Image processing method and device, computer device and storage medium

Abstract

The application relates to an image processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: obtaining an image to be evaluated and a reference image corresponding to the image to be evaluated; extracting pixel gradient information and pixel chrominance information of the image to be evaluated and the reference image respectively; determining gradient similarity between corresponding pixel points of the image to be evaluated and the reference image based on the extracted pixel gradient information, and determining chrominance similarity between the corresponding pixel points of the image to be evaluated and the reference image based on the extracted pixel chrominance information; determining contrast evaluation information of the image to be evaluated based on the gradient similarity and the chrominance similarity; obtaining structure evaluation information of the image to be evaluated; the structure evaluation information is used for representing a structure similarity degree; and determining a quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information. The method can improve the accuracy of the image quality evaluation result.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an image processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of computer technology, image quality assessment can be performed using computer equipment. Image quality assessment has wide applications in many fields, thus increasing the demand for efficient and reliable assessment results. Image quality assessment can use mathematical models to provide quantitative values ​​of image quality. In traditional techniques, the difference between the image to be assessed and the distorted image is directly calculated, squared, and summed, which has low computational complexity and is easy to implement.

[0003] However, traditional image quality assessment methods suffer from low accuracy. Summary of the Invention

[0004] This application provides an image processing method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of image quality assessment results.

[0005] On one hand, this application provides an image processing method. The method includes: acquiring an image to be evaluated and a reference image corresponding to the image to be evaluated; extracting pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, respectively; determining the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determining the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromaticity information; determining the contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity; acquiring the structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image; and determining the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structural evaluation information.

[0006] On the other hand, this application also provides an image processing apparatus. The apparatus includes: an image acquisition module for acquiring an image to be evaluated and a reference image corresponding to the image to be evaluated; an information extraction module for extracting pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, respectively; a similarity calculation module for determining the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determining the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromaticity information; a contrast evaluation module for determining contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity; a structure evaluation module for acquiring structure evaluation information of the image to be evaluated; the structure evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image; and an evaluation result acquisition module for determining the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information.

[0007] On the other hand, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described image processing method.

[0008] On the other hand, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described image processing method.

[0009] On the other hand, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described image processing method.

[0010] The aforementioned image processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product extract pixel gradient information and pixel chromaticity information from the image to be evaluated and the reference image, respectively. Based on the extracted pixel gradient information, they determine the gradient similarity of corresponding pixels between the image to be evaluated and the reference image. Based on the extracted pixel chromaticity information, they determine the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image. Based on the gradient similarity and chromaticity similarity, they determine the contrast evaluation information of the image to be evaluated, obtain the structural evaluation information of the image to be evaluated, and based on the contrast evaluation information and the structural evaluation information, they determine the corresponding quality evaluation result of the image to be evaluated. Because the contrast evaluation information is obtained by combining gradient similarity and chromaticity similarity, and the structural evaluation information is also combined, the obtained evaluation result is closer to the subjective evaluation result of the human eye, thus improving the accuracy of the image evaluation result. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is an application environment diagram of an image processing method in one embodiment;

[0013] Figure 2 This is a flowchart of an image processing method in one embodiment;

[0014] Figure 3 A flowchart illustrating the steps for obtaining structural evaluation information of the image to be evaluated in one embodiment;

[0015] Figure 4 This is a schematic diagram of the image position correspondence in one embodiment;

[0016] Figure 5 This is a general flowchart of an image processing method in one embodiment;

[0017] Figure 6 This is a structural block diagram of an image processing device in one embodiment;

[0018] Figure 7 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0020] The image processing method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle systems, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0021] Specifically, the terminal can acquire images and send them to the server, requesting the server to perform a quality assessment on the acquired images. The server uses the image sent by the terminal as the image to be assessed, obtains the corresponding reference image, extracts the pixel gradient information and pixel chromaticity information of the image to be assessed and the reference image respectively, determines the gradient similarity of corresponding pixels between the image to be assessed and the reference image based on the extracted pixel gradient information, and determines the chromaticity similarity of corresponding pixels between the image to be assessed and the reference image based on the extracted pixel chromaticity information, determines the contrast assessment information of the image to be assessed based on the gradient similarity and chromaticity similarity, obtains the structural assessment information of the image to be assessed, and uses the structural assessment information to characterize the degree of structural similarity between the image to be assessed and the reference image. Based on the contrast assessment information and the structural assessment information, the server determines the quality assessment result corresponding to the image to be assessed and returns the obtained quality assessment result to the terminal.

[0022] In one embodiment, such as Figure 2 As shown, an image processing method is provided, which can be executed collaboratively by a terminal and a server, or by either the terminal or the server alone. In this embodiment, the method is applied to... Figure 1 Taking a server as an example, the following steps are included:

[0023] Step 202: Obtain the image to be evaluated and the corresponding reference image.

[0024] Here, the image to be evaluated refers to the image that needs to undergo quality assessment. In one embodiment, the image to be evaluated may be a night scene image captured by the terminal. The reference image corresponding to the image to be evaluated refers to a standard image used as an evaluation reference when performing quality assessment on the image to be evaluated. It is understood that the higher the similarity between the image to be evaluated and the reference image, the better the quality of the image to be evaluated.

[0025] In one embodiment, the terminal can capture a night scene image, send the night scene image to the server, and request the server to evaluate the quality of the night scene image. After receiving the night scene image, the server uses the night scene image as the image to be evaluated and uses an image obtained by long exposure of the night scene image as a reference image to evaluate the quality of the night scene image captured by the terminal.

