Image processing method, device, computer equipment and storage medium

Abstract

The present application provides an image processing method, device, computer equipment and storage medium. The method obtains a target image to be evaluated, and divides the target image into a first area and a second area according to the pixel brightness value of the target image; then extracts first image feature information and second image feature information from the first area and the second area respectively, wherein the image feature information at least includes grayscale feature information, image detail information and color feature information; finally, the evaluation result of the target image is determined according to the first image feature information and the second image feature information. The image is segmented according to the pixel brightness information in the target image, and then the image feature information is extracted separately for the areas with different brightness in the target image, so as to reduce the influence of the brightness in the image on the acquisition of the image feature information in the target image, and improve the representation ability of the image feature information on the information in the target image, so as to improve the accuracy of the subsequent evaluation of the target image.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to an image processing method, apparatus, computer equipment, and computer-readable storage medium (storage medium for short). Background Art

[0002] When a camera device (such as a digital camera) is collecting images, it often measures the light of the shooting environment, and selectively adjusts the brightness of different areas in the collected image based on the ambient light ratio information obtained from the light measurement results, so as to obtain a high dynamic range image. However, the adjustment of the image brightness often leads to a decrease in image quality, such as a decrease in clarity, color deviation, etc. Therefore, it is necessary to evaluate the high dynamic range image after brightness adjustment, and then fine-tune the aforementioned brightness adjustment process based on the evaluation results to improve image quality such as image clarity. However, existing evaluation methods often directly evaluate images based on various image quality parameters, and the accuracy is low. Summary of the invention

[0003] Based on this, it is necessary to provide an image processing method, apparatus, computer equipment and storage medium to address the above technical problems, so as to improve the accuracy of target image evaluation.

[0004] In a first aspect, the present application provides an image processing method, the method comprising:

[0005] Obtain the target image to be evaluated;

[0006] According to the pixel brightness values ​​of the target image, the target image is divided into a first area and a second area;

[0007] Extracting first image feature information and second image feature information from the first area and the second area respectively; wherein the image feature information includes at least grayscale feature information, image detail information and color feature information;

[0008] An evaluation result of the target image is determined according to the first image feature information and the second image feature information.

[0009] In some embodiments of the present application, the step of obtaining a target image to be evaluated includes:

[0010] Acquire an image to be evaluated, and divide the pre-processed image into a first area and a second area according to pixel brightness values ​​of the image to be evaluated;

[0011] Obtaining a first area average brightness value of the first area and a second area average brightness value of the second area;

[0012] Obtaining an image light ratio of the image to be evaluated according to a ratio of a brightness mean value of the second area to a brightness mean value of the first area;

[0013] If the image light ratio is greater than a preset light ratio threshold, the image to be evaluated is determined as a target image.

[0014] In some embodiments of the present application, segmenting the target image into a first area and a second area according to pixel brightness values ​​of the target image includes:

[0015] Obtaining the grayscale value corresponding to each pixel in the target image;

[0016] According to the grayscale segmentation threshold and the grayscale value of each pixel, determine a first pixel whose grayscale value is greater than the grayscale segmentation threshold and a second pixel whose grayscale value is not greater than the grayscale segmentation threshold;

[0017] The area where the first pixel point is located is determined as a first area, and the area where the second pixel point is located is determined as a second area.

[0018] In some embodiments of the present application, extracting first image feature information and second image feature information from the first area and the second area respectively includes:

[0019] Obtaining a maximum pixel brightness and a minimum pixel brightness in the target image;

[0020] Acquire a first normalized parameter of the first area and a second normalized parameter of the second area according to a ratio between the maximum pixel brightness and the minimum pixel brightness;

[0021] Based on the first normalization parameter, normalize the first image information of the first area, and determine first image feature information according to the normalized first image information;

[0022] Based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the normalized second image information.

[0023] In some embodiments of the present application, the first image information includes first grayscale information of each pixel in the first area, and the second image information includes second grayscale information of each pixel in the second area; the grayscale feature information includes grayscale entropy value;

[0024] The step of normalizing the first image information of the first area based on the first normalization parameter, and determining the first image feature information according to the normalized first image information includes:

[0025] Normalizing the first grayscale information of each pixel in the first area based on the first normalization parameter, calculating the entropy value of the normalized first grayscale information, and obtaining a first grayscale entropy value;

[0026] The step of normalizing the second image information of the second area based on the second normalization parameter, and determining the second image feature information according to the normalized second image information includes:

[0027] The second grayscale information of each pixel in the second area is normalized based on the second normalization parameter, and the entropy value of the normalized second grayscale information is calculated to obtain a second grayscale entropy value.

