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

Abstract

The disclosure provides an image quality evaluation method and device, computer equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: determining the quality difference degree between each first boundary image block in the region of interest of the image to be evaluated and the second boundary image block in the adjacent non-region of interest; determining the transition image block contained in each second boundary image block according to the quality difference degree; determining the weight value of each position pixel point in the region of interest, the non-region of interest and the transition image block based on a preset rule; and determining the quality of the image to be evaluated according to the weight value of each position pixel point, and the pixel value of each position pixel point in the image to be evaluated and the original image. Therefore, the quality of the image to be evaluated is determined based on the weight value of each position pixel point in the image to be evaluated, so that the objective evaluation result is consistent with the subjective feeling of the human eye, and the accuracy and reliability of the evaluation result are improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of image processing, and particularly relates to an image quality evaluation method and device, electronic equipment and storage medium. BACKGROUND

[0002] Image quality evaluation is a very meaningful research topic in the field of image processing. Image quality evaluation is divided into subjective image quality evaluation method and objective image quality evaluation method. Compared with the subjective image quality evaluation method, the objective image quality evaluation method is more accurate and more widely used. However, the objective image quality evaluation method cannot well keep consistent with the subjective feeling of people. Therefore, how to obtain an image quality evaluation index more consistent with the subjective feeling of people is a problem to be solved. SUMMARY

[0003] The present disclosure aims to at least solve one of the technical problems in the related art to some extent.

[0004] An image quality evaluation method is provided in the first aspect of the present disclosure, comprising:

[0005] determining a quality difference degree between each first boundary image block in a region of interest of a to-be-evaluated image and a second boundary image block in an adjacent non-region of interest;

[0006] determining a transition image block contained in each second boundary image block according to the quality difference degree corresponding to each second boundary image block;

[0007] determining a weight value of each position pixel point in the region of interest, the non-region of interest and the transition image block based on a preset rule;

[0008] determining the quality of the to-be-evaluated image according to the weight value of each position pixel point and the pixel value of each position pixel point in the to-be-evaluated image and an original image.

[0009] Optionally, the determining of the quality difference degree between each first boundary image block in the region of interest of the to-be-evaluated image and the second boundary image block in the adjacent non-region of interest comprises:

[0010] determining a first mean square error corresponding to any first boundary image block in the region of interest of the to-be-evaluated image and a second mean square error corresponding to an adjacent second boundary image block;

[0011] determining the quality difference degree between the any first boundary image block and the adjacent second boundary image block according to a ratio between the first mean square error and the second mean square error.

[0012] Optionally, the determining the quality difference degree between the any first boundary image block and the adjacent second boundary image block according to the first ratio between the first mean square error and the second mean square error comprises:

[0013] In a case that the first ratio between the first mean square error and the second mean square error is less than a first threshold value, determining the quality difference degree between the any first boundary image block and the adjacent second boundary image block as a first specified value.

[0014] Optionally, the determining the quality difference degree between the any first boundary image block and the adjacent second boundary image block according to the first ratio between the first mean square error and the second mean square error comprises:

[0015] In a case that the first ratio between the first mean square error and the second mean square error is greater than or equal to the first threshold value, determining a first variance of the any first boundary image block in the original image and a second variance of the second boundary image block in the original image;

[0016] determining the quality difference degree between the any first boundary image block and the adjacent second boundary image block according to a second ratio between the first variance and the second variance.

[0017] Optionally, the determining the weight value of each position pixel point in the region of interest, the non-region of interest and the transition image block respectively based on the preset rule comprises:

[0018] determining a semantic weight ratio between the region of interest and the non-region of interest in the to-be-evaluated image and the original image, wherein the semantic weight ratio is a number greater than 1;

[0019] determining a first weight value of each pixel point in the region of interest and a second weight value of each pixel point in the non-region of interest according to the semantic weight ratio;

[0020] determining a third weight value of each pixel point in the transition image block according to the first ratio, the second ratio, the first weight value and the second weight value.

[0021] Optionally, after the determining the first weight value of each pixel point in the region of interest and the second weight value of each pixel point in the non-region of interest, the method further comprises:

[0022] determining a mean square error corresponding to the region of interest and the non-region of interest in the to-be-evaluated image and the original image respectively;

[0023] The first weight and the second weight are updated according to mean square errors corresponding to the region of interest and the region of non-interest respectively, to determine updated first weight and second weight.

[0024] Optionally, the transition image block contained in each of the second boundary image blocks is determined according to the quality difference degree corresponding to each of the second boundary image blocks.

[0025] In a case where the quality difference degree corresponding to any of the second boundary image blocks is a first specified value, it is determined that no transition image block is contained in the any of the second boundary image blocks.

[0026] Alternatively,

[0027] In a case where the quality difference degree corresponding to any of the second boundary image blocks is a second specified value, it is determined that the part image block adjacent to the first boundary image block in the any of the second boundary image blocks is a transition image block.

[0028] The second aspect embodiment of the present disclosure provides an image quality evaluation device, which comprises:

[0029] The first determination module is configured to determine a quality difference degree between each first boundary image block in a region of interest of a to-be-evaluated image and a second boundary image block in an adjacent region of non-interest.

