CN116797510A - Image processing methods, devices, computer equipment and storage media - Google Patents

Abstract

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

Description

Image processing methods, devices, computer equipment and storage media

Technical field

The present application relates to the field of computer technology, and in particular to an image processing method, device, computer equipment, computer-readable storage medium and computer program product.

Background technique

With the development of computer technology, image quality assessment can be performed through computer equipment. Image quality assessment is widely used in many fields, so there is an increasing demand for efficient and reliable assessment results. For image quality assessment, mathematical models can be used to give a quantitative value of image quality. In traditional technology, the difference between the image to be evaluated and the distorted image is directly squared and summed, which has low computational complexity and is easy to implement.

However, traditional image quality assessment methods have the problem of low accuracy of assessment results.

Contents of the invention

Embodiments of the present application provide an image processing method, device, computer equipment, computer-readable storage medium, and computer program product, which can improve the accuracy of image quality assessment results.

On the one hand, this application provides an image processing method. The method includes: obtaining an image to be evaluated and a reference image corresponding to the image to be evaluated; respectively extracting pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image; and determining based on the extracted pixel gradient information. Obtain the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image, and determine the chromaticity of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel chromaticity information Similarity; based on the gradient similarity and chromaticity similarity, determine the contrast evaluation information of the image to be evaluated; obtain the structure evaluation information of the image to be evaluated; the structure evaluation information is used to characterize the image to be evaluated The degree of structural similarity between the image and the reference image; based on the contrast evaluation information and the structure evaluation information, determine the quality evaluation result corresponding to the image to be evaluated.

On the other hand, this application also provides an image processing device. The device includes: an image acquisition module, used to acquire an image to be evaluated and a reference image corresponding to the image to be evaluated; an information extraction module, used to extract pixel gradient information and pixels of the image to be evaluated and the reference image, respectively. Chromaticity information; a similarity calculation module, configured to determine the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determine based on the extracted pixel chromaticity information. The chromaticity similarity of the corresponding pixel points between the image to be evaluated and the reference image; a contrast evaluation module, used to determine the contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity. ; A structural evaluation module, used to obtain the structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the structural similarity between the image to be evaluated and the reference image; an evaluation result acquisition module, used to Based on the contrast evaluation information and the structure evaluation information, a quality evaluation result corresponding to the image to be evaluated is determined.

On the other hand, this application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the above image processing method are implemented.

On the other hand, this application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above image processing method are implemented.

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

The above-mentioned image processing method, device, computer equipment, computer-readable storage medium and computer program product, by respectively extracting the pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, based on the extracted pixel gradient information Determine and obtain the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image, and determine the color of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel chromaticity information. Degree similarity, based on the gradient similarity and chromaticity similarity, determine the contrast evaluation information of the image to be evaluated, obtain the structure evaluation information of the image to be evaluated, based on the contrast evaluation information and the structure evaluation information , determine the quality evaluation results corresponding to the image to be evaluated. Since the gradient similarity and chromaticity similarity are combined to obtain the contrast evaluation information, and combined with the structure evaluation information, the evaluation results obtained are closer to the subjective evaluation results of the human eye, improving improve the accuracy of image evaluation results.

Description of the drawings

In order to explain the embodiments of the present application or the technical solutions in the prior art more clearly, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

Figure 1 is an application environment diagram of the image processing method in one embodiment;

Figure 2 is a flow chart of an image processing method in one embodiment;

Figure 3 is a flow chart of steps for obtaining the structure evaluation information of the image to be evaluated in one embodiment;

Figure 4 is a schematic diagram of image position correspondence in one embodiment;

Figure 5 is an overall flow chart of an image processing method in one embodiment;

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

Figure 7 is a structural block diagram of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

The image processing method provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. . Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented as an independent server or a server cluster composed of multiple servers.

Specifically, the terminal can collect images and send them to the server, and request the server to perform quality assessment on the collected images. The server uses the images sent by the terminal as the images to be evaluated, obtains the reference images corresponding to the images to be evaluated, and extracts the values of the images to be evaluated and the reference images respectively. Pixel gradient information and pixel chromaticity information, based on the extracted pixel gradient information, determine the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image, and determine the image to be evaluated and the reference image based on the extracted pixel chromaticity information The chromaticity similarity of the corresponding pixels between the images, based on the gradient similarity and chromaticity similarity, determines the contrast evaluation information of the image to be evaluated, and obtains the structural evaluation information of the image to be evaluated. The structural evaluation information is used to characterize the image to be evaluated. The degree of structural similarity between the image and the reference image is based on the contrast evaluation information and the structure evaluation information, the quality evaluation result corresponding to the image to be evaluated is determined, and the obtained quality evaluation result is returned to the terminal.