[0028] In some embodiments of the present application, determining the evaluation result of the target image according to the first image feature information and the second image feature information includes:

[0029] If both the first image feature information and the second image feature information meet the preset image quality parameter conditions, determining the evaluation result of the target image as a high dynamic range image, and obtaining the weight corresponding to each of the image quality parameters;

[0030] According to each of the image quality parameters and the weight corresponding to each of the image quality parameters, a dynamic range quality value of the target image is obtained.

[0031] In some embodiments of the present application, determining the evaluation result of the target image according to the first image feature information and the second image feature information includes:

[0032] If any one of the first image feature information or the second image feature information does not meet the preset image quality parameter condition, the evaluation result of the target image is determined as a non-high dynamic range image.

[0033] In a second aspect, the present application provides an image processing device, the device comprising:

[0034] A target image acquisition module is used to acquire a target image to be evaluated;

[0035] An image region segmentation module, used for segmenting the target image into a first region and a second region according to pixel brightness values ​​of the target image;

[0036] A feature information extraction module, used to extract first image feature information and second image feature information from the first area and the second area respectively; wherein the image feature information at least includes grayscale feature information, image detail information and color feature information;

[0037] The image information acquisition module is used to determine the evaluation result of the target image according to the first image feature information and the second image feature information.

[0038] In a third aspect, the present application further provides a computer device, the computer device comprising:

[0039] one or more processors;

[0040] Memory; and

[0041] One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the image processing method.

[0042] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is loaded by a processor to execute the steps in the image processing method.

[0043] In a fifth aspect, an embodiment of the present application provides a computer program product or a computer program, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in the first aspect above.

[0044] The above-mentioned image processing method, device, computer equipment and storage medium obtain the target image to be evaluated, and divide the target image into a first area and a second area according to the pixel brightness value of the target image; then extract the first image feature information and the second image feature information from the first area and the second area respectively; wherein the image feature information at least includes grayscale feature information, image detail information and color feature information; finally, determine the evaluation result of the target image according to the first image feature information and the second image feature information. The image is segmented according to the pixel brightness information in the target image, and then the image feature information is extracted separately for the areas with different brightness in the target image, so as to reduce the influence of the brightness in the image on the acquisition of the image feature information in the target image, and improve the representation ability of the image feature information on the information in the target image, so as to improve the accuracy of the subsequent evaluation of the target image. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a schematic diagram of a scene of an image processing method in an embodiment of the present application;

[0047] Figure 2 It is a flowchart of the image processing method in the embodiment of the present application;

[0048] Figure 3 is a flowchart of the steps of extracting first image feature information and second image feature information from the first area and the second area, respectively, in an embodiment of the present application;

[0049] Figure 4 is a flowchart of another image processing method in an embodiment of the present application;

[0050] Figure 5 is a schematic diagram of the structure of an image processing device in an embodiment of the present application;

[0051] Figure 6 It is a schematic diagram of the structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0053] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0054] In the description of the present application, the word "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0055] In the embodiments of the present application, it should be noted that since the image processing method provided by the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, an image is actually image data. It can be understood that if brightness, grayscale information, color information, etc. are mentioned in subsequent embodiments, they are all corresponding data, so that the computer device can process them. The details will not be repeated here.

[0056] In the embodiment of the present application, it should be noted that the image processing method provided in the embodiment of the present application can be applied to Figure 1 In the image processing system shown. The image processing system includes a terminal 100 and a server 200. The terminal 100 may be a device including a camera or a display device, specifically a desktop terminal or a mobile terminal, such as a mobile phone, a tablet computer, a laptop computer, etc., or a camera for information collection, storage, and transmission. The server 200 may be an independent server, or a server network or server cluster composed of servers, including but not limited to a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0057] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one server 200 is shown in the figure. It is understandable that the image processing system may also include one or more other servers, which are not specifically limited here. Figure 1 As shown, the image processing system may further include a memory for storing data, such as image data.

[0058] It should also be noted that Figure 1 The scene diagram of the image processing system shown is only an example. The image processing system and scene described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not constitute a limitation on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the image processing system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0059] See also Figure 2The present application embodiment provides an image processing method, which is mainly applied to the above Figure 1 Taking the server 200 in FIG. 1 as an example, the method includes steps S210 to S240, which are specifically as follows:

[0060] S210, obtaining a target image to be evaluated.