[0030] The second determination module is configured to determine a transition image block contained in each of the second boundary image blocks according to the quality difference degree corresponding to each of the second boundary image blocks.

[0031] The third determination module is configured to determine a weight value of each position pixel point in the region of interest, the region of non-interest and the transition image block respectively based on a preset rule.

[0032] The fourth determination module is configured to determine a quality of the to-be-evaluated image according to the weight value of each position pixel point and pixel values of each position pixel point in the to-be-evaluated image and an original image.

[0033] Optionally, the first determination module comprises:

[0034] The first determination unit is configured to determine a first mean square error corresponding to any first boundary image block in the region of interest of the to-be-evaluated image and a second mean square error corresponding to an adjacent second boundary image block.

[0035] The second determination unit is configured to determine a quality difference degree between the any first boundary image block and the adjacent second boundary image block according to a ratio between the first mean square error and the second mean square error.

[0036] Optionally, the second determining unit is specifically used for:

[0037] If the first ratio between the first mean square error and the second mean square error is less than a first threshold, the quality difference between any first boundary image block and the adjacent second boundary image block is determined to be a first specified value.

[0038] Optionally, the second determining unit is specifically used for:

[0039] If the first ratio between the first mean square error and the second mean square error is greater than or equal to a first threshold, the first variance of any first boundary image block in the original image and the second variance of the second boundary image block in the original image are determined.

[0040] The degree of quality difference between any first boundary image block and its adjacent second boundary image block is determined based on the second ratio between the first variance and the second variance.

[0041] Optionally, the third determining module is specifically used for:

[0042] Determine the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image, wherein the semantic weight ratio is a number greater than 1;

[0043] Based on the semantic weight ratio, determine the first weight value of each pixel in the region of interest and the second weight value of each pixel in the region of non-interest;

[0044] A third weight value is determined for each pixel in the transition image block based on the first ratio, the second ratio, the first weight value, and the second weight value.

[0045] Optionally, the third determining module is further specifically used for:

[0046] Determine the mean square error corresponding to the region of interest and the region of non-interest in the image to be evaluated and the original image, respectively;

[0047] The first weight and the second weight are updated based on the mean squared errors corresponding to the region of interest and the region of non-interest, respectively, to determine the updated first weight and the second weight.

[0048] Optionally, the second determining module is specifically used for:

[0049] If the quality difference level corresponding to any second boundary image block is a first specified value, it is determined that no transition image block is contained in any second boundary image block;

[0050] or,

[0051] If the quality difference level corresponding to any second boundary image block is a second specified value, the portion of the image block adjacent to the first boundary image block in any second boundary image block is determined to be a transition image block.

[0052] A third aspect of this disclosure provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements an image quality evaluation method as proposed in a first aspect of this disclosure.

[0053] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements an image quality evaluation method as proposed in a first aspect of this disclosure.

[0054] A fifth aspect of this disclosure provides a computer program product that, when executed by an instruction processor, performs an image quality evaluation method proposed in a first aspect of this disclosure.

[0055] The image quality evaluation method, apparatus, electronic device, and storage medium disclosed herein have the following beneficial effects:

[0056] In this embodiment, firstly, based on the quality difference between each first boundary image block and its adjacent second boundary image block, transition image blocks contained in each second boundary image block are determined. Then, based on preset rules, weight values ​​for each pixel in the region of interest, region of non-interest, and transition image blocks are determined. Finally, the quality of the image to be evaluated is determined based on the weight values ​​of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image. Therefore, by assigning different weight values ​​to each pixel in the region of interest, region of non-interest, and transition image blocks of the image to be evaluated, and determining the quality of the image to be evaluated based on the weight values ​​of each pixel, the determined objective evaluation result is consistent with human subjective perception, improving the accuracy and reliability of the evaluation result.

[0057] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0058] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0059] Figure 1 This is a schematic flowchart of an image quality evaluation method provided in an embodiment of the present disclosure;

[0060] Figure 1a This is a schematic diagram illustrating the determination of a first boundary image block and a second boundary image block according to an embodiment of this disclosure;

[0061] Figure 1b This is a schematic diagram of a transition image block provided in an embodiment of the present disclosure;

[0062] Figure 2 A schematic flowchart illustrating an image quality evaluation method provided in another embodiment of this disclosure;

[0063] Figure 3 This is a schematic diagram of the structure of an image quality evaluation device provided in an embodiment of the present disclosure;

[0064] Figure 4 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0065] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0066] The following description, with reference to the accompanying drawings, describes an image quality evaluation method, apparatus, electronic device, and storage medium according to embodiments of the present disclosure.

[0067] Figure 1 This is a schematic flowchart illustrating the image quality evaluation method provided in an embodiment of the present disclosure.

[0068] This disclosure illustrates by exemplifying that the image quality evaluation method is configured in an image quality evaluation device, which can be applied to any electronic device to enable the electronic device to perform image quality evaluation functions.

[0069] Among them, electronic devices can be personal computers (PCs), cloud devices, etc.

[0070] like Figure 1 As shown, the image quality evaluation method may include the following steps:

[0071] Step 101: Determine the degree of quality difference between each first boundary image block in the region of interest of the image to be evaluated and the second boundary image block in the adjacent non-interest region.