In one embodiment, as shown in Figure 2, an image processing method is provided, which can be executed by a terminal and a server in cooperation, or can be executed by the terminal or the server alone. In this embodiment, the method is applied to the server in Figure 1 as an example to illustrate, including the following steps:

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

Among them, the image to be evaluated refers to the image that needs to be evaluated for quality. In one embodiment, the image to be evaluated may be a night scene image captured by a terminal. The reference image corresponding to the image to be evaluated refers to the standard image used as an evaluation reference when evaluating the quality of the image to be evaluated. It can be 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.

In one embodiment, the terminal can collect night scene images, send the night scene images to the server, and request the server to evaluate the quality of the night scene images. After the server receives the night scene images, it will use the night scene images as images to be evaluated and perform long exposure on the night scene images. The obtained image is used as a reference image to evaluate the quality of the night scene image captured by the terminal.

In one embodiment, the image to be evaluated may also be a distorted image obtained by subjecting the reference image to distortion processing. The distortion processing here can be Gaussian blur processing, adding white noise, compression processing, etc. Then the server can evaluate the quality of the image obtained by distortion processing.

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

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 gradient information of the pixel may be, for example, at least one of a vertical gradient and a horizontal gradient of the pixel.

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

In one embodiment, the image to be evaluated and the reference image are both 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. Based on the reference image in each color channel The pixel values of the color channels undergo chromaticity conversion to obtain the pixel chromaticity information of the reference image.

Step 206: Determine the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determine the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel chromaticity information. chroma similarity.

The corresponding pixel points between the image to be evaluated and the reference image refer to the pixel points with the same pixel position between the image to be evaluated and the reference image. For example, the pixels in the first row and second column of the image to be evaluated, and the corresponding pixels in the reference image refer to the pixels in the first row and second column of the reference image. Gradient similarity is used to characterize the similarity of gradient information between two pixels. Chroma similarity is used to characterize the similarity of chroma information between two pixels.

Specifically, the reference image and the image to be evaluated contain the same pixel position. For each pixel position, the server can calculate the gradient similarity between the two pixels of the image to be evaluated and the reference image at the pixel position, and calculate the pixel position to be evaluated. Evaluates the chromaticity similarity between two pixels at that pixel location in the image and the reference image.

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

Among them, 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. Contrast evaluation information is positively correlated with gradient similarity and is positively correlated with chromaticity similarity.

Specifically, for each pixel position, the server can obtain the contrast similarity corresponding to the pixel position based on the gradient similarity and chromaticity similarity corresponding to the pixel position, and calculate the similarity average based on the contrast similarities of all pixel positions to obtain Contrast evaluation information for the image to be evaluated.

In one embodiment, considering that the image content contained in each area in the image is not equally important to the image, the image to be evaluated can be divided to obtain multiple image blocks, and different weights are set for each image block, so as to When calculating the contrast evaluation information of the image to be evaluated, the server can multiply the contrast similarity of each pixel position by the weight of the image block to which the pixel position belongs to update the contrast similarity of each pixel position, and finally update the contrast similarity of each pixel position. The contrast similarities are added and divided by the number of pixel positions to obtain the contrast evaluation information of the image to be evaluated.

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

Natural images have extremely high structure, which is reflected in the strong correlation between pixels in the image. These correlations carry important information about the structure of objects in the visual scene. Assuming that the human visual system (HSV) mainly obtains structural information from the visible area, then by detecting whether the structural information changes, the approximate information of image distortion can be perceived and the similarity of two images can be measured. Based on this, in the embodiment of the present application, the structure evaluation information can be further obtained. The structure evaluation information is used to characterize the structural similarity between the image to be evaluated and the reference image.

Specifically, in one embodiment, the server can separately calculate the pixel value dispersion of the image to be evaluated and the reference image, and calculate the pixel value change trend correlation between the image to be evaluated and the reference image, and can further calculate the dispersion of the pixel values based on the image to be evaluated and the reference image. The pixel value dispersion, the pixel value dispersion of the reference image, and the pixel value change trend correlation between the image to be evaluated and the reference image determine the structural evaluation information of the image to be evaluated. Among them, the structure evaluation information is positively correlated with the pixel value change trend correlation and negatively correlated with the pixel value dispersion.

Step 212: Determine the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information.

Among them, the quality assessment results are used to evaluate the degree of quality loss of the image. The quality evaluation result may be a specific numerical value, or a quality evaluation grade. For example, the quality evaluation grade may be: poor, average, good, or very good.

Specifically, the server may multiply the contrast evaluation information and the structure evaluation information to obtain a quality evaluation result corresponding to the image to be evaluated.

In one embodiment, the server can also obtain the brightness evaluation information of the image to be evaluated. The brightness evaluation information is used to characterize the brightness similarity between the image to be evaluated and the reference image. The server can then obtain the brightness evaluation information, contrast evaluation information and structure based on the brightness evaluation information. Evaluation information to determine the quality evaluation results corresponding to the image to be evaluated.

Further, the server can return the quality assessment result to the terminal.