[0061] The target image refers to an image whose image quality needs to be evaluated, such as whether it is a high dynamic range image and a dynamic range interval, including but not limited to pictures, video frames in videos, etc.

[0062] Specifically, the target image may be an image acquired by the camera of the terminal 100. After the terminal 100 acquires the image, it sends it to the server 200. The server 200 evaluates the image acquired by the terminal 100 to determine whether the image acquired by the terminal 100 is a high dynamic range image and the dynamic range interval of the target image and other evaluation results, and obtains relevant information about the image quality of the image acquired by the terminal 100. The parameters and processes of the image imaging, image processing, image storage and other links may be adjusted according to the evaluation results to improve the image quality of the target image. Furthermore, the shooting performance of the corresponding camera of the terminal 100 may also be determined according to the evaluation results.

[0063] Furthermore, a high dynamic range image refers to an image with a larger exposure dynamic range than an ordinary image, that is, a high dynamic range image is an image with richer brightness information. When the image light ratio in a certain image is small, the possibility that the image is a high dynamic range image is small. Therefore, in one embodiment, step S210 obtains a target image to be evaluated, including: obtaining the image to be evaluated, dividing the preprocessed image into a first area and a second area according to the pixel brightness value of the image to be evaluated; obtaining a first area brightness mean of the first area and a second area brightness mean of the second area; obtaining an image light ratio of the image to be evaluated according to the ratio of the second area brightness mean to the first area brightness mean; if the image light ratio is greater than a preset light ratio threshold, determining the image to be evaluated as a target image.

[0064] The pixel brightness value can reflect the brightness of the pixel (i.e., brightness), and can be calculated based on the values ​​of the R channel, B channel, and G channel corresponding to each pixel. Furthermore, the pixel brightness value can also be measured by the grayscale value. Specifically, the image to be evaluated can be converted into a corresponding grayscale image, and then the pixel brightness value of the corresponding pixel in the image to be evaluated can be determined based on the grayscale value of each pixel on the grayscale image.

[0065] The first area and the second area may refer to the bright area and the dark area in the image to be evaluated. Specifically, it may be that the first area is the bright area and the second area is the dark area; or it may be that the first area is the dark area and the second area is the bright area, which is not limited here. After acquiring the image to be evaluated, the pixel brightness value of the image to be evaluated may be obtained, and the pixel points whose pixel brightness value is greater than a preset threshold value may be divided into one area, and the pixel points whose pixel brightness value is less than or equal to the preset threshold value may be divided into another area, thereby obtaining the first area and the second area.

[0066] The image light ratio refers to the brightness difference between the highlight and the shadow in the image. Specifically, the image light ratio of the image to be evaluated can be determined by the brightness difference between the first area and the second area, that is, by the brightness difference between the bright area and the dark area; when the image light ratio is larger, the brightness difference between the first area and the second area is larger, and the possibility that the image to be evaluated is a high dynamic range image is greater; when the image light ratio is smaller, the brightness difference between the first area and the second area is smaller, and the possibility that the image to be evaluated is a high dynamic range image is smaller.

[0067] Specifically, after obtaining the image to be evaluated, the pre-processed image is divided into a first region and a second region according to the pixel brightness value of the image to be evaluated, and then the average of the pixel brightness values ​​of each pixel point in the first region is obtained, that is, the first region brightness average is obtained, and the average of the pixel brightness values ​​of each pixel point in the second region is obtained, that is, the second region brightness average is obtained; then, the possibility that the image to be evaluated is a high dynamic range image is determined by the ratio of the second region brightness average to the first region brightness average (that is, the image light ratio). Among them, when the image light ratio is greater than the preset light ratio threshold, the possibility that the image to be evaluated is a high dynamic range image is greater, and the image to be evaluated is determined as the object of the subsequent image processing method; when the image light ratio is not greater than the preset light ratio threshold, the possibility that the image to be evaluated is a high dynamic range image is less, and there is no need to perform the subsequent image processing method.

[0068] S220, dividing the target image into a first area and a second area according to pixel brightness values ​​of the target image.

[0069] Among them, image information, such as color information, texture information, contrast information, etc., is often affected by light intensity (in digital image data, light intensity is often reflected by the brightness of pixels); for example, areas with higher brightness may be overexposed, that is, the image is too bright, resulting in the loss of image information such as color information and contrast information. At this time, the brightness value of the area needs to be dimmed to extract richer and more accurate image information; and areas with lower brightness values ​​may be underexposed, that is, the image is too dark, resulting in the loss of image information such as color information and contrast information. At this time, the brightness value of the area needs to be increased to extract richer and more accurate image information. Therefore, after acquiring the target image, the target image is partitioned according to the pixel brightness value, so as to facilitate the subsequent targeted extraction of image feature information for areas of different brightness.