[0072] The image to be evaluated is obtained by encoding the corresponding original image, which may result in data loss.

[0073] The region of interest (ROI) is the area in the image to be evaluated that is of greater interest to the human eye. For example, for an image containing a face, the ROI could be the face region in the image to be evaluated, while the non-ROI could be other regions in the image to be evaluated.

[0074] Optionally, the region of interest can be a rectangular region containing the detection box corresponding to the target of interest to the user in the image, or it can be a non-rectangular region segmented according to the target edge. This disclosure does not limit it in this way.

[0075] It should be noted that since the region of interest in the image to be evaluated is actually the same as that in the corresponding original image, but the quality of the image to be evaluated is unpredictable and may be very blurry, the region of interest can be detected in the original image first, so that the determined region of interest is more accurate.

[0076] Optionally, the original image can be identified to determine the location information corresponding to the region of interest and the region of non-interest in the original image. Then, based on the location information corresponding to the region of interest and the region of non-interest in the original image, the region of interest and the region of non-interest in the image to be evaluated can be determined.

[0077] It should be noted that there may be one or more regions of interest in the original image and the image to be evaluated, and this disclosure does not limit this.

[0078] In addition, the sizes of the first boundary image block and the second boundary image block can be the same or different, and can be adjusted as needed. This disclosure does not limit this.

[0079] For example, such as Figure 1a As shown, the first boundary image block can be of size N*N. In this disclosure, an N*N first sliding window can be slid along the inside of the boundary of the region of interest with a step size of N to obtain a first boundary image block of size N*N in the region of interest. Similarly, the second boundary image block can also be obtained by sliding an N*N second sliding window along the outside of the boundary of the region of interest with a step size of N.

[0080] The value of N can be directly proportional to the area of ​​the region of interest; that is, the larger the area of ​​the region of interest, the larger the value of N.

[0081] Optionally, the first mean absolute error corresponding to the first boundary image block and the second mean absolute error corresponding to the adjacent second boundary image block can be determined first, and then the ratio of the first mean absolute error to the second mean absolute error can be used as the degree of quality difference between the first boundary image block and the adjacent second boundary image block.

[0082] Alternatively, the texture complexity corresponding to the first boundary image block and the texture complexity corresponding to the adjacent second boundary image block can be determined first, and then the ratio of the texture complexity corresponding to the first boundary image block to the texture complexity corresponding to the second boundary image block can be used as the degree of quality difference between the first boundary image block and the adjacent second boundary image block. This disclosure does not limit this.

[0083] Step 102: Determine the transition image blocks contained in each second boundary image block based on the degree of quality difference corresponding to each second boundary image block.

[0084] Optionally, a threshold range can be set. If the degree of quality difference is within the threshold range, the second boundary image block is considered not to contain a transition image block; if the degree of quality difference is not within the threshold range, the second boundary image block is considered to contain a transition image block.

[0085] like Figure 1b As shown, when the second boundary image block includes a transition image block, the position of the transition image block is adjacent to the corresponding first boundary image block, and the area of ​​the transition image block can be determined according to the magnitude of the quality difference. Alternatively, the area of ​​the transition image block can also be 1 / 2, 1 / 3, etc., of the area of ​​the second boundary image block, and this disclosure does not limit this.

[0086] Step 103: Based on preset rules, determine the weight value of each pixel in the region of interest, the region of non-interest, and the transition image block.

[0087] Optionally, the variances of the region of interest, the region of non-interest, and the transition image block can be obtained first. Then, the weight value of each pixel in the region of interest, the region of non-interest, and the transition image block can be determined based on the ratio of the variances of the region of interest, the region of non-interest, and the transition image block.

[0088] For example, if the variance ratios of the region of interest, the region of non-interest, and the transition image block are 1:0.5:0.7, then the weight of each pixel in the region of interest is 1, the weight of each pixel in the region of non-interest is 0.5, and the weight of each pixel in the transition image block is 0.7.

[0089] Optionally, the gradients corresponding to the region of interest, the region of non-interest, and the transition image block can be obtained separately first. Then, the weight value of each pixel in the region of interest, the region of non-interest, and the transition image block can be determined based on the ratio of the gradients corresponding to the region of interest, the region of non-interest, and the transition image block.

[0090] It is understandable that the variance or gradient corresponding to the region of interest (ROI), non-ROI, and transitional image patches can all reflect the texture complexity contained in the ROI, non-ROI, and transitional image patches. The more complex the texture, the greater the weight the corresponding region occupies.

[0091] Step 104: Determine the quality of the image to be evaluated based on the weight value of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image.

[0092] Optionally, the quality of the image to be evaluated can be determined based on the peak signal-to-noise ratio (PSNR) between the image to be evaluated and the original image. The PSNR objectively evaluates the quality of the image to be evaluated. A higher PSNR indicates better image quality, while a lower PSNR indicates worse image quality.

[0093] The specific steps for obtaining the PSNR between the image to be evaluated and the original image may include:

[0094] (1) Determine the weighted mean square error between the image to be detected and the original image based on the weight value of each pixel at each position and the pixel value of each pixel at each position in the image to be evaluated and the original image.