[0026] In one embodiment, the image to be evaluated can also be a distorted image obtained by distorting a reference image. This distortion processing can include Gaussian blurring, adding white noise, compression, etc. The server can then perform a quality assessment on the distorted image.

[0027] Step 204: Extract the pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, respectively.

[0028] In this context, the pixel gradient information of the image to be evaluated refers to the gradient information of each pixel in the image to be evaluated, and the pixel chromaticity information of the image to be evaluated refers to the chromaticity information of each pixel in the image to be evaluated. The pixel gradient information of the reference image refers to the gradient information of each pixel in the reference image, and the pixel chromaticity information of the reference image refers to the chromaticity information of each pixel in the reference image. The pixel gradient information can be, for example, at least one of the vertical gradient and the horizontal gradient of the pixel.

[0029] Specifically, the server can extract gradient information from each pixel in the image to be evaluated to obtain the pixel gradient information of the image to be evaluated, and extract chromaticity information from each pixel in the image to be evaluated to obtain the pixel chromaticity information of the image to be evaluated. The server can also extract gradient information from each pixel in the reference image to obtain the pixel gradient information of the reference image, and extract chromaticity information from each pixel in the reference image to obtain the pixel chromaticity information of the reference image.

[0030] In one embodiment, both the image to be evaluated and the reference image are RGB images. The server can perform chromaticity conversion based on the pixel values ​​of the image to be evaluated in each color channel to obtain the pixel chromaticity information of the image to be evaluated, and perform chromaticity conversion based on the pixel values ​​of the reference image in each color channel to obtain the pixel chromaticity information of the reference image.

[0031] Step 206: Determine the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determine the chromatic similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromatic information.

[0032] In this context, corresponding pixels between the image to be evaluated and the reference image refer to pixels that share the same pixel position in both images. For example, the pixel in the first row and second column of the image to be evaluated corresponds to the pixel in the first row and second column of the reference image. Gradient similarity characterizes the degree of similarity in gradient information between two pixels. Chromaticity similarity characterizes the degree of similarity in chromaticity information between two pixels.

[0033] Specifically, the reference image and the image to be evaluated contain the same pixel locations. For each pixel location, the server can calculate the gradient similarity between two pixels at that pixel location in the image to be evaluated and the reference image, and also calculate the chromaticity similarity between two pixels at that pixel location in the image to be evaluated and the reference image.

[0034] Step 208: Determine the contrast evaluation information of the image to be evaluated based on gradient similarity and chromaticity similarity.

[0035] The contrast evaluation information of the image to be evaluated is used to characterize the contrast similarity between the image to be evaluated and the reference image. The contrast evaluation information is positively correlated with gradient similarity and also positively correlated with chromaticity similarity.

[0036] Specifically, for each pixel location, the server can obtain the contrast similarity corresponding to that pixel location based on the gradient similarity and chromaticity similarity. Based on the contrast similarity of all pixel locations, the server calculates the average similarity to obtain the contrast evaluation information of the image to be evaluated.

[0037] In one embodiment, considering that the image content contained in different regions of an image has different importance to the image, the image to be evaluated can be divided into multiple image blocks, and different weights can be set for each image block. Thus, when calculating the contrast evaluation information of the image to be evaluated, the server can multiply the contrast similarity of each pixel position with the weight of the image block to which the pixel position belongs to update the contrast similarity of each pixel position. Finally, the updated contrast similarities are added together and divided by the number of pixel positions to obtain the contrast evaluation information of the image to be evaluated.

[0038] Step 210: Obtain structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image.

[0039] Natural images possess extremely high structural integrity, manifested in the strong correlation between pixels. These correlations carry crucial information about object structure within a visual scene. Assuming the human visual system (HSV) primarily acquires structural information from the visible region, detecting changes in structural information can reveal approximate information about image distortion, allowing for the measurement of the similarity between two images. Based on this, in this embodiment, structural evaluation information can be further obtained, characterizing the degree of structural similarity between the image to be evaluated and a reference image.

[0040] Specifically, in one embodiment, the server can calculate the pixel value dispersion of the image to be evaluated and the reference image, respectively, and calculate the correlation of pixel value change trends between the image to be evaluated and the reference image. Then, based on the pixel value dispersion of the image to be evaluated, the pixel value dispersion of the reference image, and the correlation of pixel value change trends between the image to be evaluated and the reference image, the server can determine the structural evaluation information of the image to be evaluated. The structural evaluation information is positively correlated with the correlation of pixel value change trends and negatively correlated with pixel value dispersion.

[0041] Step 212: Based on the contrast evaluation information and the structure evaluation information, determine the quality evaluation result corresponding to the image to be evaluated.

[0042] The quality assessment result is used to evaluate the degree of image quality loss. The quality assessment result can be a specific numerical value or a quality assessment level, such as: poor, fair, good, or excellent.

[0043] Specifically, the server can multiply the contrast evaluation information and the structure evaluation information to obtain the quality evaluation result corresponding to the image to be evaluated.

[0044] In one embodiment, the server can also obtain brightness assessment information of the image to be evaluated. The brightness assessment information is used to characterize the brightness similarity between the image to be evaluated and the reference image. Then, the server can determine the quality assessment result corresponding to the image to be evaluated based on the brightness assessment information, contrast assessment information, and structure assessment information.