In the above image processing method, by respectively extracting the pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image, the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image is determined based on the extracted pixel gradient information. , based on the extracted pixel chromaticity information, determine the chromaticity similarity of the corresponding pixel points between the image to be evaluated and the reference image, based on the gradient similarity and chromaticity similarity, determine the contrast evaluation information of the image to be evaluated, and obtain the image to be evaluated The structural evaluation information of the image is based on the contrast evaluation information and the structural evaluation information to determine the quality evaluation result corresponding to the image to be evaluated. The contrast evaluation information is obtained by combining gradient similarity and chromaticity similarity, and combined with the structural evaluation information, we get The evaluation results are closer to the subjective evaluation results of the human eye, improving the accuracy of the image evaluation results.

In one embodiment, determining the gradient similarity of the corresponding pixel point between the image to be evaluated and the reference image based on the extracted pixel gradient information includes: for each pixel point to be evaluated in the image to be evaluated, calculating the pixel point to be evaluated The horizontal gradient and vertical gradient of The gradient determines the second target gradient of the reference pixel point; based on the first target gradient and the second target gradient of the corresponding pixel point between the image to be evaluated and the reference image, determine the gradient of the corresponding pixel point between the image to be evaluated and the reference image. Similarity.

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

Among them, f(x) is the pixel value, and Cg _h (x) is the calculated horizontal gradient.

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

Among them, f(x) is the pixel value, and Cg _v (x) is the calculated vertical gradient.

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

Among them, Cg(x) is the first target gradient.

For each reference pixel of the reference image, the server can use the same calculation method as the pixel to be evaluated, 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 vertical gradient. .

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 first target gradient and the second target gradient of the corresponding pixel between the image to be evaluated and the reference image. Gradient, and calculate the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image through the following formula (4):

Among them, Cg ₁ (x) is the first target gradient of the corresponding pixel point, Cg ₂ (x) is the second target gradient of the corresponding pixel point, M ₁ is a constant, S _cg (x) is the gradient similarity of the corresponding pixel point .

In the above embodiment, the horizontal gradient and the vertical gradient are calculated in the same way for the pixel points to be evaluated and the reference pixel points, and the target gradient is calculated based on the flat gradient and the vertical gradient. Finally, the relationship between the image to be evaluated and the reference image is calculated based on the target gradient. The gradient similarity of the corresponding pixels can accurately reflect the similarity of the gradient information of the corresponding pixels between the image to be evaluated and the reference image.

In one embodiment, determining the chromaticity similarity of the corresponding pixel point between the image to be evaluated and the reference image based on the extracted pixel chromaticity information includes: for each pixel point to be evaluated in the image to be evaluated, obtain The pixel values of the pixels in the red channel, green channel and blue channel are calculated based on the obtained pixel values. The first chromaticity value to be evaluated in the first chromaticity channel and the second chromaticity value in the second chromaticity channel are calculated. Second, the chromaticity value to be evaluated; for each reference pixel point of the reference image, obtain the pixel values of the reference pixel point in the red channel, green channel, and blue channel respectively, and calculate the first chromaticity value of the reference pixel point 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; the first chromaticity value to be evaluated and the first reference chromaticity value based on the corresponding pixel points between the image to be evaluated and the reference image value, determine the first chromaticity similarity component of the corresponding pixel point between the image to be evaluated and the reference image; based on the second chromaticity value to be evaluated and the second reference color of the corresponding pixel point between the image to be evaluated and the reference image The second chromaticity similarity component of the corresponding pixel point 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 relationship between the image to be evaluated and the reference image is determined. The chromaticity similarity between corresponding pixels.

Specifically, in this embodiment, the image to be evaluated and the reference image are both RGB images. Considering that the chromaticity channel contains chromaticity information and can be used as a feature to measure color distortion, then for each pixel to be evaluated in the image to be evaluated, Obtain the pixel values of the pixel to be evaluated in the red channel, green channel and blue channel respectively, and calculate the first chromaticity value to be evaluated in the first chromaticity channel and the second chromaticity value in the second chromaticity channel of the pixel to be evaluated through the following formula (5) The second chromaticity value to be evaluated for the chroma channel:

Among them, 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 of the first chroma channel, and Q represents the second chroma channel. The second chromaticity value to be evaluated.

Similarly, for each reference pixel of the reference image, after the server obtains the pixel values of the reference pixel in the red channel, green channel, and blue channel, it can calculate the reference pixel based on the obtained pixel values through the above formula (5) Point a first reference chroma value in a first chroma channel and a second reference chroma value in a second chroma channel.