[0095] The formula for calculating the weighted mean square error is as follows:

[0096]

[0097] Where MSE1 is the weighted mean square error, H is the length of the image to be evaluated and the original image, and W is the width of the image to be evaluated and the original image. i,j X represents the weight value of the pixel in the i-th row and j-th column. i,j Y is the pixel value of the pixel in the i-th row and j-th column of the original image. i,j Let be the pixel value of the pixel in the i-th row and j-th column of the image to be evaluated.

[0098] (2) Normalize the weighted mean square error to obtain the normalized mean square error.

[0099] The formula for calculating the normalized mean square error (MSE) is as follows:

[0100]

[0101] Understandably, by normalizing the weighted mean square error, the expression for the mean square error can be transformed into a dimensionless expression, that is, the normalized mean square error is a scalar. Then, the peak signal-to-noise ratio can be determined based on the normalized mean square error, thereby improving the accuracy and reliability of the peak signal-to-noise ratio.

[0102] (3) Determine the peak signal-to-noise ratio between the image to be evaluated and the original image based on the normalized mean square error.

[0103]

[0104] Where PSNR is the peak signal-to-noise ratio, MSE is the normalized mean square error, and 2 bits -1 represents the maximum value of a color in the image to be evaluated. For example, if each sampling point in the image to be evaluated is represented by 8 bits, then bits = 8, 2 bits -1 equals 255.

[0105] Optionally, the quality of the image to be evaluated can be determined based on the structural similarity between the image to be evaluated and the original image. Structural similarity (SSIM) characterizes the degree of similarity between the original image and the image to be evaluated. A higher structural similarity indicates better quality; conversely, a lower structural similarity indicates worse quality.

[0106] The specific steps for determining the SSIM between the image to be evaluated and the original image may include:

[0107] (1) Determine the first structural similarity corresponding to the region of interest, the second structural similarity corresponding to the region of non-interest, and the third structural similarity corresponding to the transition image block.

[0108] Specifically, the first structural similarity characterizes the similarity between the regions of interest (ROIs) of the original image and the image to be evaluated. The second structural similarity characterizes the similarity between the regions of non-ROIs of the original image and the image to be evaluated. The third structural similarity characterizes the similarity between the transitional image patches of the original image and the image to be evaluated.

[0109] The formula for calculating the first structural similarity is as follows:

[0110]

[0111] Where SSIM1 is the first structural similarity, x1 is the region of interest in the original image, y1 is the region of interest in the image to be evaluated, and μ x1 μ is the average value of x1. y1 σ is the average value of y1. x1Let σ be the variance of x1. y1 Let σ be the variance of y1. x1y1 Let x1 and y1 be the covariances, and c1 and c2 be the reference coefficients.

[0112] The formula for calculating the second structural similarity is as follows:

[0113]

[0114] Where SSIM2 is the second structural similarity, x2 is the non-interest region in the original image, y2 is the non-interest region in the image to be evaluated, and μ x2 μ is the average value of x². y2 σ is the average value of y2. x2 Let σ be the variance of x². y2 Let σ be the variance of y². x2y2 Let x2 and y2 be the covariances.

[0115] The formula for calculating the third structural similarity is as follows:

[0116]

[0117] Where SSIM3 is the third structural similarity, x3 is the transitional image patch in the original image, y3 is the transitional image patch in the image to be evaluated, and μ x3 μ is the average value of x². y3 σ is the average value of y3. x3 Let σ be the variance of x³. y3 Let σ be the variance of y3. x3y3 Let x3 and y3 be the covariances.

[0118] (2) Determine the structural similarity between the image to be evaluated and the original image based on the weight value of each pixel, the first structural similarity, the second structural similarity, and the third structural similarity.

[0119] The formula for calculating structural similarity is as follows:

[0120]

[0121] Where SSIM stands for structural similarity, w1 is the weight value corresponding to the region of interest, w2 is the weight value corresponding to the region of non-interest, w3 is the weight value corresponding to the transition image patch, S1 is the area of ​​the region of interest, S2 is the area of ​​the region of non-interest, and S3 is the area of ​​the transition image patch.

[0122] In this embodiment of the disclosure, by combining the subjective perception of the human eye, the weight of each pixel is determined, and then based on the weight of different pixels, the peak signal-to-noise ratio and structural similarity between the image to be evaluated and the original image are determined to comprehensively evaluate the quality of the image to be evaluated. This not only makes the evaluation results more accurate and comprehensive, but also ensures that the evaluation results are consistent with the subjective perception of the human eye regarding the quality of the image to be evaluated.

[0123] In this embodiment, firstly, based on the quality difference between each first boundary image block and its adjacent second boundary image block, transition image blocks contained in each second boundary image block are determined. Then, based on preset rules, weight values ​​for each pixel in the region of interest, region of non-interest, and transition image blocks are determined. Finally, the quality of the image to be evaluated is determined based on the weight values ​​of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image. Therefore, by assigning different weight values ​​to each pixel in the region of interest, region of non-interest, and transition image blocks of the image to be evaluated, and determining the quality of the image to be evaluated based on the weight values ​​of each pixel, the determined objective evaluation result is consistent with human subjective perception, improving the accuracy and reliability of the evaluation result.

[0124] Figure 2 This is a schematic flowchart illustrating an image quality evaluation method provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, the image quality evaluation method may include the following steps:

[0125] Step 201: Determine the first mean square error corresponding to any first boundary image block in the region of interest of the image to be evaluated, and the second mean square error corresponding to the adjacent second boundary image block.