[0045] Furthermore, the server can return the quality assessment results to the terminal.

[0046] In the above image processing method, pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image are extracted respectively. Based on the extracted pixel gradient information, the gradient similarity of corresponding pixels between the image to be evaluated and the reference image is determined. Based on the extracted pixel chromaticity information, the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image is determined. Based on the gradient similarity and chromaticity similarity, the contrast evaluation information of the image to be evaluated is determined, and the structural evaluation information of the image to be evaluated is obtained. Based on the contrast evaluation information and the structural evaluation information, the quality evaluation result corresponding to the image to be evaluated is determined. Since the contrast evaluation information is obtained by combining gradient similarity and chromaticity similarity, and the structural evaluation information is also combined, the evaluation result obtained is closer to the subjective evaluation result of the human eye, thus improving the accuracy of the image evaluation result.

[0047] In one embodiment, determining the gradient similarity of corresponding pixels between an image to be evaluated and a reference image based on the extracted pixel gradient information includes: for each pixel to be evaluated in the image to be evaluated, calculating the horizontal gradient and vertical gradient of the pixel to be evaluated, and determining a first target gradient of the pixel to be evaluated based on the horizontal gradient and vertical gradient; for each reference pixel in the reference image, calculating the horizontal gradient and vertical gradient of the reference pixel, and determining a second target gradient of the reference pixel based on the horizontal gradient and vertical gradient; and determining the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the first target gradient and the second target gradient of the corresponding pixels between the image to be evaluated and the reference image.

[0048] Specifically, for each pixel in the image to be evaluated, the server can calculate the horizontal gradient of the pixel using the following formula (1):

[0049]

[0050] Where f(x) is the pixel value, Cg h (x) represents the calculated horizontal gradient.

[0051] For each pixel in the image to be evaluated, the server can calculate the vertical gradient of the pixel using the following formula (2):

[0052]

[0053] Where f(x) is the pixel value, Cg v (x) represents the calculated vertical gradient.

[0054] After calculating the horizontal and vertical gradients of the pixel to be evaluated, the server can determine the first target gradient of the pixel to be evaluated using the following formula (3):

[0055]

[0056] Where Cg(x) is the gradient of the first objective.

[0057] For each reference pixel in the reference image, the server can use the same calculation method as for the pixel to be evaluated to calculate the horizontal and vertical gradients of the reference pixel, and determine the second target gradient of the reference pixel based on the horizontal and vertical gradients.

[0058] After calculating the first target gradient of each pixel to be evaluated and the second target gradient of each reference pixel, the server calculates the gradient similarity between the corresponding pixels of the image to be evaluated and the reference image based on the first and second target gradients of the corresponding pixels between the image to be evaluated and the reference image using the following formula (4):

[0059]

[0060] Where Cg1(x) is the first target gradient of the corresponding pixel, Cg2(x) is the second target gradient of the corresponding pixel, M1 is a constant, and S cg (x) represents the gradient similarity of the corresponding pixel.

[0061] In the above embodiments, the horizontal and vertical gradients of the pixels to be evaluated and the reference pixels are calculated in the same way, and the target gradient is calculated based on the horizontal and vertical gradients. Finally, the gradient similarity between the corresponding pixels of the image to be evaluated and the reference image is calculated based on the target gradient. The obtained gradient similarity can accurately reflect the degree of similarity of the gradient information of the corresponding pixels between the image to be evaluated and the reference image.

[0062] In one embodiment, determining the chromatic similarity of corresponding pixels between an image to be evaluated and a reference image based on extracted pixel chromaticity information includes: for each pixel to be evaluated in the image to be evaluated, obtaining the pixel values ​​of the pixel to be evaluated in the red, green, and blue channels respectively, and calculating a first chromaticity value to be evaluated and a second chromaticity value to be evaluated in the first chromaticity channel based on the obtained pixel values; for each reference pixel in the reference image, obtaining the pixel values ​​of the reference pixel in the red, green, and blue channels respectively, and calculating the second chromaticity value to be evaluated in the first chromaticity channel based on the obtained pixel values. The first reference chromaticity value of the channel and the second reference chromaticity value of the second chromaticity channel; based on the first chromaticity value to be evaluated and the first reference chromaticity value of the corresponding pixels between the image to be evaluated and the reference image, a first chromaticity similarity component of the corresponding pixels between the image to be evaluated and the reference image is determined; based on the second chromaticity value to be evaluated and the second reference chromaticity value of the corresponding pixels between the image to be evaluated and the reference image, a second chromaticity similarity component of the corresponding pixels between the image to be evaluated and the reference image is determined; based on the first chromaticity similarity component and the second chromaticity similarity component, the chromaticity similarity of the corresponding pixels between the image to be evaluated and the reference image is determined.

[0063] Specifically, in this embodiment, both the image to be evaluated and the reference image are RGB images. Considering that the chromaticity channel contains chromaticity information and can be used as a feature to measure color distortion, for each pixel to be evaluated in the image to be evaluated, the pixel values ​​of the pixel to be evaluated in the red channel, green channel and blue channel are obtained respectively, and the first chromaticity value to be evaluated in the first chromaticity channel and the second chromaticity value to be evaluated in the second chromaticity channel are calculated by the following formula (5):

[0064]

[0065] Where R represents the pixel value of the red channel, G represents the pixel value of the green channel, B represents the pixel value of the blue channel, P represents the first chromaticity value to be evaluated in the first chromaticity channel, and Q represents the second chromaticity value to be evaluated in the second chromaticity channel.