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 of each evaluation pixel point are respectively calculated, and each reference pixel point is in the first chromaticity channel. The first reference chromaticity value of the channel and the second reference chromaticity value of the second chromaticity channel. Based on these obtained chromaticity values, the server can calculate the first color of the corresponding pixel point between the image to be evaluated and the reference image. similarity component, and calculate the second chroma similarity component of the corresponding pixel point between the image to be evaluated and the reference image, and determine the image to be evaluated and based on the first chroma similarity component and the second chroma similarity component. Refer to the chromaticity similarity of corresponding pixels between reference images, specifically refer to the following formula (6):

In the above formula, S _cc (x) is the chromaticity similarity, M ₂ is a constant, and the first term of "*" is to calculate the first chromaticity similarity component, where P ₁ (x) and P ₂ (x) are respectively is the first reference chromaticity value in the first chromaticity channel of the corresponding pixel point between the image to be evaluated and the reference image; the last term of "*" is to calculate the second chromaticity similarity component, where Q ₁ (x) , Q ₂ (x) are respectively the second reference chromaticity value in the second chromaticity channel of the corresponding pixel point between the image to be evaluated and the reference image.

In the above embodiment, the chromaticity similarity of the corresponding pixels between the evaluation image and the reference image is calculated based on the chromaticity similarity of the respective pixels in the reference image and the image to be evaluated in two different chromaticity channels. The calculation result more precise.

In one embodiment, determining the contrast evaluation information of the image to be evaluated based on the gradient similarity and the chromaticity similarity includes: forming a pixel point pair from the corresponding pixel points between the image to be evaluated and the image to be evaluated; for each pixel For point pairs, the contrast component is determined based on the gradient similarity and chromaticity similarity of the pixel point pair; the contrast component is positively correlated with the gradient similarity of the pixel point pair, and is positively correlated with the chromaticity similarity of the pixel point pair; based on each pixel point Calculate the mean value of the contrast components to obtain the contrast evaluation information of the image to be evaluated.

Specifically, for each pixel pair, the server determines the contrast component based on the gradient similarity and chromaticity similarity of the pixel pair, and finally adds up all the contrast components and calculates the average value to obtain the contrast evaluation information of the image to be evaluated.

In a specific embodiment, the server can refer to the following formula (7) to calculate the contrast evaluation information of the image to be evaluated:

Among them, C is the contrast evaluation information, N is the total number of pixels in the image to be evaluated, α and β are variable parameters, and the default is 1.

In the above embodiment, by calculating the mean value of the chromaticity similarity of all corresponding pixel points 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.

In one embodiment, as shown in Figure 3, obtaining the structural evaluation information of the image to be evaluated includes:

Step 302: Divide the image to be evaluated and the reference image respectively to obtain multiple reference image blocks corresponding to the reference image and multiple image blocks to be evaluated corresponding to the image to be evaluated.

Step 304: Combine the image block to be evaluated and the reference image block that has an image position corresponding relationship with the image block to be evaluated to form an image pair to obtain an image pair set.

Wherein, 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, then for each reference image block Pixels with the same position exist in the image blocks to be evaluated corresponding to their positions. For example, assume that the reference image A is divided into four reference image blocks A1, A2, A3, and A4, and the transformed image B is divided in the same way into four image blocks to be evaluated, B1, B2, B3, B4, the image position correspondence relationship is shown in Figure 4, in which the dotted arrow represents the image position correspondence relationship. It can be seen from Figure 4 that there is a position correspondence relationship between the reference image block A1 and the image block B1 to be evaluated. Reference There is a positional correspondence between the image block A2 and the image block to be evaluated B2, there is a positional correspondence between the reference image block A3 and the image block to be evaluated B3, there is a positional correspondence between the reference image block A4 and the image block to be evaluated B4, That is, the positions of the reference image blocks and the image blocks to be evaluated that make up the image pair are consistent in the image.

Specifically, the server can divide the reference image to obtain multiple reference image blocks, divide the transformed image to obtain multiple image blocks to be evaluated, and combine the reference image blocks and the image to be evaluated that have an image position corresponding relationship with the reference image block. The blocks form image pairs to obtain a set of image pairs. Division refers to dividing the pixels in the image into regions. Where multiple refers to at least two. In some embodiments, the server may use the same image block dividing method to divide the reference image and the transformed image respectively, so that the number, position, and size of the image blocks to be evaluated match the reference image blocks. In some embodiments, the server can obtain the sliding window, slide the sliding window on the reference image according to the preset sliding method, use the image area within the sliding window as the reference image block, and slide the sliding window on the reference image according to the preset sliding method. Sliding is performed on the transformed image, and the image area within the sliding window is used as the image block to be evaluated, so that the reference image block and the image block to be evaluated can be obtained with the same size and number, and one-to-one correspondence between the image positions.

Step 306: For the image pairs in the image pair set, calculate the pixel value change trend correlation between the image blocks in the image pair, and calculate the pixel value dispersion corresponding to each image block in the image pair.

Among them, the pixel value change trend correlation refers to the degree of correlation between the transformation trends of pixel values between two image blocks. Specifically, the pixel value change trend correlation may be the covariance between the pixel values of two image blocks. Pixel value dispersion refers to the degree of dispersion of pixel values in an image block. The pixel value dispersion may specifically be the variance of the image block.