[0126] The calculation methods for the first mean square error and the second mean square error can be found in the detailed description of other embodiments of this disclosure, and will not be repeated here.

[0127] Step 202: Determine the degree of quality difference between any first boundary image block and its adjacent second boundary image block based on the ratio between the first mean square error and the second mean square error.

[0128] It should be noted that, since the quality of the first boundary image patch may be better than, or worse than, the quality of the adjacent second boundary image patch, in this embodiment of the disclosure, to facilitate characterizing the quality difference between the first and second boundary image patches based on a single parameter, the first ratio can be set to a value greater than 1. Therefore, the larger of the first mean square error and the second mean square error can be used as the divisor of the first ratio. For example, if the first mean square error is greater than the second mean square error, then the first ratio is the first mean square error divided by the second mean square error.

[0129] Optionally, if the first ratio between the first mean square error and the second mean square error is less than a first threshold, the degree of quality difference between any first boundary image block and the adjacent second boundary image block is determined as a first specified value.

[0130] In this disclosure, to conveniently represent the degree of quality difference between any first boundary image block and its adjacent second boundary image block, the degree of quality difference corresponding to a first ratio being less than a first threshold can be represented by the same value, namely, a first specified value. For example, the first specified value can be 0 or 1, etc., and this disclosure does not limit it in this way.

[0131] It is understandable that mean squared error can objectively reflect changes in image quality; however, objective quality changes are not equivalent to visual quality changes. The reasons why the first ratio between the first and second mean squared errors is greater than or equal to the first threshold may include: during the encoding process, distinguishing between regions of interest and non-regions of interest, leading to the first ratio being greater than or equal to the first threshold. Alternatively, it may be due to changes in the texture complexity of the original image itself, causing the first ratio to be greater than or equal to the first threshold.

[0132] The change in texture complexity, which causes the first ratio to be greater than or equal to the first threshold, will not cause obvious subjective abnormalities in the human eye. That is, although the objective quality has changed, the visual quality may not have changed abruptly, so this needs to be excluded.

[0133] Optionally, if the first ratio between the first mean square error and the second mean square error is greater than or equal to the first threshold, the first variance of any first boundary image block in the original image and the second variance of the second boundary image block in the original image are determined; then, based on the second ratio between the first variance and the second variance, the degree of quality difference between any first boundary image block and the adjacent second boundary image block is determined.

[0134] The second ratio can also be a value greater than 1.

[0135] Understandably, when the second ratio is greater than or equal to the second threshold, it indicates that the texture complexity of the first boundary image patch and the adjacent second boundary image patch in the original image has changed, but the visual quality of the image to be evaluated has not changed abruptly. Therefore, when the second ratio is greater than or equal to the second threshold, the degree of quality difference between the first boundary image patch and the adjacent second boundary image patch is determined as the first specified value.

[0136] If the second ratio is less than the second threshold, it indicates that the texture complexity of the first boundary image patch and the adjacent second boundary image patch in the original image does not change significantly, but the difference between the first mean square error and the second mean square error is large. In this case, the visual quality between the first boundary image patch and the second boundary image patch in the image to be evaluated undergoes a sudden change. Therefore, when the second ratio is less than the second threshold, the degree of quality difference between the first boundary image patch and the adjacent second boundary image patch is determined as the second specified value.

[0137] The second specified value can represent the degree of quality difference between the first boundary image block and the adjacent second boundary image block when the second ratio is less than the second threshold. The second specified value can also be 0 or 1, etc., and this disclosure does not limit it. It should be noted that the first specified value and the second specified value cannot be the same.

[0138] Step 203: Determine the transition image blocks contained in each second boundary image block based on the degree of quality difference corresponding to each second boundary image block.

[0139] Optionally, if the quality difference level corresponding to any second boundary image block is a first specified value, it is determined that no transition image block is contained in any second boundary image block.

[0140] Alternatively, if the quality difference level corresponding to any second boundary image block is a second specified value, the portion of the image block adjacent to the first boundary image block in any second boundary image block is determined as a transition image block.

[0141] The area of ​​the transition image block can be 1 / 2, 1 / 3, etc. of the area of ​​the second boundary image block, or the area of ​​the transition image block can be determined according to the second ratio. For example, the larger the second ratio, the larger the area of ​​the transition image block can be, etc. This disclosure does not limit this.

[0142] Step 204: Determine the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image, wherein the semantic weight ratio is a number greater than 1.

[0143] In this disclosure, semantic weight ratios are used to characterize the degree of influence of regions of interest (ROI) and non-ROI on image quality. It should be noted that ROIs have a higher semantic weight, thus allowing the quality of ROIs in the image to have a greater impact on the image quality evaluation index. This means that the final determined image quality can, to some extent, reflect the user's subjective perception.

[0144] Optionally, the semantic weight ratio between regions of interest and non-regions of interest can be determined based on the complexity between them in the image. For example, the first texture complexity of the original image and the second texture complexity of the region of interest in the original image can be determined first; then, the semantic weight ratio between the region of interest and non-regions of interest can be determined based on the first texture complexity and the second texture complexity.