[0066] Similarly, for each reference pixel in the reference image, after obtaining the pixel values ​​of the reference pixel in the red, green and blue channels respectively, the server can calculate the first reference chromaticity value of the reference pixel in the first chromaticity channel and the second reference chromaticity value in the second chromaticity channel based on the obtained pixel values ​​using the above formula (5).

[0067] After calculating the first chromaticity value to be evaluated in the first chromaticity channel and the second chromaticity value to be evaluated in the second chromaticity channel for each evaluation pixel, and the first reference chromaticity value in the first chromaticity channel and the second reference chromaticity value in the second chromaticity channel for each reference pixel, the server can calculate the first chromaticity similarity component of corresponding pixels between the image to be evaluated and the reference image, and calculate the second chromaticity similarity component of corresponding pixels between the image to be evaluated and the reference image. Based on the first chromaticity similarity component and the second chromaticity similarity component, the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image is determined, specifically referring to the following formula (6):

[0068]

[0069] In the above formula, S cc (x) represents the chromaticity similarity, M2 is a constant, the term before "*" is for calculating the first chromaticity similarity component, where P1(x) and P2(x) are the first reference chromaticity values ​​of the corresponding pixels between the image to be evaluated and the reference image in the first chromaticity channel, respectively; the term after "*" is for calculating the second chromaticity similarity component, where Q1(x) and Q2(x) are the second reference chromaticity values ​​of the corresponding pixels between the image to be evaluated and the reference image in the second chromaticity channel, respectively.

[0070] In the above embodiments, the chromatic similarity between corresponding pixels in the evaluation image and the reference image is calculated by using the chromatic similarity of the pixels in the reference image and the image to be evaluated in two different chromaticity channels, resulting in a more accurate calculation.

[0071] In one embodiment, determining the contrast evaluation information of the image to be evaluated based on gradient similarity and chromaticity similarity includes: forming pixel pairs between corresponding pixels of the image to be evaluated; for each pixel pair, determining a contrast component based on the gradient similarity and chromaticity similarity of the pixel pair; the contrast component is positively correlated with the gradient similarity of the pixel pair and also positively correlated with the chromaticity similarity of the pixel pair; and the mean of the contrast components of each pixel pair is calculated to obtain the contrast evaluation information of the image to be evaluated.

[0072] Specifically, for each pixel pair, the server determines the contrast component based on the gradient similarity and chromaticity similarity of the pixel pair. Finally, all contrast components are summed and the average value is calculated to obtain the contrast evaluation information of the image to be evaluated.

[0073] In one specific embodiment, the server can calculate the contrast evaluation information of the image to be evaluated by referring to the following formula (7):

[0074]

[0075] Where C represents the contrast evaluation information, N represents the total number of pixels in the image to be evaluated, and α and β are variable parameters, with a default value of 1.

[0076] In the above embodiments, by calculating the mean of the chromaticity similarity of all corresponding pixels as the chromaticity evaluation information of the image to be evaluated, the quality of the chromaticity information of the image to be evaluated can be well evaluated.

[0077] In one embodiment, such as Figure 3 As shown, structural evaluation information of the image to be evaluated is obtained, including:

[0078] Step 302: Divide the image to be evaluated and the reference image into multiple reference image blocks corresponding to the reference image and multiple image blocks to be evaluated corresponding to the image to be evaluated.

[0079] Step 304: Combine the image block to be evaluated and the reference image block that has an image position correspondence with the image block to be evaluated into an image pair to obtain a set of image pairs.

[0080] The image position correspondence between the reference image block and the image block to be evaluated means that the position of the reference image block in the reference image corresponds to the position of the image block to be evaluated in the transformed image. Therefore, for each pixel in the reference image block, there exists a pixel at the same position in the image block to be evaluated. For example, suppose the reference image A is divided into four reference image blocks A1, A2, A3, and A4, and the transformed image B is divided into four image blocks to be evaluated, B1, B2, B3, and B4, of the same size, position, and number, then the image position correspondence is as follows: Figure 4 As shown, the dashed arrows indicate the corresponding positions in the image. Figure 4 It can be seen that there is a positional correspondence between reference image block A1 and image block B1 to be evaluated, a positional correspondence between reference image block A2 and image block B2 to be evaluated, a positional correspondence between reference image block A3 and image block B3 to be evaluated, and a positional correspondence between reference image block A4 and image block B4 to be evaluated. That is, the reference image block and the image block to be evaluated that make up the image pair are in the same position in the image.

[0081] Specifically, the server can divide the reference image into multiple reference image blocks and the transformed image into multiple image blocks to be evaluated. The reference image blocks and the image blocks to be evaluated that have a corresponding image position with the reference image blocks are then combined to form image pairs, resulting in a set of image pairs. Here, "division" refers to dividing the pixels in the image into regions. "Multiple" means at least two. In some embodiments, the server can use the same image block division method to divide both the reference image and the transformed image, thereby ensuring that the number, position, and size of the image blocks to be evaluated match those of the reference image blocks. In some embodiments, the server can obtain a sliding window, slide the sliding window on the reference image according to a preset sliding method, and use the image region within the sliding window as a reference image block. Then, the server can slide the sliding window on the transformed image according to the same preset sliding method, and use the image region within the sliding window as the image block to be evaluated. This results in reference image blocks and image blocks to be evaluated that are identical in size and number and have one-to-one image position correspondences.