Step 308: Obtain the intermediate similarity corresponding to the image pair based on the pixel value change trend correlation and the pixel value dispersion corresponding to each image block in the image pair.

Among them, the similarity between the image pairs is positively correlated with the pixel value change trend correlation, and is negatively correlated with the pixel value dispersion.

Specifically, for the image pairs in the image pair set, the server can calculate the pixel value change trend correlation between the image blocks in the image pair, and the pixel value dispersion corresponding to each image block in the image pair, based on the pixel value change trend The correlation degree and the pixel value dispersion corresponding to each image block in the image pair are used to obtain the intermediate similarity corresponding to the image pair. The intermediate similarity is used to characterize the similarity obtained by comparing the structure of the image blocks in the image pair.

In one embodiment, the pixel value change trend correlation 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 the image blocks in the image pair, where S is the image block. The similarity between them, σ ₁₂ is the covariance of pixel values between image blocks, σ ₁ and σ ₂ are the variances of the pixel values of the two image blocks in the image pair, and M ₄ is a constant:

Step 310: Obtain the preset degree of attention of each image block to be evaluated, and perform attention processing on the structural similarity corresponding to the image pair where the image block to be evaluated is located based on the preset degree of attention, to obtain the target similarity corresponding to the image pair.

The preset degree of attention refers to the preset degree of attention to the image block to be evaluated. The preset degree of attention may be a weight, for example.

Specifically, for each image block to be evaluated, the server can multiply the preset degree of attention of the image to be evaluated by the structural similarity corresponding to the image pair where the image block to be evaluated is located, to obtain the corresponding image pair of the image block to be evaluated. target similarity.

Step 312: Statistics are made on the target similarity corresponding to each image pair in the image pair set to obtain the structure evaluation information of the image to be evaluated.

Specifically, after obtaining the similarity corresponding to each image pair in the image pair set, the server can perform statistics on these similarities to obtain the statistical similarity. Specifically, the statistics can be to find the average similarity or the median similarity. At least one of them uses statistical similarity as structural evaluation information of the image to be evaluated.

In the above embodiment, by dividing the image to be evaluated and the reference image, the image to be evaluated and the reference image can be calculated based on the image block as a unit, based on the correlation of the pixel value change trend between the image blocks and the pixel value dispersion of each image block. The structural similarity between the image blocks can be obtained, and the similarity can be paid attention to by obtaining the preset attention degree of each image block to be evaluated, and the similarity obtained by the attention processing can be statistically obtained to obtain the structure evaluation information, and the obtained structure evaluation information can be more accurate.

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

Specifically, the server can add 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 the first mean pixel value, and add the pixel values of all the pixels in the reference image and divide by the reference The second average pixel value is obtained from the total number of pixels in the image, and then the brightness evaluation information of the image to be evaluated is determined based on the first average pixel value and the second average pixel value. The brightness evaluation information is used to characterize the brightness similarity between the image to be evaluated and the reference image.

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, μ ₁ is the second pixel value mean, μ ₂ is the second pixel value mean, M ₃ is a constant:

After obtaining the brightness evaluation information, the server can perform a quality evaluation of the image to be evaluated based on the brightness evaluation information, contrast evaluation information, and structure evaluation information to obtain the quality evaluation result corresponding to the image to be evaluated. Refer to the following formula (10):

SITD＝C*L*S (10)

In the above embodiment, the brightness evaluation information is obtained by calculating the mean value of pixel values in the image to be evaluated and the reference image, and the quality evaluation result corresponding to the image to be evaluated is determined by combining the brightness evaluation information, contrast evaluation information and structure evaluation information, and the obtained quality evaluation The results are more accurate.

In a specific embodiment, an image processing method is provided. The specific flow of the image processing method can be seen in Figure 5. The following is explained in conjunction with Figure 5 and taking the method applied to the server in Figure 1 as an example, including the following steps:

1. Obtain the image to be evaluated and the reference image corresponding to the image to be evaluated.

Among them, the image to be evaluated is a night scene image. The reference image is an image obtained by performing a long exposure on a night scene image. Both the image to be evaluated and the reference image are RGB images.

2. Extract the pixel gradient Cg _{1 of each pixel point to be evaluated in the image to be evaluated and the pixel gradient Cg 2 of each reference pixel point in the reference image, based on the pixel gradient Cg 1 of the} image to be evaluated and the pixel gradient Cg of the reference image. ₂ Calculate the gradient similarity Scg of the corresponding pixels between the image to be evaluated and the reference image.

Specifically, the server may refer to the above formulas (1)-(3) to calculate the pixel gradient, and refer to the above formula (4) to calculate the gradient similarity.

3. Extract the chromaticity P ₁ in the first chromaticity channel and the chromaticity Q ₁ in the second chromaticity channel of each pixel point to be evaluated in the image to be evaluated.

