, and each image quality evaluation task includes a different image identifier of an image to be evaluated, and each image quality evaluation task includes the same image identifier of the reference image, which is the image identifier of the reference image in the image quality evaluation request.

[0057] Optionally, the image quality evaluation request can also include multiple image identifiers corresponding to multiple images to be evaluated and multiple image identifiers corresponding to multiple reference images. When the server receives the image quality evaluation request, multiple image quality evaluation tasks are created for each image to be evaluated based on the image quality evaluation request. The specific creation method can be: for each image identifier corresponding to an image to be evaluated in the image quality evaluation request, the image identifier corresponding to the current image to be evaluated is paired with each image identifier corresponding to a reference image in the image quality evaluation request, and an image quality evaluation task is created for each pairing result. Each image quality evaluation task created includes an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image in the corresponding pairing result. For example, the image quality evaluation request includes ID_1 of image to be evaluated 1, ID_2 of image to be evaluated 2, ID_3 of reference image 3, and ID_4 of reference image 4. For the current image to be evaluated 1 ID_1, ID_1 is paired with ID_3 of reference image 3 and ID_4 of reference image 4, and image quality evaluation task 1 including ID_1 and ID_3 and image quality evaluation task 2 including ID_1 and ID_4 are created. For the current image to be evaluated 2 ID_2, ID_2 is paired with ID_3 of reference image 3 and ID_4 of reference image 4, and image quality evaluation task 3 including ID_2 and ID_3 and image quality evaluation task 4 including ID_2 and ID_4 are created.

[0058] Optionally, the image quality evaluation request can further include an image identifier corresponding to the image to be evaluated and image identifiers corresponding to the plurality of reference images. When the server receives the image quality evaluation request, M image quality evaluation tasks are created for the image to be evaluated based on the image quality evaluation request, where M is the number of image identifiers corresponding to the reference images included in the image quality evaluation request. Each image quality evaluation task includes the image identifier corresponding to the image to be evaluated in the image quality evaluation request and the image identifiers corresponding to different reference images. That is, an image quality evaluation task includes an image identifier of an image to be evaluated and an image identifier of a reference image, and the image identifiers of the reference images included in each image quality evaluation task are different, the image identifier of the image to be evaluated included in each image quality evaluation task is the same, and the image identifier of the image to be evaluated is the image identifier of the image to be evaluated in the image quality evaluation request.

[0059] S120, the image to be evaluated is obtained according to the image identifier of the image to be evaluated, and the reference image is obtained according to the image identifier corresponding to the reference image.

[0060] In the embodiments of the present application, after the server receives the image quality evaluation request including the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image, the current image to be evaluated can be obtained according to the image identifier corresponding to the current image to be evaluated included in the current image quality evaluation task, and the current reference image can be obtained according to the image identifier corresponding to the current reference image included in the current image quality evaluation task, for each image quality evaluation task respectively by direct or indirect method, so as to obtain the image to be evaluated and the reference image of each image quality evaluation task in turn.

[0061] Specifically, the execution process of the direct acquisition method is: if the image is stored in the storage component of the server for storing images, the server obtains the image to be evaluated from the storage component according to the image identifier of the image to be evaluated, and obtains the reference image from the storage component according to the image identifier corresponding to the reference image. The execution process of the indirect acquisition method is: if the image is stored in the server, the server finds the server storage path of the image to be evaluated and the server storage path of the reference image respectively according to the image identifier, and then obtains the image to be evaluated and the reference image according to the storage path. If the image is stored in the cloud, the server finds the cloud storage path of the image to be evaluated and the cloud storage path of the reference image respectively according to the image identifier, and then obtains the image to be evaluated and the reference image according to the cloud storage path. Preferably, the server should store the association table of the server storage path of the image and the image identifier or the association table of the cloud storage path and the image identifier.

[0062] S130, evaluate the quality of the image to be evaluated relative to the reference image by calling the image quality evaluation tool to obtain the image quality evaluation result.

[0063] In the embodiment of the application, after the server obtains the image to be evaluated and the reference image of the current image quality evaluation task, the quality of the current image to be evaluated relative to the current reference image is evaluated by calling the image quality evaluation tool to obtain the image quality evaluation result corresponding to the current image quality evaluation task, so that the image quality evaluation result of the image to be evaluated of each image quality evaluation task is obtained in turn. The server can call the image quality evaluation tool through a Python calling script, the image quality evaluation tool can be a video quality evaluation standard (Video Multimethod Assessment Fusion, VMAF) developed by Netflix and open sourced on Github, and can also be other encapsulation tools based on VMAF.

[0064] Optionally, in addition to the server calling the image quality evaluation tool after obtaining the current image quality evaluation task, the image quality evaluation tool can also check whether there is an image quality evaluation task to be executed at a regular time, and if so, obtain the image quality evaluation task, and obtain the image to be evaluated and the reference image according to the image identifier of the image to be evaluated and the image identifier of the reference image of the image quality evaluation task. The created image quality evaluation tasks can be saved in a task queue, and the image quality evaluation tool checks whether there is an image quality evaluation task to be executed in the task queue at a regular time. Optionally, a task data maintenance table can also be created for the image quality evaluation task, so that after obtaining the image quality evaluation result corresponding to the current image quality evaluation task, the image quality evaluation result is saved in the task maintenance data table, and the task management page of the client can also be used to view; in addition to the field of the image quality evaluation result, the task maintenance data table can also include at least one of the fields of task identifier, image identifier of the image to be evaluated, image identifier of the reference image, task state and task description. The task state includes executing, executing successfully, executing failed and published. The task data maintenance table is shown in Table 1 as follows:

[0065] Table 1, task data maintenance table

[0066] Field Type Meaning task_id long task identification reference_id long image identification of reference image distorted_id long image identification of image to be evaluated status int task status score int image quality evaluation result task_desc string task description

[0067] S140, send the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result.