[0082] Step 306: For each image pair in the image pair set, calculate the correlation of pixel value change trends between image blocks in the image pair, and calculate the pixel value dispersion of each image block in the image pair.

[0083] Among them, pixel value change trend correlation refers to the degree of correlation between the changing trends of pixel values ​​between two image patches. Pixel value change trend correlation can specifically be the covariance between the pixel values ​​of the two image patches. Pixel value dispersion refers to the degree of dispersion of pixel values ​​within an image patch. Pixel value dispersion can specifically be the variance of the image patch.

[0084] Step 308: Obtain the intermediate similarity of the image pair based on the correlation of pixel value change trends and the pixel value dispersion of each image block in the image pair.

[0085] Among them, the similarity of image pairs is positively correlated with the trend of pixel value changes, and negatively correlated with the dispersion of pixel values.

[0086] Specifically, for image pairs in the image pair set, the server can calculate the correlation of pixel value change trends between image blocks in the image pair, as well as the pixel value dispersion of each image block in the image pair. Based on the correlation of pixel value change trends and the pixel value dispersion of each image block in the image pair, the intermediate similarity of the image pair is obtained. This intermediate similarity is used to characterize the similarity obtained by structural comparison of image blocks in the image pair.

[0087] In one embodiment, the correlation of pixel value change trends is the covariance, and the pixel value dispersion is the variance. The server can refer to the following formula (8) to calculate the similarity between image patches in an image pair, where S is the similarity between image patches, and σ is the similarity between image patches. 12 Let σ1 and σ2 be the covariance of pixel values ​​between image blocks, respectively, and M4 be a constant.

[0088]

[0089] Step 310: Obtain the preset attention level of each image block to be evaluated, and perform attention processing on the structural similarity of the image pair containing the image block to be evaluated based on the preset attention level to obtain the target similarity of the image pair.

[0090] Here, preset attention level refers to the pre-defined degree of attention given to the image patch to be evaluated. Preset attention level can be, for example, a weight.

[0091] Specifically, for each image patch to be evaluated, the server can multiply the preset attention of the image patch to be evaluated by the structural similarity of the image pair to which the image patch to be evaluated belongs, to obtain the target similarity of the image pair to which the image patch to be evaluated belongs.

[0092] Step 312: Statistical analysis of the target similarity of each image pair in the image pair set is performed to obtain the structural evaluation information of the image to be evaluated.

[0093] Specifically, after obtaining the similarity of each image pair in the image pair set, the server can perform statistics on these similarities to obtain statistical similarity. Specifically, the statistics can be at least one of calculating the average or median of the similarities, and the statistical similarity is used as structural evaluation information for the image to be evaluated.

[0094] In the above embodiments, by dividing the image to be evaluated and the reference image, the structural similarity between the image to be evaluated and the reference image can be calculated by taking image blocks as units, through the correlation of pixel value change trends between image blocks and the pixel value dispersion of each image block. Furthermore, the similarity can be processed by obtaining the preset attention of each image block to be evaluated, and the structural evaluation information can be obtained by statistically analyzing the similarity obtained by the attention processing. The obtained structural evaluation information is more accurate.

[0095] In one embodiment, the method further includes: calculating the first pixel value mean of each pixel in the image to be evaluated, and calculating the second pixel value mean of each pixel in the reference image; determining brightness evaluation information of the image to be evaluated based on the first pixel value mean and the second pixel value mean, wherein the brightness evaluation information is positively correlated with the product of the first pixel value mean and the second pixel value mean, and negatively correlated with the sum of the squares of the first pixel value mean and the second pixel value mean; and determining the quality evaluation result corresponding to the image to be evaluated based on contrast evaluation information and structure evaluation information, including: determining the quality evaluation result corresponding to the image to be evaluated based on brightness evaluation information, contrast evaluation information, and structure evaluation information.

[0096] Specifically, the server can sum the pixel values ​​of all pixels in the image to be evaluated and divide by the total number of pixels in the image to be evaluated to obtain a first average pixel value, and sum the pixel values ​​of all pixels in the reference image and divide by the total number of pixels in the reference image to obtain a second average pixel value. Based on the first and second average pixel values, the server determines the brightness evaluation information of the image to be evaluated. This brightness evaluation information is used to characterize the brightness similarity between the image to be evaluated and the reference image.

[0097] In a specific embodiment, the server can calculate the brightness evaluation information by referring to the following formula (9), where L is the brightness evaluation information, μ1 is the average value of the second pixel, μ2 is the average value of the second pixel, and M3 is a constant:

[0098]

[0099] After obtaining the brightness assessment information, the server can perform a quality assessment on the image to be assessed based on the brightness assessment information, contrast assessment information, and structure assessment information, and obtain the quality assessment result corresponding to the image to be assessed, referring to the following formula (10):

[0100] SITD=C*L*S (10)

[0101] In the above embodiments, brightness evaluation information is obtained by calculating the average pixel values ​​in the image to be evaluated and the reference image. By combining the brightness evaluation information, contrast evaluation information and structure evaluation information, the quality evaluation result corresponding to the image to be evaluated is determined, and the obtained quality evaluation result is more accurate.

[0102] In one specific embodiment, an image processing method is provided, the specific flow of which can be found in [reference needed]. Figure 5 The following is a combination of... Figure 5 And applied to this method Figure 1 Taking the server in the example, the following steps are included:

[0103] 1. Obtain the image to be evaluated and the corresponding reference image.