4. Extract the chroma P ₂ in the first chroma channel and the chroma Q ₂ in the second chroma channel of each reference pixel point of the reference image respectively.

5. The server calculates chromaticity similarity based on the chromaticity P ₁ and P ₂ of the first chroma channel and the chroma Q ₁ and Q ₂ of the second chroma channel of the corresponding pixels between the image to be evaluated and the reference image. Degree Scc.

Specifically, the server can obtain the pixel values of the R channel, G channel, and B channel of the image to be evaluated, and obtain the pixel values of the R channel, G channel, and B channel of the reference image, and extract the first pixel value by referring to the above formula (5). The chroma value of the chroma channel and the chroma value of the second chroma channel, and refer to the above formula (6) to calculate the chroma similarity Scc.

6. The corresponding pixels between the image to be evaluated and the image to be evaluated are formed into pixel pairs. For each pixel pair, the contrast component is determined based on the gradient similarity and chromaticity similarity of the pixel pair. Based on each pixel pair The contrast components are averaged to obtain the contrast evaluation factor C of the image to be evaluated.

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

7. Calculate the mean pixel value μ ₁ of all the pixels to be evaluated in the image to be evaluated and the mean pixel value μ ₂ of all the reference pixels in the reference image, and calculate the brightness evaluation factor L based on μ ₁ and μ ₂ .

Specifically, the server can calculate the brightness evaluation factor L with reference to the above formula (9).

8. Calculate the variance σ ₁ of the pixel values of all the pixels to be evaluated in the image to be evaluated, and calculate the variance σ ₂ of the pixel values of all the reference pixels in the reference image.

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

10. Based on the variance σ ₁ , variance σ ₂ and covariance σ ₁₂ , calculate the structure evaluation factor S between the image to be evaluated and the reference image.

Specifically, the server can calculate the structure evaluation factor S by referring to the above formula (8).

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

Specifically, the server can calculate the quality assessment result with reference to the above formula (10).

In the above embodiment, considering that night scene images often have large contrast and the image chromaticity changes are relatively obvious, the contrast evaluation factor is obtained by calculating the gradient similarity and chromaticity similarity between the night scene image and the reference image, and combined with the night scene image The brightness evaluation factor and structure evaluation factor are used to obtain the quality evaluation results of the night scene image, and a more rigorous image quality evaluation result can be obtained, which is closer to the subjective evaluation results of the human eye.

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

Based on the same inventive concept, embodiments of the present application also provide an image processing device for implementing the above-mentioned method. The solution to the problem provided by this device is similar to the solution described in the above method. Therefore, for the specific limitations in one or more image processing device embodiments provided below, please refer to the above limitations on the image processing method. I won’t go into details here.

In one embodiment, as shown in Figure 6, an image processing device 600 is provided, including:

The image acquisition module 602 is used to acquire the image to be evaluated and the reference image corresponding to the image to be evaluated;

Information extraction module 604, 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 606 is used to determine the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information, and to determine the gradient similarity between the image to be evaluated and the reference image based on the extracted pixel chromaticity information. Chroma similarity between corresponding pixels;

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;

The structure evaluation module 610 is used to obtain the structure evaluation information of the image to be evaluated; the structure evaluation information is used to characterize the structural similarity between the image to be evaluated and the reference image;

The evaluation result obtaining module 612 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.

The above image processing device extracts the pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image respectively, and determines the gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information, Based on the extracted pixel chromaticity information, determine the chromaticity similarity of the corresponding pixel points between the image to be evaluated and the reference image. Based on the gradient similarity and chromaticity similarity, determine the contrast evaluation information of the image to be evaluated, and obtain the image to be evaluated. The structure evaluation information of The evaluation results are closer to the subjective evaluation results of the human eye, improving the accuracy of the image evaluation results.

In one embodiment, the similarity calculation module is also used to calculate the horizontal gradient and vertical gradient of the pixel to be evaluated for each pixel to be evaluated in the image to be evaluated, and determine the gradient of the pixel to be evaluated based on the horizontal gradient and the vertical gradient. The first target gradient; for each reference pixel point of the reference image, calculate the horizontal gradient and vertical gradient of the reference pixel point, and determine the second target gradient of the reference pixel point based on the horizontal gradient and vertical gradient; based on the relationship between the image to be evaluated and the reference image The first target gradient and the second target gradient of the corresponding pixels between the images are determined to determine the gradient similarity of the corresponding pixels between the image to be evaluated and the reference image.

