Image quality assessment method, device, equipment and computer storage medium

Abstract

The present application provides an image quality assessment method, device, equipment and computer storage medium. The image quality assessment method includes: determining an image to be processed and a reference image set; determining quality comparison assessment information corresponding to each reference image in the reference image set; wherein one quality comparison assessment information is used to characterize the quality comparison assessment information of the corresponding reference image and the image to be processed; based on each determined quality comparison assessment information, determining the quality assessment value of the image to be processed. In the above manner, the image quality assessment method of the present application improves the accuracy of image quality assessment.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an image quality assessment method, device, equipment and computer storage medium. Background Art

[0002] Image processing technology is becoming more and more mature. Many image processing tasks such as classification and regression based on image processing hope to select high-quality images from a large amount of data for image processing. Due to different image processing tasks, the requirements for image quality are different. When using the multi-dimensional factors corresponding to different image processing tasks to comprehensively evaluate image quality, there are problems such as cumbersome image quality assessment and low accuracy. Summary of the invention

[0003] The present application provides an image quality assessment method, apparatus, device and computer storage medium.

[0004] The present application provides an image quality assessment method, the image quality assessment method comprising:

[0005] Determine the image to be processed and the reference image set;

[0006] Determine the quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of the quality comparison and evaluation information is used to represent the quality comparison and evaluation information of the corresponding reference image and the image to be processed;

[0007] Based on the determined pieces of quality comparison and evaluation information, a quality evaluation value of the image to be processed is determined.

[0008] In order to solve the above problems, the present application provides an image quality assessment device, which includes:

[0009] A first determining unit, used to determine an image to be processed and a reference image set;

[0010] A second determination unit is used to determine the quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of the quality comparison and evaluation information is used to represent the quality comparison and evaluation information of the corresponding reference image and the image to be processed;

[0011] The third determining unit determines the quality evaluation value of the image to be processed based on the determined quality comparison evaluation information.

[0012] To solve the above problem, the present application further provides a terminal device, the terminal device comprising a memory and a processor, wherein the memory is coupled to the processor;

[0013] The memory is used to store program data, and the processor is used to execute the program data to implement the above-mentioned image quality assessment method.

[0014] The present application also provides a computer storage medium, which is used to store program data. When the program data is executed by a processor, it is used to implement the above-mentioned image quality assessment method.

[0015] The image quality assessment device of the present application determines the image to be processed and the reference image set; determines the quality comparison assessment information corresponding to each reference image in the reference image set; wherein one piece of quality comparison assessment information is used to characterize the quality comparison assessment information of the corresponding reference image and the image to be processed; and determines the quality assessment value of the image to be processed based on each piece of quality comparison assessment information determined. In the above manner, the image quality assessment method of the present application determines the quality assessment value of the image to be processed by using the quality comparison assessment information between the image to be processed and each reference image in the reference image set, thereby improving the quality assessment accuracy of the image to be processed. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0017] Figure 1 It is a flowchart of an embodiment of an image quality assessment method provided by the present application;

[0018] Figure 2 yes Figure 1 The flowchart of S101 in the embodiment of the image quality assessment method shown;

[0019] Figure 3 yes Figure 2 A flow chart of an embodiment between S11 and S12 in the image quality assessment method shown;

[0020] Figure 4 yes Figure 1 A flow chart of an embodiment of S103 in the image quality assessment method shown;

[0021] Figure 5 yes Figure 4 A flow chart of an embodiment of S33 in the image quality assessment method shown;

[0022] Figure 6 yes Figure 1 A flow chart of an embodiment of S102 in the image quality assessment method shown;

[0023] Figure 7 is a structural schematic diagram of an embodiment of an image quality assessment device provided by the present application;

[0024] Figure 8 It is a structural diagram of an embodiment of a terminal device provided by the present application;

[0025] Fig. 9 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] This application proposes an image quality assessment method. For details, please refer to Figure 1 , Figure 1 It is a flowchart of an embodiment of the image quality assessment method provided by the present application. The image quality assessment method in this embodiment can be applied to an image quality assessment device, and the image quality assessment device of the present application can be a server, a mobile device, or a system in which a server and a mobile device cooperate with each other. Accordingly, the various parts included in the mobile device, such as various units, sub-units, modules, and sub-modules, can all be set in the server, can all be set in the mobile device, or can be set in the server and the mobile device respectively.