[0104] The image to be evaluated is a night scene image. The reference image is an image obtained by long exposure of the night scene image. Both the image to be evaluated and the reference image are RGB images.

[0105] 2. Extract the pixel gradient Cg1 of each pixel in the image to be evaluated and the pixel gradient Cg2 of each pixel in the reference image. Calculate the gradient similarity Scg between corresponding pixels in the image to be evaluated and the reference image based on the pixel gradient Cg1 of the image to be evaluated and the pixel gradient Cg2 of the reference image.

[0106] Specifically, the server can calculate the pixel gradient by referring to the above formulas (1)-(3) and calculate the gradient similarity by referring to the above formula (4).

[0107] 3. Extract the chromaticity P1 of the first chromaticity channel and the chromaticity Q1 of the second chromaticity channel for each pixel in the image to be evaluated.

[0108] 4. Extract the chromaticity P2 of each reference pixel in the first chromaticity channel and the chromaticity Q2 of the second chromaticity channel from the reference image.

[0109] 5. The server calculates the chromatic similarity Scc based on the chromaticity P1 and P2 of the corresponding pixels between the image to be evaluated and the reference image in the first chromaticity channel, and the chromaticity Q1 and Q2 of the second chromaticity channel.

[0110] Specifically, the server can obtain the pixel values ​​of the image to be evaluated in the R channel, G channel and B channel respectively, and obtain the pixel values ​​of the reference image in the R channel, G channel and B channel respectively. The chromaticity values ​​of the first chromaticity channel and the second chromaticity channel are extracted with reference to the above formula (5), and the chromaticity similarity Scc is calculated with reference to the above formula (6).

[0111] 6. Form pixel pairs between corresponding pixels of the image to be evaluated. For each pixel pair, determine the contrast component based on the gradient similarity and chromaticity similarity of the pixel pair. Calculate the mean of the contrast components of each pixel pair to obtain the contrast evaluation factor C of the image to be evaluated.

[0112] Among them, the contrast component is positively correlated with the gradient similarity of pixel pairs and also positively correlated with the chromaticity similarity of pixel pairs. The server can calculate the contrast evaluation factor C by referring to the above formula (7).

[0113] 7. Calculate the average pixel value μ1 of all pixels to be evaluated in the image to be evaluated and the average pixel value μ2 of all reference pixels in the reference image. Calculate the brightness evaluation factor L based on μ1 and μ2.

[0114] Specifically, the server can calculate the brightness evaluation factor L by referring to the above formula (9).

[0115] 8. Calculate the variance σ1 of the pixel values ​​of all pixels to be evaluated in the image to be evaluated, and calculate the variance σ2 of the pixel values ​​of all reference pixels in the reference image.

[0116] 9. Calculate the covariance σ of pixel values ​​between the image to be evaluated and the reference image. 12 .

[0117] 10. Based on variance σ1, variance σ2, and covariance σ 12 Calculate the structural evaluation factor S between the image to be evaluated and the reference image.

[0118] Specifically, the server can calculate the structural evaluation factor S by referring to the above formula (8).

[0119] 11. Based on the luminance evaluation factor L, contrast evaluation factor C, and structure evaluation factor S, determine the quality evaluation result of the image to be evaluated.

[0120] Specifically, the server can calculate the quality assessment result by referring to the above formula (10).

[0121] In the above embodiments, considering that night scene images often have high contrast and significant color variations, a contrast evaluation factor is obtained by calculating the gradient similarity and color similarity between the night scene image and the reference image. This contrast factor is then combined with the brightness evaluation factor and structure evaluation factor of the night scene image to obtain a quality evaluation result for the night scene image. This approach yields a more rigorous image quality evaluation result that is closer to the subjective evaluation result of the human eye.

[0122] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0123] Based on the same inventive concept, this application also provides an image processing apparatus for implementing the methods described above. The solution provided by this apparatus is similar to the implementation schemes described in the above methods; therefore, the specific limitations in one or more image processing apparatus embodiments provided below can be found in the limitations of the image processing methods described above, and will not be repeated here.

[0124] In one embodiment, such as Figure 6 As shown, an image processing apparatus 600 is provided, comprising:

[0125] Image acquisition module 602 is used to acquire the image to be evaluated and the reference image corresponding to the image to be evaluated;

[0126] The information extraction module 604 is used to extract pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, respectively.

[0127] The similarity calculation module 606 is used to determine the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information, and to determine the chromatic similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromatic information.

[0128] The contrast evaluation module 608 is used to determine the contrast evaluation information of the image to be evaluated based on gradient similarity and chromaticity similarity.

[0129] The structural evaluation module 610 is used to acquire structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image.

[0130] The evaluation result acquisition module 612 is used to determine the quality evaluation result corresponding to the image to be evaluated based on contrast evaluation information and structure evaluation information.

[0131] The aforementioned image processing device extracts pixel gradient information and pixel chromaticity information from the image to be evaluated and the reference image, respectively. Based on the extracted pixel gradient information, it determines the gradient similarity of corresponding pixels between the image to be evaluated and the reference image. Based on the extracted pixel chromaticity information, it determines the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image. Based on the gradient similarity and chromaticity similarity, it determines the contrast evaluation information of the image to be evaluated and obtains the structural evaluation information of the image to be evaluated. Based on the contrast evaluation information and the structural evaluation information, it determines the corresponding quality evaluation result of the image to be evaluated. Because it combines gradient similarity and chromaticity similarity to obtain contrast evaluation information, and also combines structural evaluation information, the obtained evaluation result is closer to the subjective evaluation result of the human eye, thus improving the accuracy of the image evaluation result.