In one embodiment, the similarity calculation module is also used to obtain, 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, the green channel, and the blue channel respectively, based on the obtained pixels. Calculate the first chromaticity value to be evaluated in the first chromaticity channel of the pixel point to be evaluated and the second chromaticity value to be evaluated in the second chromaticity channel; for each reference pixel point of the reference image, obtain the reference pixel point Calculate the first reference chromaticity value of the reference pixel point in the first chromaticity channel and the second reference chromaticity value in the second chromaticity channel based on the pixel values in the red channel, green channel and blue channel respectively. value; based on the first chromaticity value to be evaluated and the first reference chromaticity value of the corresponding pixel point between the image to be evaluated and the reference image, determine the first chromaticity similarity of the corresponding pixel point between the image to be evaluated and the reference image degree component; based on the second chromaticity value to be evaluated and the second reference chromaticity value of the corresponding pixel point between the image to be evaluated and the reference image, determine the second chromaticity of the corresponding pixel point between the image to be evaluated and the reference image Similarity component; based on the first chromaticity similarity component and the second chromaticity similarity component, determine the chromaticity similarity of the corresponding pixel points between the image to be evaluated and the reference image.

In one embodiment, the contrast evaluation module is also used to form a pixel pair between the image to be evaluated and the corresponding pixels between the image to be evaluated; for each pixel pair, based on the gradient similarity and chromaticity of the pixel pair The similarity determines the contrast component; the contrast component is positively correlated with the gradient similarity of the pixel pair, and is positively correlated with the chromaticity similarity of the pixel pair; based on the mean calculation of the contrast component of each pixel pair, the contrast of the image to be evaluated is obtained Evaluate information.

In one embodiment, the structure evaluation module is also used to divide the image to be evaluated and the reference image respectively to obtain multiple reference image blocks corresponding to the reference image and multiple image blocks to be evaluated corresponding to the image to be evaluated; Blocks and reference image blocks that have an image position correspondence relationship with the image blocks to be evaluated form an image pair to obtain a set of image pairs; for the image pairs in the image pair set, calculate the pixel value change trend correlation between the image blocks in the image pair. , and calculate the pixel value dispersion corresponding to each image block in the image pair; obtain the intermediate similarity corresponding to the image pair based on the pixel value change trend correlation and the pixel value dispersion corresponding to each image block in the image pair; obtain each image to be evaluated Based on the preset attention degree of the block, the intermediate similarity corresponding to the image pair where the image block to be evaluated is located is focused on to obtain the target similarity corresponding to the image pair; the target similarity corresponding to each image pair in the image pair set is obtained Perform statistics to obtain the structural evaluation information of the image to be evaluated.

In one embodiment, the above device is also used for: a brightness evaluation module, used to calculate the first average pixel value of each pixel point of the image to be evaluated, and calculate the second average pixel value of each pixel point of the reference image; based on the first pixel The mean value of the first pixel value and the mean value of the second pixel value determine the brightness evaluation information of the image to be evaluated. The brightness evaluation information is positively correlated with the product of the mean value of the first pixel value and the mean value of the second pixel value, and the mean value of the first pixel value and the mean value of the second pixel value are The sum of squares is negatively correlated; the evaluation result acquisition module is also used 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.

Each module in the above image processing device can be implemented in whole or in part by software, hardware and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in Figure 7 . The computer device includes a processor, a memory, an input/output interface (Input/Output, referred to as I/O), and a communication interface. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The computer device's database is used to store image data. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program implements an image processing method when executed by the processor.

Those skilled in the art can understand that the structure shown in Figure 7 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.

An embodiment of the present application also provides a computer-readable storage medium. One or more non-volatile computer-readable storage media containing computer-executable instructions that, when executed by one or more processors, cause the processors to perform the steps of the image processing method.

Embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, causes the computer to execute an image processing method.

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

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may 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 memory (ReRAM), magnetic variable memory (Magnetoresistive Random) Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

The technical features of the above embodiments can be combined in any way. To simplify the description, 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, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (10)