[0028] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

[0029] Specifically, the image quality assessment method of this embodiment includes the following steps:

[0030] S101: Determine an image to be processed and a reference image set.

[0031] In the disclosed embodiment, considering that directly performing quality assessment on a single frame of image has problems such as difficulty in defining the quality assessment task, low quality assessment accuracy, and complicated process, etc., the image quality assessment device of the present embodiment determines the quality assessment value of the image to be processed by performing quality comparison assessment on two images. Specifically, the image quality assessment device determines the image to be processed and a reference image set. The reference image set includes multiple reference images.

[0032] S102: Determine quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of quality comparison and evaluation information is used to represent quality comparison and evaluation information of the corresponding reference image and the image to be processed.

[0033] In order to effectively solve the problem of difficult definition of quality assessment, the image quality assessment device of this embodiment takes into account both the human visual system and the image quality scoring task. Specifically, the image quality assessment device determines the quality comparison assessment information between each reference image in the reference image set and the image to be processed, and obtains multiple quality comparison assessment information between the image to be processed and each reference image.

[0034] The quality comparison evaluation information between the image to be processed and each reference image is the image quality evaluation criteria of the image to be processed and the corresponding reference image, which is annotated by the annotator according to the annotation document description.

[0035] S103: Determine a quality evaluation value of the image to be processed based on the determined quality comparison evaluation information.

[0036] The image quality assessment device determines the quality assessment value of the image to be processed according to the quality comparison assessment information between the image to be processed and each reference image. It should be noted that the quality assessment value of the image to be processed may be a quality score obtained by performing a quality score assessment process on the image to be processed and each reference image. It may also be a quality grade obtained by performing a quality grade assessment process on the image to be processed and each reference image. This embodiment does not limit the quality assessment value of the image to be processed.

[0037] In the above scheme, the image quality assessment device determines the image to be processed and the reference image set; determines the quality comparison assessment information corresponding to each reference image in the reference image set; wherein one quality comparison assessment information is used to characterize the quality comparison assessment information of the corresponding reference image and the image to be processed; and determines the quality assessment value of the image to be processed based on each determined quality comparison assessment information. In the above manner, the image quality assessment method of the present application determines the quality assessment value of the image to be processed by using the quality comparison assessment information between the image to be processed and each reference image in the reference image set, thereby improving the quality assessment accuracy of the image to be processed.

[0038] Furthermore, in order to improve the accuracy of quality assessment of the image to be processed, it is possible to avoid the large differences between the determined image to be processed and each reference image in the reference image set, which makes it impossible to accurately assess the quality of the image to be processed. The image quality assessment device of this embodiment can select the image to be processed and each reference image from different frame images of the same target. For details, please refer to Figure 2 , Figure 2 yes Figure 1 The flowchart of S101 in the embodiment of the image quality assessment method shown in FIG. 1 includes the following steps:

[0039] S11: Acquire a target image sequence, where the target image sequence includes at least two frames of target images containing the same target.

[0040] The image quality assessment device obtains a target image sequence. On the one hand, the camera captures the image sequence and sends the image sequence to the image quality assessment device connected thereto. On the other hand, the image quality assessment device may also be a device with a capture and processing function and directly obtain the image sequence. When a camera is used to obtain an image sequence or an image quality assessment device is used to obtain an image sequence, the camera or the image quality assessment device may be used to capture a video stream and extract a sequence of images in the video stream to obtain an image sequence.

