A quality evaluation method for underwater enhanced images

Abstract

The present invention belongs to the field of image processing technology and discloses a method for evaluating the quality of underwater enhanced images, comprising the following steps: S1, calculating a local normalized map for an input enhanced underwater image to measure the naturalness of the enhanced underwater image; S2, calculating a gradient intensity map for the input enhanced underwater image to measure the blurriness of the enhanced underwater image; S3, performing a convolution operation on the input enhanced underwater image to obtain a feature map, inputting the map into a channel spatial attention module to obtain a purified feature map, and measuring the degree of color cast and local distortion of the enhanced underwater image; S4, concatenating the feature maps extracted in S1-S3, inputting the map into a channel attention module, and passing the map through a multi-layer perceptron to obtain an image quality score; and S5, using a trained model to predict the quality of the image to be evaluated. The present invention does not require reference to the original image, can achieve high prediction performance, and has a fast running speed, meeting the application requirements of underwater operations.

Description

Technical Field

[0001] The invention belongs to the technical field of image processing and relates to a quality evaluation method for underwater enhanced images. Background Art

[0002] Underwater imaging is widely used in underwater operations and is a crucial component of these operations. Due to the refraction and scattering of light by water, underwater image quality is low, often exhibiting issues such as a blue-green cast, blurring, and low contrast, failing to meet the demands of underwater operations. Therefore, acquired underwater images often require appropriate enhancement to improve their quality and provide accurate information for underwater operations. However, due to the lack of accurate quality metrics, existing underwater image enhancement methods remain largely inefficient and ineffective in improving underwater image quality.

[0003] In the area of ​​natural image quality assessment, some researchers have proposed the structural similarity method (SSIM), others have used changes in visual saliency features to evaluate image quality, others have used image gradient intensity features to evaluate image quality, and others have proposed statistical modeling of image structure, naturalness, and perception to construct an unsupervised quality assessment method. In the area of ​​underwater image quality assessment, some researchers have proposed an underwater image quality assessment metric that measures image color, contrast, and saturation, and then uses a linear weighted sum of these three to evaluate underwater image quality. Some researchers have proposed an underwater image quality measurement method that calculates image color, blur, and contrast, and then uses a linear weighted sum to evaluate underwater image quality. Some researchers have proposed constructing underwater image quality assessment models, such as those based on channel spatial attention and the Transformer. Other models measure the naturalness, sharpness, and structure of enhanced underwater images.

[0004] Based on this, the present invention proposes a quality evaluation method for underwater enhanced images, which effectively guides the enhancement process of underwater images, thereby improving the efficiency of underwater operations. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention proposes a quality evaluation method for underwater enhanced images. Based on a deep neural network, the naturalness, blurriness, color cast, and local distortion of the underwater enhanced images are characterized, and an image quality evaluation model is trained using an end-to-end training method to accurately judge the quality of the underwater enhanced images.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A method for evaluating the quality of underwater enhanced images comprises the following steps:

[0008] S1. Calculate the local normalized map:

[0009] The local normalized map is calculated for the input enhanced underwater image, and then the local normalized map is input into N cascaded residual blocks for feature extraction to obtain the feature map F N , measures the naturalness of underwater enhanced images;

[0010] S2. Calculate the gradient intensity map:

[0011] The gradient intensity map is calculated for the input enhanced underwater image, and then the gradient intensity map is input into N cascaded residual blocks for feature extraction to obtain the feature map F B , measures the blurriness of underwater enhanced images;

[0012] S3. Calculate feature map:

[0013] The input enhanced underwater image is convolved, and the feature map is input into the channel space attention module to obtain the purified feature map F", which measures the degree of color deviation and local distortion of the underwater enhanced image.

[0014] S4. Feature stitching:

[0015] The feature maps extracted from S1-S3 are spliced ​​together to fuse the naturalness, blur, color cast, and local distortion features of the underwater enhanced image. The images are input into the channel attention module and passed through the multi-layer perceptron to obtain the image quality score.

[0016] S5. Image quality prediction:

[0017] Through S1-S4, a quality evaluation model for underwater enhanced images is constructed. The model consists of three branches: naturalness measurement branch, blur measurement branch, and color deviation and local distortion measurement branch. The features output by the three branches are concatenated, channel attention module and multi-layer perceptron to output the image quality score. End-to-end training is performed, and the trained model is used to predict the quality of the image to be evaluated.