[0145] Optionally, the target type of the original image can be determined first based on the content contained in the original image, and then the semantic weight ratio corresponding to the target type can be determined based on the preset mapping relationship between each type of image and the semantic weight ratio.

[0146] The target type may include images of people, landscapes, objects, etc., and this disclosure does not limit it.

[0147] In this disclosure, an image dataset containing various target types can be obtained first, and then the images in the image dataset can be classified and statistically analyzed to determine the semantic weight ratio of the region of interest to the region of non-interest in each target type of image, and establish a mapping relationship between each type of image and the semantic weight ratio.

[0148] Step 205: Determine the first weight value of each pixel in the region of interest and the second weight value of each pixel in the region of non-interest based on the semantic weight ratio;

[0149] Optionally, after determining the first weight value for each pixel in the region of interest and the second weight value for each pixel in the region of non-interest, the first weight value and the second weight value can be updated based on the mean square error corresponding to the region of interest and the region of non-interest. Specific steps may include:

[0150] (1) Determine the mean square error of the region of interest and the region of non-interest in the image to be evaluated and the original image, respectively.

[0151] (2) Update the first weight and the second weight according to the mean square error corresponding to the region of interest and the region of non-interest, so as to determine the updated first weight and the second weight.

[0152] Optionally, the mean square error weight ratio between the region of interest and the region of non-interest can be determined based on the mean square error corresponding to the region of interest and the region of non-interest, respectively. Then, the first weight and the second weight can be updated based on the mean square error weight ratio to obtain the updated first weight and the second weight.

[0153] The mean square error weight ratio can characterize the quality difference between the region of interest and the region of non-interest in an image. It can be the ratio of the mean square error of the region of interest to the mean square error of the region of non-interest in the image to be evaluated and the original image.

[0154] Optionally, the first weight of the region of interest can be multiplied by the mean squared error weight, and the second weight of the region of non-interest can be multiplied by the mean squared error weight to obtain the updated first and second weights. Alternatively, the first weight of the region of interest can be added to the mean squared error weight, and the second weight of the region of non-interest can be added to the mean squared error weight to obtain the updated first and second weights.

[0155] For example, if the semantic weight ratio between the region of interest and the region of non-interest is (m:n) and the mean squared error weight ratio is (a:b), then the semantic weight ratio and the mean squared error weight ratio are multiplied to obtain the updated first weight as am and the second weight as bn; or, the semantic weight of the region of interest is added to the mean squared error weight determined based on quality, and the semantic weight of the region of non-interest is added to the mean squared error weight determined based on quality, then the updated first weight is a+m and the second weight is b+n.

[0156] In this disclosure, the mean square error weight ratio is determined based on the quality difference between the region of interest and the region of non-interest. Then, the first weight and the second weight are updated based on the mean square error weight, so that the final determined weight can reflect both the objective quality of the image and the subjective visual perception of the image.

[0157] Step 206: Determine the third weight value of each pixel in the transition image block based on the first ratio, the second ratio, the first weight value, and the second weight value.

[0158] The formula for calculating the third weight value is as follows:

[0159]

[0160] Where w3 is the third weight value of each pixel in the transition image block, w1 is the first weight value corresponding to the region of interest, w2 is the second weight value corresponding to the region of non-interest, R1 is the first ratio, and R2 is the second ratio.

[0161] Step 207: Determine the quality of the image to be evaluated based on the weight value of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image.

[0162] The specific implementation of step 207 can be found in the detailed descriptions of other embodiments in this disclosure, and will not be repeated here.

[0163] In this embodiment, a first weight value for each pixel in the region of interest and a second weight value for each pixel in the region of non-interest are determined by the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image. Then, a third weight value for each pixel in the transition image block is determined based on the first weight value, the second weight value, the first ratio, and the second ratio. Finally, the quality of the image to be evaluated is determined based on the weight value of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image. Therefore, by assigning more accurate weights to the transition image block and determining the quality of the image to be evaluated based on the weight value of each pixel in the image to be evaluated, the determined objective evaluation result is not only consistent with human subjective perception, but the accuracy and reliability of the evaluation result are further improved.

[0164] To achieve the above embodiments, this disclosure also proposes an image quality evaluation device.

[0165] Figure 3 This is a schematic diagram of the structure of the image quality evaluation device provided in the embodiments of this disclosure.

[0166] like Figure 3 As shown, the image quality evaluation device 300 may include: a first determining module 310, a second determining module 320, a third determining module 330, and a fourth determining module 340.

[0167] The first determining module is used to determine the degree of quality difference between each first boundary image block in the region of interest of the image to be evaluated and the second boundary image block in the adjacent non-interest region.

[0168] The second determining module is used to determine the transition image block contained in each second boundary image block according to the degree of quality difference corresponding to each second boundary image block;

[0169] The third determining module is used to determine the weight value of each pixel in the region of interest, the region of non-interest, and the transition image block based on preset rules.

[0170] The fourth determining module is used to determine the quality of the image to be evaluated based on the weight value of each pixel at each location and the pixel value of each pixel at each location in the image to be evaluated and the original image.

[0171] In one possible implementation, the first determining module 310 includes:

[0172] The first determining unit is used to determine the first mean square error corresponding to any first boundary image block in the region of interest of the image to be evaluated, and the second mean square error corresponding to the adjacent second boundary image block.