[0041] Furthermore, considering that there may be multiple targets in an image sequence, if the image sequence including at least one target is directly processed, there may be mutual interference between the targets, resulting in inaccurate image quality assessment. To avoid the above problems. The image quality assessment device of this embodiment performs image quality assessment processing on a single target image sequence. Specifically, the image quality assessment device identifies images in the image sequence and obtains a target image sequence. Among them, the target image sequence includes at least two frames of target images containing the same target.

[0042] S12: Select a frame of target image from the target image sequence as an image to be processed.

[0043] The image quality assessment device selects a frame of target image in the target image sequence as the image to be processed, which is denoted as

[0044] S13: Selecting part or all of the target images except one frame of the target image in the target image sequence as reference images in the reference image set.

[0045] The image quality assessment device selects target images other than one target image in the target image sequence as reference images, thereby forming a reference image set. Specifically, the image quality assessment device may select part or all of the target images as reference images to form a reference image set. The reference image is denoted as

[0046] Furthermore, considering that there may be a situation where the target image sequence is stationary for a long time, if the image to be processed and the reference image are determined in the target image corresponding to the situation where the target is stationary for a long time, the quality assessment accuracy of the image to be processed will be low and the amount of calculation will be increased. To avoid the above problems, the image quality assessment device removes redundant target images in the target image sequence. For details, please refer to Figure 3 , Figure 3 yes Figure 2 The flowchart of an embodiment of the image quality assessment method between S11 and S12 is shown. Specifically, the following steps are also included between S11 and S12:

[0047] S14: Calculate the feature similarity between adjacent frame target images in the target image sequence.

[0048] The image quality assessment device calculates the feature similarity between adjacent frame target images in the target image sequence.

[0049] S15: Determine whether the feature similarity is greater than or equal to a preset similarity threshold.

[0050] The image quality processing device determines whether the feature similarity between adjacent frame target images in the target image sequence is greater than or equal to a preset similarity threshold, and if so, executes S16. If not, it determines that there is no redundant target image between adjacent frame target images, and then retains the adjacent frame target images.

[0051] S16: Deleting a frame of target images from adjacent frames of target images according to a preset rule.

[0052] When the image quality assessment device determines that the feature similarity between adjacent frame target images in the target image sequence is greater than or equal to a preset similarity threshold, it retains one frame of the adjacent frame target images according to a preset rule. The preset rule may be to delete the previous image in the adjacent frame target images and retain the next image in the adjacent frame target images, so as to use the next image and the next adjacent target image to perform feature similarity calculation again until the redundant images in the target image sequence are removed. In addition, the image quality assessment device may also delete the next target image in the adjacent frame target images and retain the previous target image in the adjacent frame target images.

[0053] In the above scheme, the image quality assessment device uses the similarity between adjacent frame target images in the target image sequence to remove redundant images in the target image sequence, thereby avoiding using redundant target images as images to be processed or reference images, which may cause inaccurate quality assessment of the images to be processed.

[0054] In a specific embodiment, the quality comparison evaluation information between the image to be processed and the reference image can be a quality comparison result between the image to be processed and the reference image. Therefore, the image quality evaluation device can use the quality comparison result between the image to be processed and the reference image to determine the quality evaluation value of the image to be processed. For details, please refer to Figure 4 , Figure 4 yes Figure 1 The flowchart of S103 in the image quality assessment device is shown in FIG. 1 . Specifically, S103 includes the following steps:

[0055] S31: Based on the determined quality comparison and evaluation information, determine a first number of reference images in a reference image set whose quality is higher than or equal to that of the image to be processed.

[0056] The image quality assessment device determines, based on the quality comparison result between the image to be processed and each reference image, reference images in the reference image set whose quality is higher than or equal to that of the image to be processed, and obtains a first number of reference images.

[0057] S32: Determine a second number of reference images in the reference image set whose quality is lower than that of the image to be processed.

[0058] The image quality assessment device determines, based on the quality comparison result between the image to be processed and each reference image, reference images in the reference image set whose quality is lower than that of the image to be processed, and obtains a second number of reference images.