[0068] In the embodiment of the present application, after the server obtains the image quality evaluation result of the to-be-evaluated image relative to the reference image, the server sends the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result.

[0069] The technical scheme provided by the embodiment of the present application comprises the following steps: receiving an image quality evaluation request sent by a client, the image quality evaluation request comprising an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image; obtaining the to-be-evaluated image according to the image identifier of the to-be-evaluated image, and obtaining the reference image according to the image identifier corresponding to the reference image; calling an image quality evaluation tool to evaluate the quality of the to-be-evaluated image relative to the reference image, and obtaining an image quality evaluation result; and sending the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result. By obtaining the to-be-evaluated image and the reference image through the server and evaluating the quality of the to-be-evaluated image, the present application can solve the problems of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art, and can improve the accuracy of image quality evaluation.

[0070] Embodiment two

[0071] Figure 2 The second flowchart of the image quality evaluation method provided by the embodiment of the present application. The embodiment of the present application is optimized on the basis of the above-mentioned embodiment, and the specific optimization is that the embodiment explains and describes the storage process of the image and the acquisition process of the image in detail.

[0072] Referring to Figure 2 The method of the embodiment of the present application comprises but is not limited to the following steps:

[0073] S210, receiving an image uploaded by a client, storing the image in a cloud storage component, and saving a uniform resource locator (URL) of the image and an image identifier in a resource maintenance data table.

[0074] The image uploaded by the client comprises a to-be-evaluated image and a reference image.

[0075] In the embodiment of the present application, a user can select one or more to-be-uploaded images in an image upload interface of a client and upload the images to a server. The server receives the images uploaded by the user in the client, and stores the images in a cloud storage component in batches. Each image is assigned a uniform resource locator (URL) by the cloud storage component. Since the URL is not unique, the server also needs to generate an image identifier corresponding to each image.

[0076] Optionally, the application does not specifically limit the generation method of the image identifier, which can be that the server converts the image URL into the image identifier according to a hash operation, or can be that the image identifier is determined by using a message digest algorithm (MD5), an accumulated number of historically uploaded images, or the like.

[0077] Preferably, when the user selects one or more images to be uploaded in the image uploading interface of the client, the user can also add corresponding image information to the images, and upload the images and the image information corresponding to the images to the server. After the server receives the images and the image information corresponding to the images, the server stores the images in the cloud storage component, and saves the URL, the image identifier, and the image information of the images in the resource maintenance data table, and the resource management page of the client can support viewing. The image information includes at least one of image resolution information, image source application (APP) information, image source APP version information, and image description information. The resource maintenance data table is shown in Table 2.

[0078] Table 2, resource maintenance data table

[0079] Field Type Meaning file_url string image URL file_id long image identification resolution_w int image resolution information - width resolution_h int image resolution information - height source string image source APP information source_version string image source APP version information source_desc string image description information

[0080] Preferably, when the server receives the uploading record viewing request sent by the client, the server generates image historical uploading records based on the resource maintenance data table and sends the historical uploading records to the client. The record information of the image historical uploading records includes at least one of the image identifier of the uploaded image, the URL of the uploaded image, the uploading time, the uploader, and the image information.

[0081] S220, receiving an image quality evaluation request sent by the client, the image quality evaluation request containing an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image.

[0082] S230, finding the URL of the to-be-evaluated image from the resource maintenance data table according to the image identifier of the to-be-evaluated image, and downloading the to-be-evaluated image from the cloud storage component according to the URL of the to-be-evaluated image; and finding the URL of the reference image from the resource maintenance data table according to the image identifier of the reference image, and downloading the reference image from the cloud storage component according to the URL of the reference image.

[0083] In the embodiment of the application, after the server receives the image quality evaluation request containing the image identifier corresponding to the to-be-evaluated image and the image identifier corresponding to the reference image, the server first finds the corresponding URL based on the resource maintenance data table according to the image identifier, so as to find the URL of the to-be-evaluated image and the URL of the reference image. Then, the server downloads the to-be-evaluated image and the reference image from the cloud storage component according to the URL of the to-be-evaluated image and the URL of the reference image, respectively.

[0084] Optionally, the downloaded to-be-evaluated image and the reference image are saved in a local folder of the server, to obtain a saving path of the to-be-evaluated image and the reference image.

[0085] S240, evaluating the quality of the to-be-evaluated image relative to the reference image by calling the image quality evaluation tool, to obtain an image quality evaluation result.

[0086] In the embodiments of the present application, when evaluating the to-be-evaluated image, the resource type of the to-be-evaluated image is first checked to determine whether the to-be-evaluated image is a picture or a video; if it is a picture, a picture evaluation module in the image quality evaluation tool is called; if it is a video, a video evaluation module in the image quality evaluation tool is called.

[0087] Optionally, the to-be-evaluated image can also be set with parameters such as resolution, frame rate (when the to-be-evaluated image is a video), etc., and the image quality evaluation tool is called to evaluate the to-be-evaluated image according to the saving path of the to-be-evaluated image and the reference image and the set parameters. In addition, the to-be-evaluated image can also be set with a saving path of the image quality evaluation result, so that the server can find the image quality evaluation result of the to-be-evaluated image according to the saving path of the image quality evaluation result and parse the image quality evaluation result.

[0088] Optionally, the image quality evaluation result can be in the form of a score, such as 0-100 points, and the server can round off the image quality evaluation result, such as rounding off 80.3 points to 80 points.

[0089] S250, sending the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result.