[0173] The second determining unit is used to determine the degree of quality difference between any first boundary image block and the adjacent second boundary image block based on the ratio between the first mean square error and the second mean square error.

[0174] In one possible implementation, the second determining unit 320 is specifically used for:

[0175] If the first ratio between the first mean square error and the second mean square error is less than a first threshold, the quality difference between any first boundary image block and its adjacent second boundary image block is determined as a first specified value.

[0176] In one possible implementation, the second determining unit 320 is specifically used for:

[0177] If the first ratio between the first mean square error and the second mean square error is greater than or equal to the first threshold, determine the first variance of any first boundary image block in the original image and the second variance of the second boundary image block in the original image.

[0178] The degree of quality difference between any first boundary image block and its adjacent second boundary image block is determined based on the second ratio between the first variance and the second variance.

[0179] In one possible implementation, the third determining module 330 is specifically used for:

[0180] Determine the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image, where the semantic weight ratio is a number greater than 1;

[0181] Based on the semantic weight ratio, determine the first weight value of each pixel in the region of interest and the second weight value of each pixel in the region of non-interest;

[0182] The third weight value of each pixel in the transition image block is determined based on the first ratio, the second ratio, the first weight value, and the second weight value.

[0183] In one possible implementation, the third determining module 330 is further specifically used for:

[0184] Determine the mean squared errors corresponding to the regions of interest and non-interest regions in the image to be evaluated and the original image, respectively;

[0185] The first and second weights are updated based on the mean squared errors corresponding to the regions of interest and non-interest, respectively, to determine the updated first and second weights.

[0186] In one possible implementation, the second determining module 320 is specifically used for:

[0187] If the quality difference level corresponding to any second boundary image block is a first specified value, it is determined that no transition image block is contained in any second boundary image block;

[0188] or,

[0189] When the quality difference level corresponding to any second boundary image block is a second specified value, the portion of the image block adjacent to the first boundary image block in any second boundary image block is determined as a transition image block.

[0190] The functions and specific implementation principles of the modules described in this embodiment can be found in the above method embodiments, and will not be repeated here.

[0191] The image quality evaluation apparatus of this disclosure first determines the transition image blocks contained in each second boundary image block based on the degree of quality difference between each first boundary image block and its adjacent second boundary image block. Then, based on preset rules, it determines the weight value of each pixel in the region of interest, the region of non-interest, and the transition image blocks. Finally, it determines the quality of the image to be evaluated based on the weight value of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image. Therefore, by assigning different weight values ​​to each pixel in the region of interest, the region of non-interest, and the transition image blocks of the image to be evaluated, and determining the quality of the image to be evaluated based on the weight value of each pixel, the determined objective evaluation result is consistent with the subjective perception of the human eye, thus improving the accuracy and reliability of the evaluation result.

[0192] To implement the above embodiments, this disclosure also proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the image quality evaluation method proposed in the foregoing embodiments of this disclosure.

[0193] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program, which, when executed by a processor, implements the image quality evaluation method proposed in the foregoing embodiments of this disclosure.

[0194] To implement the above embodiments, this disclosure also proposes a computer program product that, when executed by an instruction processor, performs an image quality evaluation method as proposed in the foregoing embodiments of this disclosure.

[0195] Figure 4 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Figure 4 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0196] like Figure 4 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0197] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0198] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0199] Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0200] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0201] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with computer device 12, and / or with any device that enables computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0202] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the foregoing embodiments.

[0203] The technical solution disclosed herein first determines the transition image blocks contained in each second boundary image block based on the quality difference between each first boundary image block and its adjacent second boundary image block. Then, based on preset rules, it determines the weight values ​​of each pixel in the region of interest, the region of non-interest, and the transition image blocks. Finally, it determines the quality of the image to be evaluated based on the weight values ​​of each pixel and the pixel values ​​of each pixel in the image to be evaluated and the original image. Therefore, by assigning different weight values ​​to each pixel in the region of interest, the region of non-interest, and the transition image blocks of the image to be evaluated, and determining the quality of the image to be evaluated based on the weight values ​​of each pixel, the determined objective evaluation result is consistent with human subjective perception, thus improving the accuracy and reliability of the evaluation result.

[0204] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0205] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0206] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0207] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0208] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0209] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0210] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0211] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for evaluating image quality, characterized in that, include: Determine the degree of quality difference between each first boundary image patch in the region of interest of the image to be evaluated and the second boundary image patch in the adjacent region of non-interest. The first mean square error corresponding to any first boundary image block in the region of interest of the image to be evaluated, and the second mean square error corresponding to the adjacent second boundary image block are determined, and the ratio between the first mean square error and the second mean square error is the first ratio. Determine the first variance of any first boundary image block in the original image, and the second variance of the second boundary image block in the original image, wherein the ratio between the first variance and the second variance is the second ratio. Based on the degree of quality difference corresponding to each second boundary image block, determine the transition image block contained in each second boundary image block; Determine the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image, wherein the semantic weight ratio is a number greater than 1; Based on the semantic weight ratio, determine the first weight value of each pixel in the region of interest and the second weight value of each pixel in the region of non-interest; Based on the first ratio, the second ratio, the first weight value, and the second weight value, a third weight value is determined for each pixel in the transition image block; The quality of the image to be evaluated is determined based on the weight value of each pixel at each location and the pixel value of each pixel at each location in the image to be evaluated and the original image.