[0059] S33: Determine a quality evaluation value of the image to be processed according to the first quantity and the second quantity.

[0060] The detailed scheme of the image quality assessment device using the first quantity and the second quantity to determine the quality assessment value of the image to be processed can be found in Figure 5 The detailed description of S331 to S332 in the embodiment includes:

[0061] S331: Calculate the quantity difference and quantity sum between the first quantity and the second quantity respectively.

[0062] The image quality evaluation device calculates a sum of the first quantity and the second quantity, and a difference between the first quantity and the second quantity.

[0063] S332: Determine a quality evaluation value of the image to be processed using a ratio between the quantity difference and the quantity sum.

[0064] The image evaluation device determines the quality evaluation value of the image to be processed by using the ratio between the quantity difference and the quantity sum.

[0065] It should be noted that, in other embodiments, the image quality assessment device may also determine the number of reference images in the reference image set whose quality is equal to that of the image to be processed as the fifth number, recorded as y, based on the quality comparison result between the image to be processed and each reference image; determine the number of reference images in the reference image set whose quality is higher than that of the image to be processed as the sixth number, recorded as x; and determine the number of reference images in the reference image set whose quality is lower than that of the image to be processed as the second number, recorded as z, based on the quality comparison result between the image to be processed and each reference image. Then, the sum of the second number, the fifth number, and the sixth number is calculated, recorded as C=x+y+z, and the quantity difference xz between the second number and the sixth number is calculated. Thus, the quality assessment value of the image to be processed is determined by the ratio between the quantity difference and the quantity sum.

[0066] Specifically, the quality evaluation value of the image to be processed satisfies the following formula:

[0067]

[0068] Wherein, C is the sum of the second number, the fifth number and the second number, xz is the difference between the first number and the sixth number, and score is the quality evaluation value of the image to be processed.

[0069] In the above scheme, the image quality assessment device uses various quality comparison assessment information to determine the first number of reference images in the reference image set whose quality is higher than or equal to the image to be processed; and determines the second number of reference images in the reference image set whose quality is lower than the image to be processed; based on the first number and the second number, the quality assessment value of the image to be processed is determined, avoiding the problems of directly performing quality assessment on a single frame image, which makes it difficult to define the quality assessment task, and has low quality assessment accuracy, and statistically quantifies the quality assessment, thereby improving the accuracy of image quality assessment.

[0070] In a specific embodiment, for determining the quality comparison evaluation information between the image to be processed and the reference image, in order to avoid omission of the quality comparison evaluation between the image to be processed and the reference image, the image quality evaluation device of this embodiment can use the image to be processed and each reference image in the reference image set to form an image pair, and then determine the quality evaluation value of the image to be processed based on the quality comparison evaluation information of the image pair. For details, please refer to Figure 6 , Figure 6 yes Figure 1 The flowchart of S102 in the image quality assessment method is shown in FIG. 1 . Specifically, S102 also includes the following steps:

[0071] S21: Generate image pairs using the image to be processed and each reference image in the reference image set, where the number of image pairs is equal to the number of reference images.

[0072] The image quality assessment device generates an image pair using the image to be processed and each reference image in the reference image set, which is denoted as The image pair includes the image to be processed and the reference image. The image to be processed is denoted as The reference image is denoted as The number of image pairs is equal to the number of reference images.

[0073] S22: Based on the quality comparison and evaluation information corresponding to the reference image, obtain the quality comparison and evaluation information of the image pair where the reference image is located.

[0074] The quality comparison and evaluation information is used to characterize the quality level between the image to be processed and the reference image. In addition, the quality comparison and evaluation information can also be used to characterize the quality score between the image to be processed and the reference image. The image quality evaluation device determines the quality comparison and evaluation information of the image pair by acquiring the quality comparison and evaluation information between the image to be processed and the reference image.

[0075] S23: Based on the determined quality comparison evaluation information of each image pair, determine a third number of image pairs whose reference image quality is higher than or equal to that of the image to be processed.