[0090] Preferably, when the server receives the task record viewing request sent by the client, historical task records are generated based on the resource maintenance data table and sent to the client, wherein the record information of the historical task records includes at least one of a task identifier, a task creation time, an image identifier of the reference image and an image identifier of the to-be-evaluated image corresponding to the task, source information of the reference image, source information of the to-be-evaluated image, an evaluation result of the to-be-evaluated image, a task creator, image description information, and a task publishing state. The task publishing state includes not published and published.

[0091] The technical scheme provided by the embodiment comprises the following steps: receiving an image uploaded by a client, storing the image in a cloud storage component, and saving a uniform resource locator (URL) of the image and an image identifier in a resource maintenance data table; receiving an image quality evaluation request sent by the client, the request comprising an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image; finding the URL of the to-be-evaluated image from the resource maintenance data table according to the image identifier of the to-be-evaluated image, and downloading the to-be-evaluated image from the cloud storage component according to the URL of the to-be-evaluated image; finding the URL of the reference image from the resource maintenance data table according to the image identifier of the reference image, and downloading the reference image from the cloud storage component according to the URL of the reference image; evaluating the quality of the to-be-evaluated image relative to the reference image by calling an image quality evaluation tool, and obtaining an image quality evaluation result; and sending the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result. The application can solve the problems of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art, and can improve the accuracy of image quality evaluation. By storing the images in the cloud, the server can obtain the to-be-evaluated image and the reference image from the cloud through the URL before evaluating the to-be-evaluated image, thereby meeting the user's demand for evaluating a large number of images.

[0092] Embodiment three

[0093] Figure 3 A third flowchart of an image quality evaluation method provided by the embodiment of the application; Figure 4 The embodiment of the application provides a schematic diagram of an image evaluation trigger interface. The embodiment can be applicable to the case of evaluating the quality of a to-be-evaluated image. The image quality evaluation method provided by the embodiment can be executed by the image quality evaluation device provided by the embodiment six of the application. The device can be realized by software and / or hardware, and integrated in the client that executes the method.

[0094] Reference Figure 3 The method of the embodiment comprises but is not limited to the following steps:

[0095] S310, when detecting an image quality evaluation trigger operation, acquiring an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image.

[0096] In the embodiment of the application, when a user wants to evaluate the quality of a to-be-evaluated image relative to a reference image, the user can trigger an image quality evaluation operation in the image evaluation trigger interface of the client. When the client detects that the image quality evaluation operation is triggered, the image identifier corresponding to the to-be-evaluated image and the image identifier corresponding to the reference image are acquired according to the to-be-evaluated image and the reference image selected by the user in the image evaluation trigger interface.

[0097] S320, sending, to the server, an image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image.

[0098] In the embodiment of the present application, after the client obtains the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image, the image identifier corresponding to the evaluation image and the image identifier corresponding to the reference image are carried in the image quality evaluation request and sent to the server, so that when the server receives the image quality evaluation request, the server creates an image quality evaluation task for the image to be evaluated based on the image quality evaluation request.

[0099] Preferably, the user can also add corresponding task description information for the image quality evaluation task in the image evaluation trigger interface, so as to mark the image quality evaluation task.

[0100] As Figure 4 The image evaluation trigger interface is shown in the schematic diagram, and as can be seen from the diagram, the user needs to select the reference image and the image to be evaluated in the image evaluation trigger interface, and add the task description information. When the user clicks the submit button of the interface, the image quality evaluation request can be sent to the server.

[0101] S330, receiving the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generating a result display page based on the image quality evaluation result, and displaying the result display page.

[0102] In the embodiment of the present application, after the server receives the image quality evaluation request, the quality of the image to be evaluated is evaluated in response to the image quality evaluation request, the image quality evaluation result is obtained, and the image quality evaluation result is sent to the client. The client receives the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server. When the client receives the result display instruction of the user, the image quality evaluation result of the image to be evaluated is displayed in the result display page according to the preset display method.

[0103] The technical scheme provided in the embodiment, by detecting the image quality evaluation trigger operation, obtaining the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image, sending an image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image to the server, receiving the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generating a result display page based on the image quality evaluation result, and displaying the result display page. The present application sends an image quality evaluation request to the server through the client, so that the server evaluates the quality of the image to be evaluated relative to the reference image, which can solve the problem of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art, and can improve the accuracy of image quality evaluation.

[0104] Embodiment Four

[0105] Figure 5 A fourth flow diagram of an image quality evaluation method provided in an embodiment of the present application is shown in FIG. 4. Figure 6A A diagram of an image uploading interface provided in an embodiment of the present application is shown in FIG. 5. Figure 6B A diagram of a resource management page provided in an embodiment of the present application is shown in FIG. 6. Figure 6C A diagram of a task management page provided in an embodiment of the present application is shown in FIG. 7. Figure 6D A diagram of an evaluation result comparison chart of an image to be evaluated provided in an embodiment of the present application is shown in FIG. 8. The embodiment of the present application is optimized on the basis of the above-mentioned embodiments, and the specific optimization is that the embodiment explains the uploading process of the image in detail.

[0106] Reference Figure 5 The method of the embodiment includes but is not limited to the following steps:

[0107] S410. When an image uploading trigger operation is detected, an image to be uploaded is acquired.

[0108] The image uploaded by the client includes an image to be evaluated and a reference image.

[0109] In the embodiment of the present application, when a user wants to upload an image to a server, the user can trigger an image uploading operation on an image uploading interface of a client. When the client detects that the image uploading operation is triggered, the client acquires one or more images to be uploaded selected by the user in the image uploading interface.

[0110] Specifically, the specific process of acquiring the image to be uploaded by the client is as follows: first, it is checked whether the image to be uploaded exists in a local file of the client. If the image to be uploaded exists, the image to be uploaded is acquired from the local file. If the image to be uploaded does not exist, the image to be uploaded is downloaded from an application software storing the image to be uploaded to the local file.