[0132] In one embodiment, the similarity calculation module is further configured to: calculate the horizontal gradient and vertical gradient of each pixel to be evaluated in the image to be evaluated, and determine a first target gradient of the pixel to be evaluated based on the horizontal gradient and vertical gradient; calculate the horizontal gradient and vertical gradient of each reference pixel in the reference image, and determine a second target gradient of the reference pixel based on the horizontal gradient and vertical gradient; and determine the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the first target gradient and the second target gradient of corresponding pixels between the image to be evaluated and the reference image.

[0133] In one embodiment, the similarity calculation module is further configured to: for each pixel in the image to be evaluated, obtain the pixel values ​​of the pixel in the red, green, and blue channels respectively; calculate a first chromaticity value to be evaluated in the first chromaticity channel and a second chromaticity value to be evaluated in the second chromaticity channel based on the obtained pixel values; for each reference pixel in the reference image, obtain the pixel values ​​of the reference pixel in the red, green, and blue channels respectively; calculate a first reference chromaticity value in the first chromaticity channel and a second reference chromaticity value in the second chromaticity channel based on the obtained pixel values; determine a first chromaticity similarity component of corresponding pixels between the image to be evaluated and the reference image based on the first chromaticity value to be evaluated and the first reference chromaticity value of corresponding pixels between the image to be evaluated and the reference image; determine a second chromaticity similarity component of corresponding pixels between the image to be evaluated and the reference image based on the second chromaticity value to be evaluated and the second reference chromaticity value of corresponding pixels between the image to be evaluated and the reference image; and determine the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image based on the first chromaticity similarity component and the second chromaticity similarity component.

[0134] In one embodiment, the contrast evaluation module is further configured to form pixel pairs between corresponding pixels of the image to be evaluated; for each pixel pair, determine a contrast component based on the gradient similarity and chromaticity similarity of the pixel pair; the contrast component is positively correlated with the gradient similarity of the pixel pair and positively correlated with the chromaticity similarity of the pixel pair; and calculate the mean value based on the contrast components of each pixel pair to obtain the contrast evaluation information of the image to be evaluated.

[0135] In one embodiment, the structure evaluation module is further configured to: divide the image to be evaluated and the reference image into multiple reference image blocks corresponding to the reference image and multiple image blocks to be evaluated corresponding to the image to be evaluated; form image pairs by combining the image blocks to be evaluated and the reference image blocks that have an image position correspondence with the image blocks to be evaluated, thereby obtaining an image pair set; for each image pair in the image pair set, calculate the correlation of pixel value change trends between the image blocks in the image pair and calculate the pixel value dispersion of each image block in the image pair; obtain the intermediate similarity of the image pair based on the correlation of pixel value change trends and the pixel value dispersion of each image block in the image pair; obtain the preset attention level of each image block to be evaluated, and perform attention processing on the intermediate similarity of the image pair to which the image block to be evaluated belongs based on the preset attention level to obtain the target similarity of the image pair; and statistically analyze the target similarity of each image pair in the image pair set to obtain the structure evaluation information of the image to be evaluated.

[0136] In one embodiment, the above apparatus is further configured to: a brightness evaluation module, configured to calculate the first pixel value mean of each pixel in the image to be evaluated, and to calculate the second pixel value mean of each pixel in the reference image; determine brightness evaluation information of the image to be evaluated based on the first pixel value mean and the second pixel value mean, wherein the brightness evaluation information is positively correlated with the product of the first pixel value mean and the second pixel value mean, and negatively correlated with the sum of the squares of the first pixel value mean and the second pixel value mean; and an evaluation result acquisition module, further configured to determine the quality evaluation result corresponding to the image to be evaluated based on the brightness evaluation information, contrast evaluation information, and structure evaluation information.

[0137] Each module in the aforementioned image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0138] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores image data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an image processing method.

[0139] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0140] This application also provides a computer-readable storage medium. One or more non-volatile computer-readable storage media containing computer-executable instructions, which, when executed by one or more processors, cause the processors to perform the steps of an image processing method.

[0141] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform an image processing method.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0144] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An image processing method, characterized in that, include: Obtain the image to be evaluated and the corresponding reference image; Pixel gradient information and pixel chromaticity information are extracted from the image to be evaluated and the reference image, respectively. The gradient similarity between corresponding pixels in the image to be evaluated and the reference image is determined based on the extracted pixel gradient information, and the chromaticity similarity between corresponding pixels in the image to be evaluated and the reference image is determined based on the extracted pixel chromaticity information. Based on the gradient similarity and chromaticity similarity, the contrast evaluation information of the image to be evaluated is determined; including: according to The contrast evaluation information is obtained; C is the contrast evaluation information, N is the total number of pixels in the image to be evaluated, and α and β are variable parameters. This represents the gradient similarity of the corresponding pixels. This represents the chromaticity similarity of the corresponding pixels. Obtain structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image. Based on the contrast evaluation information and the structure evaluation information, the quality evaluation result corresponding to the image to be evaluated is determined, including: obtaining the quality evaluation result according to SITD = C * L * S; where SITD is the quality evaluation result, C is the contrast evaluation information, L is the brightness evaluation information of the image to be evaluated, and S is the structure evaluation information.