[0018] Furthermore, the step S1 specifically includes: decomposing the input underwater enhanced image into three channels of red, green, and blue, represented as R, G, and B respectively, and then converting it into a grayscale image, represented as:

[0019]

[0020] in, Represents the grayscale image corresponding to the underwater image, and calculates Locally normalized image of :

[0021]

[0022] in, Represents a local normalized image, (i, j) represents the coordinate position of the pixel, μ(i, j) and σ(i, j) represent the local mean and variance, which are calculated as follows:

[0023]

[0024] Among them, s, t represent the offset of the coordinates, and S, T represent the maximum value of the offset;

[0025] Then, Input to the residual block for feature extraction to obtain the feature map F N , expressed as:

[0026]

[0027] Among them, ResBlock() represents N cascaded residual blocks.

[0028] Furthermore, in step S2, the specific method is as follows: using the Sobel operator to perform a convolution operation on the grayscale image to obtain horizontal and vertical gradient maps, then calculating the gradient intensity map, inputting the gradient intensity map into N cascaded residual blocks to obtain a feature map to measure the blur degree of the underwater enhanced image;

[0029] The step S2 specifically includes: performing convolution operations on the image using the horizontal and vertical Sobel operators respectively:

[0030]

[0031] Among them, G x and G y Represent the horizontal and vertical gradient maps respectively, * represents the convolution operation, and then calculate the gradient intensity map:

[0032]

[0033] Among them, GM represents the gradient strength map; GM is input into N cascaded residual blocks to obtain the feature map F B :

[0034] F B =ResBlock(GM).

[0035] Furthermore, the specific method of step S3 is as follows: performing a convolution operation on the input underwater enhanced image to obtain a feature map, and then inputting the feature map into the channel space attention module, using the channel space attention mechanism to adjust and optimize the input feature map to obtain a purified feature map, and measure the color cast and local distortion of the underwater image;

[0036] Step S3 specifically includes: performing a convolution operation on the input underwater image using a 3×3 convolution kernel to obtain a feature map F:

[0037] F=conv 3×3 (I) Among them, conv 3×3 (·) represents the convolution operation, and the convolution kernel size is 3×3. Then F is input into the channel space attention module to purify the feature map, which is expressed as:

[0038]

[0039] Among them, the channel spatial attention module includes the channel attention module and the spatial attention module. F' represents the feature map adjusted by the channel attention module, and F" represents the feature map adjusted by the spatial attention module. Represents element-wise multiplication operation, M c represents channel attention, M S represents spatial attention, M c (F) and M s (F) is calculated as follows:

[0040] M c (F)=σ(MLP(AvgPool(F))+MLP(MaxPool(F)))

[0041] M s (F)=σ(conv 7×7 [AvgPool(·);MaxPool(·)])

[0042] Among them, MLP represents multi-layer perceptron, AvgPool(·) and MaxPool(·) represent average pooling and maximum pooling, conv 7×7 (·) represents the convolution operation, the convolution kernel size is 7×7, and σ(·) represents the sigmoid function. Furthermore, in step S4, the feature maps extracted from S1-S3 are concatenated and then input into the channel attention module. The channel attention mechanism assigns different weights to different feature maps for feature map optimization. The obtained feature maps are then input into the multi-layer perceptron, which outputs the image quality score.

[0043] Specifically, the feature maps extracted from S1-S3 are spliced ​​to obtain the feature map F c :

[0044] F c =concat(F N ,F B ,F”)

[0045] Among them, concat(·) represents the feature map concatenation operation, which converts F cInput channel attention module to optimize feature map and obtain feature map F f :

[0046]

[0047] F f Input is a multilayer perceptron, which outputs an image quality score:

[0048] q=MLP(F f )

[0049] Where q represents the image quality score.