[0111] S420. The image is uploaded to the server, so that the server stores the image in a cloud storage component and saves a URL of the image and an image identifier in a resource maintenance data table.

[0112] In the embodiment of the present application, after the client acquires the image to be uploaded, the image is uploaded to the server. The server receives the image uploaded by the user in the client, and stores the images in the cloud storage component in batches. Each image is assigned a corresponding URL by the cloud storage component, and a corresponding image identifier is generated for each image. The URL of the image and the image identifier are saved in the resource maintenance data table.

[0113] Preferably, when the user selects one or more images to be uploaded in the image uploading interface of the client, the user can also add corresponding image information to the images, upload the images and the image information of the images to the server, so that the server stores the images in the cloud storage component, saves the URL, image identifier and image information of the images in the resource maintenance data table, and can be viewed in the resource management page of the client. The image information includes at least one of image resolution information, image source APP information, image source APP version information and image description information.

[0114] As shown in Figure 6A The schematic diagram of the image uploading interface is shown in the figure. As can be seen from the figure, the user needs to select the images to be uploaded in the image uploading interface and add image resolution information, image source APP information, image source APP version information and image description information. When the user clicks the save button of the interface, the images and the image information of the images are uploaded to the server.

[0115] Optionally, the client can generate image historical uploading records according to the user's demand; the image historical uploading records are displayed; wherein the record information of the image historical uploading records includes at least one of the image identifier of the uploaded images, the URL of the uploaded images, the uploading time, the uploader and the image information. Specifically, the client generates an uploading record viewing request according to the user's demand, and sends the uploading record viewing request to the server, so that the server generates image historical uploading records based on the resource maintenance data table and sends the historical uploading records to the client. The client receives the historical uploading records and displays the historical uploading records to the user in the corresponding interface of the client.

[0116] As shown in Figure 6B The schematic diagram of the resource management page is shown in the figure. As can be seen from the figure, the user can see the image historical uploading records in the resource management page of the client, such as at least one of the image identifier of the uploaded images, the URL of the uploaded images, the uploading time, the uploader and the image information (such as image resolution information, image source APP information, image source APP version information and image description information).

[0117] S430, when detecting an image quality evaluation trigger operation, obtaining image identifiers corresponding to a plurality of images to be evaluated and an image identifier corresponding to a reference image.

[0118] In this embodiment, when a user wants to evaluate the quality of multiple images to be evaluated compared to a reference image, they can trigger an image quality evaluation operation in the client's image evaluation trigger interface. When the client detects that the image quality evaluation operation has been triggered, it obtains the image identifiers corresponding to the multiple images to be evaluated and the image identifier corresponding to the reference image based on the multiple images to be evaluated and the reference image selected by the user in the image evaluation trigger interface.

[0119] S440: Send an image quality assessment request to the server, which includes the image identifiers corresponding to each image to be evaluated and the image identifiers corresponding to the reference images.

[0120] In this embodiment, the client sends an image quality assessment request to the server along with image identifiers corresponding to multiple images to be evaluated and an image identifier corresponding to a reference image. That is, the image quality assessment request may contain image identifiers corresponding to multiple images to be evaluated and an image identifier corresponding to a reference image. The server creates N image quality assessment tasks corresponding to the multiple images to be evaluated based on this image quality assessment request. Here, N is the number of image identifiers corresponding to the images to be evaluated included in the image quality assessment request. The server sequentially evaluates the quality of the images to be evaluated in the N image quality assessment tasks to obtain the image quality assessment results.

[0121] Optional, in Figure 4 In the image evaluation trigger interface shown, the user can select multiple images to be evaluated. When the user clicks the submit button on this interface, an image quality evaluation request containing the image identifiers corresponding to each of the multiple images to be evaluated, as well as an image identifier referring to the image, will be sent to the server.

[0122] S450: Receive the image quality assessment results corresponding to the N image quality assessment tasks returned by the server.

[0123] Among them, the image quality assessment results corresponding to each image quality assessment task are the image quality assessment results of different images to be evaluated relative to the reference image.

[0124] In this embodiment, after obtaining the image quality assessment results corresponding to N image quality assessment tasks, the server saves the image quality assessment results in a task maintenance data table, which can be viewed on the client's task management page. The server also sends the results to the client, enabling the client to receive the image quality assessment results for N images to be evaluated from the N image quality assessment tasks. The task maintenance data table also includes at least one of the following: task identifier, image identifier of the image to be evaluated, image identifier of the reference image, task status, and task description.

[0125] Optionally, the client can generate a historical task record according to the user's demand; the historical task record is displayed; wherein the record information of the historical task record includes at least one of the task identifier, the task creation time, the image identifier of the reference image corresponding to the task and the image identifier of the to-be-evaluated image, the source information of the reference image, the source information of the to-be-evaluated image, the evaluation result of the to-be-evaluated image, the task creator, the image description information and the task publishing state. Specifically, the client generates a historical task record viewing request according to the user's demand, and sends the historical task record viewing request to the server, so that the server generates a historical task record based on the resource maintenance data table and sends the historical task record to the client. The client receives the historical task record and displays the historical task record to the user in the corresponding interface of the client.

[0126] As shown in Figure 6C The task management page schematic diagram is shown in the figure: the user can see the historical task record in the task management page of the client, such as the task identifier, the task creation time, the image identifier of the reference image corresponding to the task (such as the reference image ID in the figure), the image identifier of the to-be-evaluated image (such as the to-be-evaluated image ID in the figure), the source information of the reference image, the source information of the to-be-evaluated image, the evaluation result of the to-be-evaluated image, the task creator, the image description information and the task publishing state. Among them, the task publishing state includes two states of not published and published. If the publishing state of a task is not published, it means that the image quality evaluation result of the task cannot be used, such as cannot be used for the generation and display of the subsequent evaluation result comparison chart; if the publishing state of a task is published, it means that the image quality evaluation result of the task can be used, such as can be used for the generation and display of the subsequent evaluation result comparison chart. The user can also switch the publishing state on the task management page as needed.