2. The method as described in claim 1, characterized in that, The determination of the quality difference between each first boundary image patch in the region of interest of the image to be evaluated and the second boundary image patch in the adjacent non-interest region includes: Based on the first ratio, the degree of quality difference between any first boundary image block and its adjacent second boundary image block is determined.

3. The method as described in claim 2, characterized in that, The step of determining the degree of quality difference between any first boundary image patch and its adjacent second boundary image patch based on the first ratio includes: If the first ratio is less than the first threshold, the quality difference between any first boundary image block and the adjacent second boundary image block is determined to be a first specified value.

4. The method as described in claim 2, characterized in that, The step of determining the degree of quality difference between any first boundary image patch and its adjacent second boundary image patch based on the first ratio includes: If the first ratio is greater than or equal to the first threshold, the quality difference between any first boundary image block and the adjacent second boundary image block is determined according to the second ratio.

5. The method as described in claim 1, characterized in that, After determining the first weight value of each pixel in the region of interest and the second weight value of each pixel in the non-region of interest, the method further includes: Determine the mean square error corresponding to the region of interest and the region of non-interest in the image to be evaluated and the original image, respectively; The first weight value and the second weight value are updated based on the mean square error corresponding to the region of interest and the region of non-interest, respectively, to determine the updated first weight value and the second weight value.

6. The method according to any one of claims 1-5, characterized in that, The step of determining the transition image blocks contained in each second boundary image block based on the quality difference degree corresponding to each second boundary image block includes: If the quality difference level corresponding to any second boundary image block is a first specified value, it is determined that no transition image block is contained in any second boundary image block; or, When the second ratio is less than the second threshold, the quality difference between the first boundary image block and the adjacent second boundary image block is determined to be a second specified value. When the quality difference corresponding to any second boundary image block is the second specified value, the portion of the image block adjacent to the first boundary image block in any second boundary image block is determined to be a transition image block.

7. An image quality evaluation device, characterized in that, include: The first determining module is used to determine the degree of quality difference between each first boundary image block in the region of interest of the image to be evaluated and the second boundary image block in the adjacent non-interest region; The first determining module includes: The first determining unit is used to determine the first mean square error corresponding to any first boundary image block in the region of interest of the image to be evaluated, and the second mean square error corresponding to the adjacent second boundary image block, wherein the ratio between the first mean square error and the second mean square error is a first ratio. The second determining unit is used to determine the first variance of any first boundary image block in the original image and the second variance of the second boundary image block in the original image, wherein the ratio between the first variance and the second variance is a second ratio. The device further includes: The second determining module is used to determine the transition image block contained in each second boundary image block according to the degree of quality difference corresponding to each second boundary image block; The third determining module is used to determine the semantic weight ratio between the region of interest and the region of non-interest in the image to be evaluated and the original image, wherein the semantic weight ratio is a number greater than 1; Based on the semantic weight ratio, determine the first weight value of each pixel in the region of interest and the second weight value of each pixel in the region of non-interest; Based on the first ratio, the second ratio, the first weight value, and the second weight value, a third weight value is determined for each pixel in the transition image block; The fourth determining module is used to determine the quality of the image to be evaluated based on the weight value of each pixel at each location and the pixel value of each pixel at each location in the image to be evaluated and the original image.

8. The apparatus as claimed in claim 7, characterized in that, The second determining unit is specifically used for: Based on the first ratio, the degree of quality difference between any first boundary image block and its adjacent second boundary image block is determined.

9. The apparatus as claimed in claim 8, characterized in that, The second determining unit is specifically used for: If the first ratio is less than the first threshold, the quality difference between any first boundary image block and the adjacent second boundary image block is determined to be a first specified value.

10. The apparatus as claimed in claim 8, characterized in that, The second determining unit is specifically used for: If the first ratio is greater than or equal to the first threshold, the quality difference between any first boundary image block and the adjacent second boundary image block is determined according to the second ratio.

11. The apparatus as claimed in claim 7, characterized in that, The third determining module is further specifically used for: Determine the mean square error corresponding to the region of interest and the region of non-interest in the image to be evaluated and the original image, respectively; The first weight value and the second weight value are updated based on the mean square error corresponding to the region of interest and the region of non-interest, respectively, to determine the updated first weight value and the second weight value.

12. The apparatus according to any one of claims 7-11, characterized in that, The second determining module is specifically used for: If the quality difference level corresponding to any second boundary image block is a first specified value, it is determined that no transition image block is contained in any second boundary image block; or, When the second ratio is less than the second threshold, the quality difference between the first boundary image block and the adjacent second boundary image block is determined to be a second specified value. When the quality difference corresponding to any second boundary image block is the second specified value, the portion of the image block adjacent to the first boundary image block in any second boundary image block is determined to be a transition image block.

13. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the image quality evaluation method as described in any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing a computer program, which, when executed by a processor, implements the image quality evaluation method as described in any one of claims 1-6.

15. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the image quality evaluation method as described in any one of claims 1-6.

Images