[0076] The image quality assessment device records the number of image pairs in which the quality of the reference image is higher than or equal to that of the image to be processed as the third number.

[0077] S24: Determine a fourth number of image pairs whose reference image quality is lower than that of the image to be processed.

[0078] The image quality assessment device records the number of image pairs in which the quality of the reference image is lower than that of the image to be processed as the third number.

[0079] S25: Determine a quality evaluation value of the image to be processed according to the third quantity and the fourth quantity.

[0080] The image quality assessment device calculates the quantity difference and quantity sum between the third quantity and the fourth quantity, and then determines the quality assessment value of the image to be processed based on the ratio between the quantity difference and the quantity sum.

[0081] It should be noted that the image quality assessment device can also count the number of image pairs whose reference image quality is higher than the quality of the image to be processed, the number of image pairs whose reference image quality is equal to the quality of the image to be processed, and the number of image pairs whose reference image quality is lower than the quality of the image to be processed based on the quality comparison assessment information of each image pair. Then, the quality assessment value of the image to be processed is quantified based on the number of image pairs whose reference image quality is higher than the quality of the image to be processed, the number of image pairs whose reference image quality is equal to the quality of the image to be processed, and the number of image pairs whose reference image quality is lower than the quality of the image to be processed.

[0082] In the above scheme, the image quality assessment device uses the image to be processed and each reference image in the reference image set to form an image pair, and then determines the quality assessment value of the image to be processed based on the quality comparison assessment information of the acquired image pair, thereby improving the accuracy of image quality assessment.

[0083] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0084] In order to implement the image quality assessment method of the above embodiment, this application proposes an image quality assessment device. Figure 7 , Figure 7 Schematic diagram of the structure of an embodiment of an image quality assessment device provided by the present application. Specifically, the image quality assessment device 700 includes a first determination unit 71 , a second determination unit 72 and a third determination unit 73 .

[0085] The first determining unit 71 is used to determine the image to be processed and the reference image set.

[0086] The second determining unit 72 is used to determine the quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of quality comparison and evaluation information is used to represent the quality comparison and evaluation information of the corresponding reference image and the image to be processed.

[0087] The third determining unit 73 determines a quality evaluation value of the image to be processed based on the determined quality comparison evaluation information.

[0088] In order to implement the image quality assessment method of the above embodiment, the present application also proposes a terminal device, for details, please refer to Figure 8 , Figure 8 It is a structural diagram of an embodiment of a terminal device provided in this application.

[0089] The terminal device 800 of the embodiment of the present application includes a memory 81 and a processor 82, wherein the memory 81 and the processor 82 are coupled.

[0090] The memory 81 is used to store program data, and the processor 82 is used to execute the program data to implement the image quality assessment method described in the above embodiment.

[0091] In this embodiment, the processor 82 may also be referred to as a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip having the ability to process signals. The processor 82 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 82 may also be any conventional processor, etc.

[0092] The present application also provides a computer storage medium, such as Fig. 9 As shown, the computer storage medium 900 is used to store program data 91. When the program data 91 is executed by the processor, it is used to implement the image quality assessment method described in the above embodiment.

[0093] The present application also provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to enable a computer to execute the image quality assessment method as described in the embodiment of the present application. The computer program product may be a software installation package.

[0094] The image quality assessment method described in the above embodiment of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0095] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for evaluating image quality, characterized in that: The image quality assessment method comprises: The step of determining the image to be processed and the reference image set includes: obtaining a target image sequence, wherein the target image sequence includes at least two frames of target images containing the same target, and the target image sequence is a single target image sequence; selecting a frame of target image from the target image sequence as the image to be processed; and selecting part or all of the target images from the target images other than the frame of target image in the target image sequence as reference images in the reference image set; Determine the quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of the quality comparison and evaluation information is used to represent the quality comparison result between the corresponding reference image and the image to be processed; The step of determining the quality evaluation value of the image to be processed based on each determined quality comparison evaluation information includes: According to the quality comparison result between the image to be processed and each reference image, the number of reference images in the reference image set whose quality is equal to that of the image to be processed is determined as the fifth number; the number of reference images in the reference image set whose quality is higher than that of the image to be processed is determined as the sixth number; the number of reference images in the reference image set whose quality is lower than that of the image to be processed is determined as the second number; the sum of the second number, the fifth number and the sixth number is calculated; the difference between the second number and the sixth number is calculated; and the ratio between the difference and the sum is determined as the quality evaluation value of the image to be processed.