[0127] S460, based on the current evaluation result of the to-be-evaluated image and the historical evaluation result of the to-be-evaluated image, a result display page containing the evaluation result comparison chart of the to-be-evaluated image is generated.

[0128] In the embodiment of the application, the client generates a line chart with the evaluation time as the horizontal coordinate and the image quality evaluation result as the vertical coordinate, and obtains the image quality evaluation result comparison chart of the to-be-evaluated target image to show the comparison result of the current evaluation result and the historical evaluation result of the to-be-evaluated image, wherein the evaluation result comparison chart of the to-be-evaluated image is shown as the line chart on the left side of Figure 6D As shown in the figure, the image quality evaluation results of the four to-be-evaluated images (such as the application name: self-developed APP, competitor APP1, competitor APP2 and competitor APP3) performed on August 1, 2021, August 16, 2021, September 1, 2021 and September 16, 2021, respectively.

[0129] Preferably, since the image to be evaluated is the image after the reference image is uploaded to the application software, when the version of the application software changes, the image quality of the object to be evaluated will also change. Therefore, the embodiment can also compare the changes of the image to be evaluated with the changes of the version of the application software. As shown in the number table on the right side of the figure, the current version information and the image quality evaluation result of the four images to be evaluated (such as the application name in the figure: self-developed APP, competitor APP1, competitor APP2, and competitor APP3) can be seen, and the difference between the image quality evaluation result and the last version is also shown. Figure 6D

[0130] The technical scheme provided by the embodiment comprises the following steps: when an image uploading trigger operation is detected, an image to be uploaded is acquired; the image is uploaded to a server, so that the server stores the image in a cloud storage component and saves the URL of the image and an image identifier in a resource maintenance data table; when an image quality evaluation trigger operation is detected, image identifiers corresponding to a plurality of images to be evaluated and an image identifier corresponding to a reference image are acquired; an image quality evaluation request containing the image identifiers corresponding to the images to be evaluated and the image identifier corresponding to the reference image is sent to the server; image quality evaluation results corresponding to a plurality of image quality evaluation tasks returned by the server are received; and based on the current evaluation result of the image to be evaluated and the historical evaluation result of the image to be evaluated, a result display page containing an evaluation result comparison chart of the image to be evaluated is generated. The client of the application uploads a plurality of images to the server to enable the server to store the images in the cloud, and sends an image quality evaluation request to the server to enable the server to acquire the images to be evaluated and the reference image from the cloud according to the image quality evaluation request and then evaluate the images to be evaluated. The scheme can meet the demand of the user for evaluating a large number of images.

[0131] Embodiment five

[0132] Figure 7A A signaling interaction diagram of image quality evaluation provided by the embodiment of the application; Figure 7B An execution diagram of image quality evaluation provided by the embodiment of the application. The embodiment of the application gives a preferred example of interaction between the server and the client based on application control on the basis of the above-mentioned embodiment. Specifically, the embodiment comprises the following steps:

[0133] Referring to Figure 7A-7B The method of the embodiment comprises but is not limited to the following steps:

[0134] S5001, when an image uploading trigger operation is detected, the client acquires an image to be uploaded.

[0135] S5002, the client uploads the image to the server. ​

[0136] S5003, the server receives the image uploaded by the client, and stores the image in a cloud storage component.

[0137] S5004, the server generates an image identifier corresponding to the image.

[0138] S5005, the server saves the URL of the image and the image identifier in a resource maintenance data table.

[0139] S5006, when detecting an image quality evaluation trigger operation, the client obtains the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image.

[0140] S5007, the client sends an image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image to the server.

[0141] S5008, the server receives the image quality evaluation request sent by the client.

[0142] S5009, the server finds the URL of the image to be evaluated from the resource maintenance data table according to the image identifier of the image to be evaluated, and downloads the image to be evaluated from the cloud storage component according to the URL of the image to be evaluated; and finds the URL of the reference image from the resource maintenance data table according to the image identifier of the reference image, and downloads the reference image from the cloud storage component according to the URL of the reference image.

[0143] S5010, the server evaluates the quality of the image to be evaluated relative to the reference image by calling an image quality evaluation tool, and obtains an image quality evaluation result.

[0144] S5011, the server sends the image quality evaluation result to the client.

[0145] S5012, the client receives the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server.

[0146] S5013, the client generates a result display page based on the image quality evaluation result, and displays the result display page.

[0147] The technical scheme provided by the embodiment can solve the problems of low accuracy and low evaluation efficiency caused by manual evaluation in the prior art by obtaining the image to be evaluated and the reference image by the server and evaluating the quality of the image to be evaluated, and can improve the accuracy of image quality evaluation.

[0148] Embodiment six

[0149] Figure 8 A first structural schematic diagram of an image quality evaluation device provided by an embodiment of the present application is shown inFigure 8 As shown, the apparatus 600 can include:

[0150] The request receiving module 610 is configured to receive an image quality evaluation request sent by a client, the image quality evaluation request containing an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image.

[0151] The image obtaining module 620 is configured to obtain the to-be-evaluated image according to the image identifier of the to-be-evaluated image, and obtain the reference image according to the image identifier corresponding to the reference image.

[0152] The image evaluation module 630 is configured to evaluate the quality of the to-be-evaluated image relative to the reference image by invoking an image quality evaluation tool, to obtain an image quality evaluation result.

[0153] The result sending module 640 is configured to send the image quality evaluation result to the client, so that the client generates and displays a result presentation page based on the image quality evaluation result.