[0050] Furthermore, the underwater enhanced image quality assessment model constructed in S1-S4 is end-to-end trained in step S5, and the quality of the image to be evaluated is predicted using the trained model. The specific method is as follows: a number of underwater enhanced images with subjective quality marks are selected, and the quality scores of these images are predicted using the image quality assessment model constructed in S1-S4. The model is end-to-end trained using mean square error. After the training is completed, the quality of the underwater enhanced image to be evaluated is predicted;

[0051] The mean square error is defined as:

[0052]

[0053] Among them, q i is the quality score of the i-th image predicted by the model, s i represents the subjective quality score of the i-th image, and the Adam algorithm is used to optimize the model;

[0054] After the training is completed, for an underwater enhanced image I to be evaluated, it is input into the trained model, and the model outputs its quality score, which is expressed as:

[0055] q=M(I)

[0056] Where M(·) represents the trained image quality assessment model, and q represents the quality score of I.

[0057] Compared with the prior art, the present invention has the following advantages:

[0058] The underwater enhanced image quality assessment method described in the present invention enables accurate judgment of the quality of underwater enhanced images, achieving prediction performance superior to existing technologies. The present invention calculates a local normalized image of the image to measure the naturalness of the underwater enhanced image, and uses residual learning to learn deep-level naturalness perception features, which more accurately measures image quality than traditional statistics-based methods (existing methods do not consider the naturalness measurement of images, and the present invention is the first to propose a naturalness measurement in the quality assessment of underwater enhanced images). Similarly, the gradient intensity image is calculated, and the deep-level blur characteristics are learned using residual learning to more accurately measure the blur level of the image.

[0059] In the quality evaluation of underwater enhanced images, this paper proposes for the first time to use the channel spatial attention mechanism to measure the degree of color deviation and local distortion of underwater enhanced images. By fusing the naturalness features, blur features, color deviation features and local distortion features of underwater enhanced images, accurate measurement of the quality of underwater enhanced images is achieved.

[0060] In addition, the present invention does not require reference to original underwater images, and the method runs quickly, meeting the application requirements of underwater operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0062] Figure 1 This is a model structure diagram of the present invention;

[0063] Figure 2 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0064] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0065] The embodiments of the present invention respectively characterize the naturalness, blur, channel, and local distortion of underwater enhanced images, use a multi-layer perceptron for feature fusion and quality score prediction, and train an image quality assessment model using an end-to-end training method. After training, the model is used to accurately judge the quality of underwater enhanced images.

[0066] like Figure 1 、 Figure 2 As shown, an embodiment of the present invention provides a method for evaluating the quality of underwater enhanced images, the method comprising:

[0067] S1. Calculate the local normalized map:

[0068] The local normalized map is calculated for the input enhanced underwater image, and then the local normalized map is input into N (for example, 5) cascaded residual blocks for feature extraction to obtain the feature map F N , measures the naturalness of underwater enhanced images.

[0069] S2. Calculate the gradient intensity map:

[0070] The gradient intensity map is calculated for the input enhanced underwater image, and then the gradient intensity map is input into N (for example, 5) cascaded residual blocks for feature extraction to obtain the feature map F B , measure the blur of underwater enhanced image; S3, calculate feature map:

[0071] The input enhanced underwater image is convolved, and the feature map is input into the channel space attention module to obtain the purified feature map F", which measures the degree of color deviation and local distortion of the underwater enhanced image.

[0072] S4. Feature stitching:

[0073] The feature maps extracted from S1-S3 are spliced ​​together to fuse the naturalness, blur, color cast, and local distortion features of the underwater enhanced image. The images are input into the channel attention module and passed through the multi-layer perceptron to obtain the image quality score.

[0074] S5. Image quality prediction:

[0075] Through S1-S4, a quality evaluation model for underwater enhanced images is constructed. The model consists of three branches: naturalness measurement branch, blur measurement branch, and color deviation and local distortion measurement branch. The features output by the three branches are concatenated, channel attention module and multi-layer perceptron to output the image quality score. End-to-end training is performed, and the trained model is used to predict the quality of the image to be evaluated.

[0076] This method does not require reference to the original image and can achieve high prediction performance while running fast, meeting the application requirements of underwater operations.