2. The method according to claim 1, characterized in that: After the step of acquiring the target image sequence and before the step of selecting a frame of the target image from the target image sequence as the image to be processed, the process further includes: Calculating feature similarity between adjacent frame target images in the target image sequence; If the feature similarity is greater than or equal to a preset similarity threshold, one of the adjacent frames of target images is deleted according to a preset rule.

3. The method according to claim 1, characterized in that The step of determining the quality evaluation value of the image to be processed based on the determined quality comparison evaluation information includes: Determining, based on the determined quality comparison and evaluation information, a first number of reference images in the reference image set whose quality is higher than or equal to that of the image to be processed; and Determine a second number of reference images in the reference image set whose quality is lower than that of the image to be processed; A quality evaluation value of the image to be processed is determined according to the first number and the second number.

4. The image quality assessment method according to claim 1, characterized in that: The step of determining the quality comparison evaluation information corresponding to each reference image in the reference image set comprises: Generate image pairs corresponding to the image to be processed and each reference image in the reference image set, the number of the image pairs being equal to the number of the reference images; Based on the quality comparison and evaluation information corresponding to the reference image, obtaining quality comparison and evaluation information of the image pair to which the reference image belongs; Determining a third number of image pairs whose quality of the reference image is higher than or equal to that of the image to be processed based on the determined quality comparison evaluation information of each image pair; and determining a fourth number of image pairs whose quality of the reference image is lower than that of the image to be processed; A quality evaluation value of the image to be processed is determined according to the third number and the fourth number.

5. The image quality assessment method according to claim 3, characterized in that: The step of determining the quality evaluation value of the image to be processed according to the first quantity and the second quantity comprises: respectively calculating a quantity difference and a quantity sum between the first quantity and the second quantity; The quality evaluation value of the image to be processed is determined using the ratio between the quantity difference and the quantity sum.

6. An image quality assessment device, characterized in that: The device comprises: The first determination unit is used to determine the steps of the image to be processed and the reference image set, including: obtaining a target image sequence, wherein the target image sequence includes at least two frames of target images containing the same target, and the target image sequence is a single target image sequence; selecting a frame of target image from the target image sequence as the image to be processed; and selecting part or all of the target images from the target images other than the frame of target image in the target image sequence as reference images in the reference image set; A second determination unit is used to determine quality comparison and evaluation information corresponding to each reference image in the reference image set; wherein one piece of quality comparison and evaluation information is used to represent a quality comparison result between the corresponding reference image and the image to be processed; The third determination unit determines the quality evaluation value of the image to be processed based on the determined quality comparison and evaluation information, including: according to the quality comparison result between the image to be processed and each reference image, determining the number of reference images in the reference image set whose quality is equal to that of the image to be processed as the fifth number; determining the number of reference images in the reference image set whose quality is higher than that of the image to be processed as the sixth number; determining the number of reference images in the reference image set whose quality is lower than that of the image to be processed as the second number; calculating the sum of the second number, the fifth number and the sixth number; calculating the difference between the second number and the sixth number; and determining the ratio between the difference and the sum as the quality evaluation value of the image to be processed.

7. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory is coupled to the processor; The memory is used to store program data, and the processor is used to execute the program data to implement the image quality assessment method according to any one of claims 1 to 5.

8. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by the processor, it is used to implement the image quality assessment method according to any one of claims 1 to 5.

Images