[0154] Optionally, the image quality evaluation request contains a plurality of image identifiers corresponding to a plurality of to-be-evaluated images and an image identifier corresponding to a reference image.

[0155] Further, the image obtaining module 620 and the image evaluation module 630 can be specifically configured to: create N image quality evaluation tasks based on the image quality evaluation request; wherein N is the number of image identifiers corresponding to to-be-evaluated images contained in the image quality evaluation request, each of the image quality evaluation tasks contains an image identifier corresponding to a different to-be-evaluated image in the image quality evaluation request and an image identifier corresponding to the reference image; for each of the image quality evaluation tasks, obtain a current to-be-evaluated image according to an image identifier corresponding to the current to-be-evaluated image contained in the current image quality evaluation task, and obtain a current reference image according to an image identifier corresponding to the current reference image contained in the current image quality evaluation task, and evaluate the quality of the current to-be-evaluated image relative to the current reference image by invoking the image quality evaluation tool, to obtain an image quality evaluation result corresponding to the current image quality evaluation task.

[0156] Further, the image quality evaluation apparatus can further include a result saving module.

[0157] The result saving module is configured to save the image quality evaluation result in a task maintenance data table after obtaining the image quality evaluation result corresponding to the current image quality evaluation task; wherein the task maintenance data table further contains at least one of a task identifier, an image identifier of a to-be-evaluated image, an image identifier of a reference image, a task state, and a task description.

[0158] Further, the image quality evaluation device can further include a first image uploading module.

[0159] The first image uploading module is configured to receive the image uploaded by the client before receiving the image quality evaluation request, store the image in a cloud storage component, and save a uniform resource locator (URL) of the image and an image identifier in a resource maintenance data table.

[0160] Correspondingly, the image obtaining module 620 can be specifically configured to find the URL of the image to be evaluated from the resource maintenance data table according to the image identifier of the image to be evaluated, download the image to be evaluated from the cloud storage component according to the URL of the image to be evaluated, find the URL of the reference image from the resource maintenance data table according to the image identifier of the reference image, and download the reference image from the cloud storage component according to the URL of the reference image.

[0161] Further, the first image uploading module is specifically configured to receive the image uploaded by the client and image information of the image, store the image in a cloud storage component, and save a uniform resource locator (URL) of the image, an image identifier, and the image information in a resource maintenance data table.

[0162] Optionally, the image information includes at least one of image resolution information, image source APP information, image source APP version information, and image description information.

[0163] Optionally, the image to be evaluated is an image after the reference image is uploaded to the application software, and the reference image is an image after a product is photographed.

[0164] Optionally, the image to be evaluated is a picture, and the reference image is a picture, or the image to be evaluated is a video, and the reference image is a video.

[0165] The image quality evaluation device provided in this embodiment can be applied to the image quality evaluation method provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0166] Embodiment Seven

[0167] Figure 9 A second structural schematic diagram of an image quality evaluation device provided in this embodiment is shown in FIG. 7, which can include: Figure 9

[0168] An identifier obtaining module 710 is configured to obtain an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image when detecting an image quality evaluation trigger operation. ​

[0169] The request sending module 720 is configured to send, to a server, an image quality evaluation request containing image identifiers corresponding to the images to be evaluated and an image identifier corresponding to the reference image.

[0170] The result display module 730 is configured to receive image quality evaluation results of the images to be evaluated relative to the reference image returned by the server, generate a result display page based on the image quality evaluation results, and display the result display page.

[0171] Further, the identifier obtaining module 710 can be specifically configured to obtain image identifiers corresponding to a plurality of images to be evaluated respectively and an image identifier corresponding to a reference image.

[0172] Correspondingly, the request sending module 720 can be specifically configured to send, to a server, an image quality evaluation request containing image identifiers corresponding to the images to be evaluated respectively and an image identifier corresponding to the reference image.

[0173] Correspondingly, the result display module 730 can be specifically configured to receive image quality evaluation results corresponding to N image quality evaluation tasks respectively returned by the server; wherein N is the number of image identifiers corresponding to the images to be evaluated in the image quality evaluation request, and the image quality evaluation results corresponding to each image quality evaluation task are image quality evaluation results of different images to be evaluated relative to the reference image.

[0174] Further, the image quality evaluation device can further include a first record generation module.

[0175] The first record generation module is configured to generate a historical task record and display the historical task record; wherein record information of the historical task record includes at least one of a task identifier, a task creation time, image identifiers of a reference image and images to be evaluated corresponding to the task, source information of the reference image, source information of the images to be evaluated, an evaluation result of the images to be evaluated, a task creator, image description information, and a task publishing state.

[0176] Further, the image quality evaluation device can further include a second image uploading module.

[0177] The second image uploading module is configured to, before detecting an image quality evaluation triggering operation, detect an image uploading triggering operation, obtain an image to be uploaded, upload the image to a server, so that the server stores the image in a cloud storage component, and saves a URL and an image identifier of the image in a resource maintenance data table.

[0178] Furthermore, the aforementioned second image upload module can be specifically used to: upload the image and the image information of the image to the server, so that the server stores the image in the cloud storage component and saves the URL of the image, the image identifier and the image information in the resource maintenance data table.

[0179] Furthermore, the aforementioned image quality assessment device may also include: a second recording generation module;

[0180] The second record generation module is used to generate image history upload records and display the image history upload records; wherein, the record information of the image history upload records includes at least one of the following: image identifier of the uploaded image, URL of the uploaded image, upload time, uploader, and image information.

[0181] Furthermore, the aforementioned result display module 730 can be specifically used to generate a result display page containing a comparison chart of the evaluation results of the image to be evaluated, based on the current evaluation result of the image to be evaluated and the historical evaluation results of the image to be evaluated.