[0077] In one embodiment, the specific implementation process and details of the above-mentioned underwater enhanced image quality assessment method are as follows:

[0078] Specifically, S1 decomposes the input underwater enhanced image into three channels: red, green, and blue, represented as R, G, and B respectively, and then converts it into a grayscale image, represented as:

[0079]

[0080] in, Represents the grayscale image corresponding to the underwater image, and calculates Locally normalized image of :

[0081]

[0082] in, Represents a local normalized image, (i, j) represents the coordinate position of the pixel, μ(i, j) and σ(i, j) represent the local mean and variance, which are calculated as follows:

[0083]

[0084] Where s and t represent the offset of the coordinates, S and T represent the maximum value of the offset, and S and T are set to 5.

[0085] Then, Input to the residual block for feature extraction to obtain the feature map F N , expressed as:

[0086]

[0087] Among them, F N Represents the feature map output by the residual block, and ResBlock() represents the residual block.

[0088] The present invention proposes a naturalness metric for the first time in the quality evaluation of underwater enhanced images. Existing methods do not consider the naturalness metric of images. How to accurately measure the naturalness of images is one of the problems solved by the present invention. The present invention proposes to achieve this by using residual learning.

[0089] Specifically, S2 uses the Sobel operator to perform convolution operations on the grayscale image to obtain horizontal and vertical gradient maps, and then calculates the gradient intensity map. The gradient intensity map is input into N cascaded residual blocks to obtain a feature map to measure the blur degree of the underwater enhanced image.

[0090] Specifically, the horizontal and vertical Sobel operators are used to perform convolution operations on the input underwater enhanced image respectively:

[0091] Among them, G x and G y Represent the horizontal and vertical gradient maps respectively, * represents the convolution operation, and then calculate the gradient intensity map:

[0092]

[0093] Among them, GM represents the gradient strength map. GM is input into 5 cascaded residual blocks to obtain the feature map F B :

[0094] F B =ResBlock(GM)

[0095] Among them, F B is the obtained feature map.

[0096] Specifically, S3 performs a convolution operation on the input underwater enhanced image to obtain a feature map, and then inputs the feature map into the channel space attention module. The channel space attention mechanism is used to adjust and optimize the input feature map to obtain a purified feature map to measure the degree of color deviation and local distortion of the underwater image.

[0097] As an embodiment, a convolution operation is performed on the input underwater enhanced image using a 3×3 convolution kernel to obtain a feature map F:

[0098] F=conv 3×3 (I)

[0099] Among them, conv 3×3 (·) represents the convolution operation, and the convolution kernel size is 3×3. Then F is input into the channel space attention module to purify the feature map:

[0100]

[0101] Among them, the channel spatial attention module includes the channel attention module and the spatial attention module. F' represents the feature map adjusted by the channel attention module, and F" represents the feature map adjusted by the spatial attention module. Represents element-wise multiplication operation, M c represents channel attention, M S represents spatial attention, M c (F) and M s (F) is calculated as follows:

[0102] M c (F)=σ(MLP(AvgPool(F))+MLP(MaxPool(F)))

[0103] M s (F)=σ(conv 7×7 [AvgPool(·);MaxPool(·)])

[0104] Among them, MLP represents multi-layer perceptron, AvgPool(·) and MaxPool(·) represent average pooling and maximum pooling, conv 7×7 (·) represents the convolution operation, the convolution kernel size is 7×7, and σ(·) represents the sigmoid function, which is defined as:

[0105]

[0106] Here, x is the input variable of the function.

[0107] It should be noted that in the underwater enhanced image quality evaluation, the present invention uses the channel space attention mechanism for the first time to measure the degree of color deviation and local distortion of the image.

[0108] Specifically, step S4 splices the feature maps extracted by S1-S3 together, then inputs them into the channel attention module, assigns different weights to different feature maps through the channel attention mechanism to optimize the feature maps, inputs the obtained feature maps into the multi-layer perceptron, and outputs the image quality score.

[0109] This step accurately measures the quality of underwater enhanced images by concatenating feature maps and integrating their naturalness, blur, color cast, and local distortion characteristics. After feature concatenation, a channel attention mechanism is introduced to assign different weights to different feature maps, improving the accuracy of image quality assessment.

[0110] Specifically, the feature maps extracted in the above steps are spliced ​​to obtain the feature map F c :

[0111] F c =concat(F N ,F B ,F”)

[0112] Among them, concat(·) represents the feature map concatenation operation, which converts F c Input channel attention module to optimize feature map and obtain feature map F f :

[0113]

[0114] F f Input is a multilayer perceptron, which outputs an image quality score:

[0115] q=MLP(F f )

[0116] Where q represents the image quality score.