2. The method according to claim 1, characterized in that, The step of determining the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information includes: For each pixel in the image to be evaluated, calculate the horizontal gradient and vertical gradient of the pixel to be evaluated, and determine the first target gradient of the pixel to be evaluated based on the horizontal gradient and the vertical gradient. For each reference pixel in the reference image, calculate the horizontal gradient and vertical gradient of the reference pixel, and determine the second target gradient of the reference pixel based on the horizontal gradient and the vertical gradient. The gradient similarity between corresponding pixels in the image to be evaluated and the reference image is determined based on the first target gradient and the second target gradient of corresponding pixels between the image to be evaluated and the reference image.

3. The method according to claim 1, characterized in that, Determining the chromatic similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromaticity information includes: For each pixel in the image to be evaluated, the pixel values ​​of the pixel to be evaluated in the red channel, green channel and blue channel are obtained respectively. Based on the obtained pixel values, the first chromaticity value to be evaluated in the first chromaticity channel and the second chromaticity value to be evaluated in the second chromaticity channel are calculated. For each reference pixel in the reference image, the pixel values ​​of the reference pixel in the red channel, green channel and blue channel are obtained respectively. Based on the obtained pixel values, the first reference chromaticity value of the reference pixel in the first chromaticity channel and the second reference chromaticity value in the second chromaticity channel are calculated. Based on the first chromaticity value to be evaluated and the first reference chromaticity value of the corresponding pixels between the image to be evaluated and the reference image, the first chromaticity similarity component of the corresponding pixels between the image to be evaluated and the reference image is determined; Based on the second chromaticity value to be evaluated and the second reference chromaticity value of the corresponding pixels between the image to be evaluated and the reference image, the second chromaticity similarity component of the corresponding pixels between the image to be evaluated and the reference image is determined; Based on the first chromaticity similarity component and the second chromaticity similarity component, the chromaticity similarity of corresponding pixels between the image to be evaluated and the reference image is determined.

4. The method according to claim 1, characterized in that, The step of determining the contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity includes: The corresponding pixels between the images to be evaluated are grouped into pixel pairs; For each pixel pair, a contrast component is determined based on the gradient similarity and chromaticity similarity of the pixel pair; the contrast component is positively correlated with the gradient similarity of the pixel pair and also positively correlated with the chromaticity similarity of the pixel pair. The contrast evaluation information of the image to be evaluated is obtained by averaging the contrast components of each pixel pair.

5. The method according to claim 1, characterized in that, The process of obtaining structural evaluation information for the image to be evaluated includes: The image to be evaluated and the reference image are divided into multiple reference image blocks corresponding to the reference image and multiple image blocks to be evaluated corresponding to the image to be evaluated. The image block to be evaluated and the reference image block that has an image position correspondence with the image block to be evaluated are combined into an image pair to obtain an image pair set; For each image pair in the image pair set, calculate the correlation of pixel value change trends between image blocks in the image pair, and calculate the pixel value dispersion of each image block in the image pair; The intermediate similarity of the image pair is obtained based on the correlation of the pixel value change trend and the pixel value dispersion of each image block in the image pair. Obtain the preset attention value of each image block to be evaluated, and perform attention processing on the intermediate similarity of the image pair containing the image block to be evaluated based on the preset attention value to obtain the target similarity of the image pair. The structural evaluation information of the image to be evaluated is obtained by statistically analyzing the target similarity of each image pair in the image pair set.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Calculate the average first pixel value of each pixel in the image to be evaluated, and calculate the average second pixel value of each pixel in the reference image; Based on the first pixel value mean and the second pixel value mean, the brightness evaluation information of the image to be evaluated is determined. The brightness evaluation information is positively correlated with the product of the first pixel value mean and the second pixel value mean, and negatively correlated with the sum of the squares of the first pixel value mean and the second pixel value mean. The step of determining the quality assessment result corresponding to the image to be evaluated based on the contrast assessment information and the structure assessment information includes: Based on the brightness evaluation information, the contrast evaluation information, and the structure evaluation information, the quality evaluation result corresponding to the image to be evaluated is determined.

7. An image processing apparatus, characterized in that, include: The image acquisition module is used to acquire the image to be evaluated and the reference image corresponding to the image to be evaluated; The information extraction module is used to extract pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, respectively. The similarity calculation module is used to determine the gradient similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel gradient information, and to determine the chromatic similarity of corresponding pixels between the image to be evaluated and the reference image based on the extracted pixel chromatic information. The contrast evaluation module is used to determine the contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity; specifically, it is used to: based on... The contrast evaluation information is obtained; C is the contrast evaluation information, N is the total number of pixels in the image to be evaluated, and α and β are variable parameters. This represents the gradient similarity of the corresponding pixels. This represents the chromaticity similarity of the corresponding pixels. A structural evaluation module is used to acquire structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the degree of structural similarity between the image to be evaluated and the reference image. The evaluation result acquisition module is used to determine the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information; specifically, it is used to obtain the quality evaluation result according to SITD = C * L * S; where SITD is the quality evaluation result, C is the contrast evaluation information, L is the brightness evaluation information of the image to be evaluated, and S is the structure evaluation information.

8. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the computer program is executed by the processor, the processor performs the steps of the image processing method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the image processing method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the image processing method according to any one of claims 1 to 6.

Images