[0182] The image quality assessment device provided in this embodiment can be applied to the image quality assessment method provided in any of the above embodiments, and has the corresponding functions and beneficial effects.

[0183] Example 8

[0184] This application provides an image quality assessment system, which includes a server and a client. The image quality assessment system can be used to execute the image quality assessment method provided in any of the above embodiments of this application.

[0185] Example 9

[0186] Figure 10 This is a block diagram of an electronic device used to implement an image quality assessment method according to an embodiment of this application. Figure 10 A block diagram is shown that is suitable for implementing embodiments of the present application. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of use of the embodiments described in this application. Typical examples of such electronic devices include smartphones, tablets, laptops, in-vehicle terminals, and wearable devices.

[0187] like Figure 10 As shown, the electronic device 1000 is presented in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: one or more processors or processing units 1016, a memory 1028, and a bus 1018 connecting different system components (including the memory 1028 and the processing unit 1016).

[0188] Bus 1018 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures. By way of example, these architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0189] Electronic device 1000 typically includes a variety of computer system readable media. Such media can be any available media that is located either internally or externally to electronic device 1000, including both volatile and nonvolatile media, removable and non-removable media.

[0190] Memory 1028 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1030 and / or cache memory 1032. Electronic device 1000 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 1034 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 10 not shown, is typically provided as residual storage across electronic device 1000, and can be used for storing data that is both received as well as data that is generated by the processor 1010. Although Figure 10 not shown, is typically provided as residual storage across electronic device 1000, and can be used for storing data that is both received as well as data that is generated by the processor 1010. Although

[0191] Program / utility 1040 having a set (at least one) of program modules 1042 can be stored in memory 1028 by way of example, such program modules 1042 include an operating system, one or more application programs, other program modules, and program data, each of or some combination of which can include an implementation of a network environment. Program modules 1042 generally carry out the functions and / or methodologies described in embodiments of the present application.

[0192] The electronic device 1000 can also communicate with one or more external devices 1014 such as a keyboard or pointing device, a display 1024, etc.; other devices Figure 10 associated with the electronic device 1000. Communication can occur via Input / Output (I / O) interface(s) 1022. Still yet, the electronic device 1000 can communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), and / or a public network such as the Internet, via the network adapter 1020. As depicted, the network adapter 1020 communicates with the other components of the electronic device 1000 via bus 1018. It should be appreciated that the network adapter 1020 and / or the bus 1018 can be implemented using one or more types of technology Figure 10 including, but not limited to, application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), and other hardware or software components.

[0193] The processing unit(s) 1016 can execute instructions stored in the memory 1028 to perform various functions, including the image quality assessment method provided by any of the embodiments of the present application.

[0194] Embodiment Ten

[0195] The embodiment ten of the present application further provides a computer readable storage medium, which has stored thereon a computer program (or computer executable instructions), and the program is executed by a processor to implement the image quality assessment method provided by any of the embodiments of the present application.

[0196] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0197] A computer readable signal medium can include a propagated data signal with computer executable code embodied therein. The computer readable signal medium can be any computer readable medium that is part of a computer system that is capable of storing, communicating, propagating or transporting computer executable code. Computer readable program instructions described herein can be downloaded to or from computer-usable media, such as computer storage media, to cause a computer to perform the functions described herein. Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction- set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.

[0198] The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). These computer program instructions can be downloaded to a computer or other programmable data processing apparatus by any type of computer readable media, including a computer readable storage media.

[0199] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operations to be performed on the computer or other programmable data processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable data processing apparatus implement the functions specified by the operations in the computer program instructions. The computer program instructions can be executed by a computer, a processor or a processor core to cause the computer, the processor or the processor core to perform operations described herein.

Claims

1. A method of image quality assessment, characterized in that, Applied to a server, the method comprises: receiving an image quality evaluation request sent by a client, the request containing image identifiers of images to be evaluated and an image identifier of a reference image; obtaining the images to be evaluated according to the image identifiers of the images to be evaluated, and obtaining the reference image according to the image identifier of the reference image; evaluating the quality of the images to be evaluated relative to the reference image by calling an image quality evaluation tool, to obtain an image quality evaluation result; sending the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result; wherein the image quality evaluation request contains image identifiers of multiple images to be evaluated and an image identifier of a reference image; the multiple images to be evaluated are images obtained after the reference image is uploaded to multiple application software respectively; the reference image is an image taken after a product is photographed; the method further comprises:

2. The image quality assessment method of claim 1, wherein, creating N image quality evaluation tasks based on the image quality evaluation request; wherein N is the number of image identifiers corresponding to the images to be evaluated in the image quality evaluation request, each image quality evaluation task contains image identifiers corresponding to different images to be evaluated in the image quality evaluation request and the image identifier of the reference image; for each image quality evaluation task, a current image to be evaluated is obtained according to the image identifier corresponding to the current image to be evaluated contained in the current image quality evaluation task, and a current reference image is obtained according to the image identifier corresponding to the current reference image contained in the current image quality evaluation task. the method further comprises:

3. The image quality assessment method of claim 2, wherein, evaluating the quality of the current image to be evaluated relative to the current reference image by calling the image quality evaluation tool, to obtain an image quality evaluation result corresponding to the current image quality evaluation task. after obtaining the image quality evaluation result corresponding to the current image quality evaluation task, the method further comprises:

4. The image quality assessment method of claim 1, wherein, saving the image quality evaluation result in a task maintenance data table; wherein the task maintenance data table further contains at least one of a task identifier, an image identifier of an image to be evaluated, an image identifier of a reference image, a task state, and a task description. before receiving the image quality evaluation request, the method further comprises: receiving an image uploaded by the client, storing the image in a cloud storage component, and saving a uniform resource locator (URL) of the image and an image identifier in a resource maintenance data table; the method further comprises: According to the image identifier of the image to be evaluated, the URL of the image to be evaluated is found in the resource maintenance data table, and the image to be evaluated is downloaded from the cloud storage component according to the URL of the image to be evaluated; and according to the image identifier of the reference image, the URL of the reference image is found in the resource maintenance data table, and the reference image is downloaded from the cloud storage component according to the URL of the reference image.