[0117] Step S5: Perform end-to-end training on the underwater enhanced image quality evaluation model constructed in S1-S4, and use the trained model to predict the image quality to be evaluated.

[0118] Specifically, 1,000 underwater enhanced images with subjective quality labels are selected, and the image quality assessment model constructed in the above steps is used to predict the quality scores of these 1,000 images. The model is trained end-to-end using the mean square error, which is defined as:

[0119]

[0120] Among them, q i is the quality score of the i-th image predicted by the model, s i represents the subjective quality score of the i-th image. The model is optimized using the Adam algorithm, and the learning rate is set to 1e -4 , the number of samples used for each iteration training is set to 32.

[0121] After the training is completed, for an underwater enhanced image I to be evaluated, it is input into the trained model, and the model outputs its quality score, which is expressed as:

[0122] q=M(I)

[0123] Where M(·) represents the trained image quality assessment model, and q represents the quality score of I.

[0124] In a specific embodiment of the present invention, the performance of the present invention is tested on the SOTA library (the paper “Generation-based joint luminance-chrominance learning for underwater image quality assessment” published by Wang et al. in “IEEE Transactions on Circuits and Systems for Video Technology”, Vol. 33, No. 3, pp. 1123 to 1139). The performance of the algorithm is measured using three indicators: the Spearman rank correlation coefficient (SRCC), the Pearson linear correlation coefficient (PLCC), and the root mean square error (RMSE). The experimental results are shown in Table 1, where higher SRCC and PLCC and lower RMSE indicate better prediction performance.

[0125] Table 1 Performance comparison on SOTA database

[0126] Performance indicators UCIQE UIQM CCF FDUM GLCQE The present invention SRCC 0.1425 0.1453 0.4337 0.0425 0.7996 0.8484 PLCC 0.4573 0.1044 0.4840 0.2495 0.8377 0.8766 RMSE 11.2807 12.6184 11.0895 12.2805 6.9278 6.1051

[0127] Table 1 compares the latest underwater image quality evaluation methods, including UCIQE, UIQM, CCF, FDUM, and GLCQE. It can be seen that the present invention achieves higher prediction performance than similar methods, proving the effectiveness and superiority of the present invention.

[0128] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various variations or modifications within the scope of the claims, which do not affect the essence of the present invention.

Claims

1. A quality evaluation method for underwater enhanced images, characterized in that: The following steps are involved: S1. Calculate the local normalized map: The local normalized map is calculated for the input enhanced underwater image, and then the local normalized map is input into N cascaded residual blocks for feature extraction to obtain the feature map F N , measures the naturalness of underwater enhanced images; S2. Calculate the gradient intensity map: The gradient intensity map is calculated for the input enhanced underwater image, and then the gradient intensity map is input into N cascaded residual blocks for feature extraction to obtain the feature map F B , measures the blurriness of underwater enhanced images; S3. Calculate feature map: The input enhanced underwater image is convolved, and the feature map is input into the channel space attention module to obtain the purified feature map F", which measures the degree of color deviation and local distortion of the underwater enhanced image. S4. Feature stitching: The feature maps extracted from S1-S3 are spliced ​​together to fuse the naturalness, blur, color cast, and local distortion features of the underwater enhanced image. The images are input into the channel attention module and passed through the multi-layer perceptron to obtain the image quality score. S5. Image quality prediction: Through S1-S4, a quality evaluation model for underwater enhanced images is constructed. The model consists of three branches: naturalness measurement branch, blur measurement branch, and color deviation and local distortion measurement branch. The features output by the three branches are concatenated, channel attention module and multi-layer perceptron to output the image quality score. End-to-end training is performed, and the trained model is used to predict the quality of the image to be evaluated.