1. An image processing method, characterized by comprising: Obtain an image to be evaluated and a reference image corresponding to the image to be evaluated; Extract pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image respectively; The gradient similarity of the corresponding pixel points between the image to be evaluated and the reference image is determined based on the extracted pixel gradient information, and the gradient similarity between the image to be evaluated and the reference image is determined based on the extracted pixel chromaticity information. Chroma similarity between corresponding pixels; Based on the gradient similarity and the chromaticity similarity, determine the contrast evaluation information of the image to be evaluated; Obtain the structural evaluation information of the image to be evaluated; the structural evaluation information is used to characterize the structural similarity between the image to be evaluated and the reference image; Based on the contrast evaluation information and the structure evaluation information, a quality evaluation result corresponding to the image to be evaluated is determined. 2. The method of claim 1, wherein determining the gradient similarity of corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information includes: For each pixel point to be evaluated in the image to be evaluated, calculate the horizontal gradient and vertical gradient of the pixel point to be evaluated, and determine the first target gradient of the pixel point to be evaluated based on the horizontal gradient and the vertical gradient. ; For each reference pixel point of the reference image, calculate the horizontal gradient and vertical gradient of the reference pixel point, and determine the second target gradient of the reference pixel point based on the horizontal gradient and the vertical gradient; Based on the first target gradient and the second target gradient of the corresponding pixel point between the image to be evaluated and the reference image, a gradient similarity of the corresponding pixel point between the image to be evaluated and the reference image is determined. 3. The method of claim 1, wherein determining the chromaticity similarity of corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel chromaticity information includes: For each pixel point to be evaluated in the image to be evaluated, the pixel values of the pixel point to be evaluated in the red channel, the green channel and the blue channel are obtained, and the pixel value of the pixel point to be evaluated is calculated based on the obtained pixel values. A first chromaticity value to be evaluated in one chromaticity channel and a second chromaticity value to be evaluated in a second chromaticity channel; For each reference pixel point of the reference image, obtain the pixel values of the reference pixel point in the red channel, green channel and blue channel respectively, and calculate the first chroma channel of the reference pixel point based on the obtained pixel values. a first reference chromaticity value and a second reference chromaticity value in the second chromaticity channel; Determine the corresponding pixel point 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 the corresponding pixel point between the image to be evaluated and the reference image The first chroma similarity component of Determine the corresponding pixel point 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 the corresponding pixel point between the image to be evaluated and the reference image The second chromaticity similarity component; Based on the first chromaticity similarity component and the second chromaticity similarity component, chromaticity similarity of corresponding pixel points between the image to be evaluated and the reference image is determined. 4. The method of claim 1, wherein determining the contrast evaluation information of the image to be evaluated based on the gradient similarity and the chromaticity similarity includes: The corresponding pixel points between the image to be evaluated and the image to be evaluated are formed into a pixel point pair; 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 is positively correlated with the pixel pair The chromaticity similarity is positively correlated; An average value is calculated based on the contrast component of each pixel pair to obtain the contrast evaluation information of the image to be evaluated. 5. The method according to claim 1, characterized in that said obtaining the structural evaluation information of the image to be evaluated includes: Divide the image to be evaluated and the reference image respectively to obtain a plurality of reference image blocks corresponding to the reference image and a plurality of 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 corresponding relationship with the image block to be evaluated are formed into an image pair to obtain an image pair set; For the image pairs in the image pair set, calculate the pixel value change trend correlation between the image blocks in the image pair, and calculate the pixel value dispersion corresponding to each image block in the image pair; Obtain the intermediate similarity corresponding to the image pair based on the pixel value change trend correlation and the pixel value dispersion corresponding to each image block in the image pair; Obtain the preset degree of attention of each image block to be evaluated, and perform attention processing on the intermediate similarity corresponding to the image pair where the image block to be evaluated is located based on the preset degree of attention, to obtain the target similarity corresponding to the image pair; Statistics are performed on the target similarity corresponding to each image pair in the image pair set to obtain the structure evaluation information of the image to be evaluated. 6. The method according to any one of claims 1 to 5, characterized in that the method further includes: Calculate the first average pixel value of each pixel point of the image to be evaluated, and calculate the second average pixel value of each pixel point of the reference image; Based on the first average pixel value and the second average pixel value, brightness evaluation information of the image to be evaluated is determined, and the product of the brightness evaluation information and the first average pixel value and the second average pixel value is positive. Correlated, and the sum of the squares of the first pixel value mean and the second pixel value mean is negatively correlated; Determining the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information includes: Based on the brightness evaluation information, the contrast evaluation information and the structure evaluation information, a quality evaluation result corresponding to the image to be evaluated is determined. 7. An image processing device, characterized in that it includes: An image acquisition module, used to acquire an image to be evaluated and a reference image corresponding to the image to be evaluated; An information extraction module, configured to extract pixel gradient information and pixel chromaticity information of the image to be evaluated and the reference image respectively; A similarity calculation module, configured to determine the gradient similarity of corresponding pixel points between the image to be evaluated and the reference image based on the extracted pixel gradient information, and determine the gradient similarity to be evaluated based on the extracted pixel chromaticity information. The chromaticity similarity of corresponding pixels between the image and the reference image; A contrast evaluation module, configured to determine the contrast evaluation information of the image to be evaluated based on the gradient similarity and chromaticity similarity; A structure evaluation module, used to obtain the structure evaluation information of the image to be evaluated; the structure evaluation information is used to characterize the structural similarity between the image to be evaluated and the reference image; An evaluation result obtaining module is configured to determine the quality evaluation result corresponding to the image to be evaluated based on the contrast evaluation information and the structure evaluation information. 8. A computer device, including a memory and a processor, and a computer program is stored in the memory, characterized in that, when the computer program is executed by the processor, the processor causes the processor to execute claims 1 to 6 The image processing method described in any one of the steps. 9. A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the image processing method according to any one of claims 1 to 6 are implemented. 10. A computer program product, comprising a computer program, characterized in that when the computer program is executed by a processor, the steps of the image processing method according to any one of claims 1 to 6 are implemented.