5. The image quality assessment method of claim 4, wherein, The receiving the image uploaded by the client, storing the image in the cloud storage component, and saving the uniform resource locator URL and the image identifier of the image in the resource maintenance data table, comprises: Receiving the image uploaded by the client and the image information of the image, storing the image in the cloud storage component, and saving the uniform resource locator URL, image identifier and image information of the image in the resource maintenance data table.

6. The image quality assessment method of claim 5, wherein, The image information includes at least one of image resolution information, image source application software APP information, image source APP version information and image description information.

7. The image quality assessment method according to any of claims 1-6, characterized by, The image to be evaluated is a picture, and the reference image is a picture; or The image to be evaluated is a video, and the reference image is a video.

8. An image quality assessment method, characterized by, Applied to a client, the method comprises: Upon detecting an image quality evaluation trigger operation, obtaining an image identifier corresponding to an image to be evaluated and an image identifier corresponding to a reference image; Sending an image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image to a server; Receiving the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server, generating a result display page based on the image quality evaluation result, and displaying the result display page; Wherein, the obtaining of the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image comprises: obtaining a plurality of image identifiers corresponding to a plurality of images to be evaluated respectively and an image identifier corresponding to a reference image; the plurality of images to be evaluated are respectively obtained after the reference image is uploaded to a plurality of application software; the reference image is an image taken after a product is photographed; The sending of the image quality evaluation request containing the image identifier corresponding to the image to be evaluated and the image identifier corresponding to the reference image to the server comprises: sending an image quality evaluation request containing the image identifier corresponding to each of the images to be evaluated and the image identifier corresponding to the reference image to the server; The receiving of the image quality evaluation result of the image to be evaluated relative to the reference image returned by the server comprises: receiving the image quality evaluation result corresponding to N image quality evaluation tasks returned by the server; wherein N is the number of image identifiers corresponding to images to be evaluated contained in the image quality evaluation request, and the image quality evaluation result corresponding to each image quality evaluation task is the image quality evaluation result of different images to be evaluated relative to the reference image.

9. The image quality assessment method of claim 8, wherein, The method further comprises: Generating a historical task record; Displaying the historical task record; The record information of the historical task record includes at least one of a task identifier, a task creation time, image identifiers of a reference image corresponding to the task and a to-be-evaluated image, source information of the reference image, source information of the to-be-evaluated image, an evaluation result of the to-be-evaluated image, a task creator, image description information, and a task publishing state.

10. The image quality assessment method of claim 8, wherein, Before detecting the image quality evaluation trigger operation, the method further includes: When the image uploading trigger operation is detected, the to-be-uploaded image is acquired; The image is uploaded to the server, so that the server stores the image in the cloud storage component and saves the URL and the image identifier of the image in the resource maintenance data table.

11. The image quality assessment method of claim 10, wherein, The image and the image information of the image are uploaded to the server, so that the server stores the image in the cloud storage component and saves the URL, the image identifier, and the image information of the image in the resource maintenance data table. The method further includes:

12. The image quality assessment method of claim 10, wherein, generating an image historical uploading record; displaying the image historical uploading record; The record information of the image historical uploading record includes at least one of an image identifier of an uploaded image, a URL of the uploaded image, an uploading time, an uploader, and image information. The result display page generated based on the image quality evaluation result includes:

13. The image quality assessment method of claim 8, wherein, based on the current evaluation result of the to-be-evaluated image and the historical evaluation result of the to-be-evaluated image, a result display page containing an evaluation result comparison chart of the to-be-evaluated image is generated. Integrated in the server, used to implement the image quality evaluation method of claim 1, the device includes:

14. An image quality assessment apparatus characterized by comprising: The request receiving module is configured to receive an image quality evaluation request sent by the client and containing an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image. The image acquisition module is configured to acquire the to-be-evaluated image according to the image identifier of the to-be-evaluated image, and acquire the reference image according to the image identifier corresponding to the reference image. The image evaluation module is configured to evaluate the quality of the to-be-evaluated image relative to the reference image by calling an image quality evaluation tool to obtain an image quality evaluation result. The result sending module is configured to send the image quality evaluation result to the client, so that the client generates and displays a result display page based on the image quality evaluation result. Integrated in the client, used to implement the image quality evaluation method of claim 8, the device includes:

15. An image quality assessment apparatus characterized by comprising: The identifier acquisition module is configured to acquire an image identifier corresponding to a to-be-evaluated image and an image identifier corresponding to a reference image when an image quality evaluation trigger operation is detected. The request sending module is configured to send an image quality evaluation request containing the image identifier corresponding to the to-be-evaluated image and the image identifier corresponding to the reference image to the server. ​ A result display module is configured to receive the image quality evaluation result of the to-be-evaluated image relative to the reference image returned by the server, generate a result display page based on the image quality evaluation result, and display the result display page.

16. An image quality assessment system, characterized by, The image quality evaluation method comprises the following steps: The server is configured to implement the image quality evaluation method of claim 1, and the client is configured to implement the image quality evaluation method of claim 8.

17. An electronic device, comprising: The electronic device comprises: one or more processors; a storage device configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the image quality evaluation method of any one of claims 1 to 7, or the one or more processors implement the image quality evaluation method of any one of claims 8 to 13.

18. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the image quality evaluation method of any one of claims 1 to 7, or the computer program, when executed by a processor, implements the image quality evaluation method of any one of claims 8 to 13.

Images