2. The method for evaluating underwater enhanced image quality according to claim 1, wherein: The step S1 specifically includes: decomposing the input underwater enhanced image into three channels of red, green and blue, represented as R, G and B respectively, and then converting it into a grayscale image, represented as: in, Represents the grayscale image corresponding to the underwater image, and calculates Locally normalized image of : in, Represents a local normalized image, (i, j) represents the coordinate position of the pixel, μ(i, j) and σ(i, j) represent the local mean and variance, which are calculated as follows: Among them, s, t represent the offset of the coordinates, and S, T represent the maximum value of the offset; Then, Input to the residual block for feature extraction to obtain the feature map F N , expressed as: Among them, ResBlock() represents N cascaded residual blocks.

3. The method for evaluating underwater enhanced image quality according to claim 1, wherein: Step S2: The specific method is as follows: Use the Sobel operator to perform a convolution operation on the grayscale image to obtain horizontal and vertical gradient maps, then calculate the gradient intensity map, input the gradient intensity map into N cascaded residual blocks to obtain a feature map to measure the blur degree of the underwater enhanced image; The step S2 specifically includes: performing convolution operations on the image using the horizontal and vertical Sobel operators respectively: Among them, G x and G y Represent the horizontal and vertical gradient maps respectively, * represents the convolution operation, and then calculate the gradient intensity map: Among them, GM represents the gradient strength map; GM is input into N cascaded residual blocks to obtain the feature map F B : F B =ResBlock(GM)。 4. The method for evaluating underwater enhanced image quality according to claim 1, wherein: The specific method of step S3 is as follows: a convolution operation is performed on the input underwater enhanced image to obtain a feature map, and then the feature map is input into the channel space attention module. The channel space attention mechanism is used to adjust and optimize the input feature map to obtain a purified feature map, and the color cast and local distortion of the underwater image are measured; Step S3 specifically includes: performing a convolution operation on the input underwater image using a 3×3 convolution kernel to obtain a feature map F: F=conv 3×3 (I) Among them, conv 3×3 (·) represents the convolution operation, and the convolution kernel size is 3×3. Then F is input into the channel space attention module to purify the feature map, which is expressed as: Among them, the channel spatial attention module includes the channel attention module and the spatial attention module. F' represents the feature map adjusted by the channel attention module, and F" represents the feature map adjusted by the spatial attention module. represents the element-wise multiplication operation, Mc represents the channel attention, MS represents the spatial attention, and M c (F) and M s (F) is calculated as follows: M c (F)=σ(MLP(AvgPool(F))+MLP(MaxPool(F))) M s (F)=σ(conv 7×7 [AvgPool(·);MaxPool(·)]) Among them, MLP represents multi-layer perceptron, AvgPool(·) and MaxPool(·) represent average pooling and maximum pooling, conv 7×7 (·) represents the convolution operation, the convolution kernel size is 7×7, and σ(·) represents the sigmoid function.

5. The method for evaluating underwater enhanced image quality according to claim 1, wherein: In step S4, the feature maps extracted by S1-S3 are spliced ​​together and then input into the channel attention module. Different feature maps are assigned different weights through the channel attention mechanism to optimize the feature maps. The obtained feature maps are input into the multi-layer perceptron to output the image quality score. Specifically, the feature maps extracted from S1-S3 are spliced ​​to obtain the feature map F c : F c =concat(F N ,F B ,F”) Among them, concat(·) represents the feature map concatenation operation, which converts F c Input channel attention module to optimize feature map and obtain feature map F f : F f Input is a multilayer perceptron, which outputs an image quality score: q=MLP(F f ) Where q represents the image quality score.

6. The method for evaluating underwater enhanced image quality according to claim 1, wherein: In step S5, the underwater enhanced image quality assessment model constructed in steps S1-S4 is end-to-end trained, and the quality of the image to be evaluated is predicted using the trained model. The specific method is as follows: a number of underwater enhanced images with subjective quality marks are selected, and the quality scores of these images are predicted using the image quality assessment model constructed in steps S1-S4. The model is end-to-end trained using mean square error. After the training is completed, the quality of the underwater enhanced image to be evaluated is predicted. The mean square error is defined as: Among them, q i is the quality score of the i-th image predicted by the model, s i represents the subjective quality score of the i-th image, and the Adam algorithm is used to optimize the model; After the training is completed, for an underwater enhanced image I to be evaluated, it is input into the trained model, and the model outputs its quality score, which is expressed as: q=M(I) Where M(·) represents the trained image quality assessment model, and q represents the quality score of image I.

Images