[0070] As described above, the first area and the second area may refer to the bright area and the dark area in the image to be evaluated. Specifically, the pixel points whose pixel brightness values ​​are greater than a preset threshold value may be divided into one area, and the pixel points whose pixel brightness values ​​are less than or equal to the preset threshold value may be divided into another area, thereby obtaining the first area and the second area.

[0071] In one embodiment, step S220, according to the pixel brightness value of the target image, divides the target image into a first area and a second area, including: obtaining the grayscale value corresponding to each pixel in the target image; determining, according to the grayscale segmentation threshold and the grayscale value of each pixel, a first pixel whose grayscale value is greater than the grayscale segmentation threshold and a second pixel whose grayscale value is not greater than the grayscale segmentation threshold; determining the area where the first pixel is located as the first area, and determining the area where the second pixel is located as the second area.

[0072] Among them, the pixel brightness value can be measured by the grayscale value; specifically, the target image can be converted into a corresponding grayscale image, and then the pixel brightness value of the corresponding pixel in the target image can be determined according to the grayscale value of each pixel on the grayscale image; the grayscale value of the pixel can also be calculated according to the values ​​of the corresponding R channel, B channel, and G channel on each pixel. After obtaining the grayscale value of each pixel in the target image, the pixel points with grayscale values ​​greater than the grayscale segmentation threshold are divided into one area, and the pixel points with grayscale values ​​less than or equal to the grayscale segmentation threshold are divided into another area, thereby obtaining the first area and the second area.

[0073] Among them, the grayscale segmentation threshold can be set according to the actual situation. For example, if the grayscale value of the pixel is between 0 and 255, the grayscale segmentation threshold can be set to 155; after obtaining the grayscale value of each pixel of the target image, the pixel with a grayscale value of [0,155] can be divided into one area, which is a region with lower brightness, that is, a dark area; and the pixel with a grayscale value of (155,255] can be divided into another area, which is a region with higher brightness, that is, a bright area.

[0074] S230, extracting first image feature information and second image feature information from the first region and the second region respectively; wherein the image feature information at least includes grayscale feature information, image detail information and color feature information.

[0075] The image feature information includes first image feature information and second image feature information, which refers to information extracted in a corresponding area and used to characterize image features, such as color features, texture features, grayscale (brightness) features, etc.

[0076] Specifically, the image feature information includes at least grayscale feature information, image detail information and color feature information. Among them, the grayscale feature information in the image feature information can be the entropy value of the grayscale information, which is used to reflect the dynamic range of the image grayscale; the color feature information in the image feature information can be the color saturation and color deviation of the pixel point, which can reflect whether the image color is bright and true; the image detail information in the image feature information can be the contrast between pixels, which can be the SFR (Spatial Frequency Response) value or the MTF (Modulation Transfer Function) value. The image detail information can reflect the image clarity.

[0077] After dividing the target image into two regions, the server extracts the first image feature information from the first region and extracts the second image feature information from the second region. Specifically, the grayscale feature information, image detail information and color feature information corresponding to the first region are extracted from the first region and determined as the first image feature information; the grayscale feature information, image detail information and color feature information corresponding to the second region are extracted from the second region and determined as the second image feature information.

[0078] Furthermore, as mentioned above, if the image in the area with a larger brightness value is too bright, it will often lead to loss of image information. In this case, it is necessary to darken the brightness value of the area to extract richer and more accurate image information; and if the image in the area with a smaller brightness value is too dark, it will often lead to loss of image information. In this case, it is necessary to increase the brightness value of the area to extract richer and more accurate image information. Therefore, in one embodiment, Figure 3 As shown, step S230, extracting first image feature information and second image feature information from the first area and the second area respectively, includes:

[0079] S310, obtaining the maximum pixel brightness and the minimum pixel brightness in the target image.

[0080] S320: Obtain a first normalized parameter of the first area and a second normalized parameter of the second area according to a ratio between a maximum pixel brightness and a minimum pixel brightness.

[0081] S330: performing normalization processing on the first image information of the first area based on the first normalization parameter, and determining first image feature information according to the normalized first image information.

[0082] S340: performing normalization processing on the second image information of the second area based on the second normalization parameter, and determining second image feature information according to the normalized second image information.

[0083] Taking the first area as a bright area and the second area as a dark area as an example, the first normalization parameter is the bright area normalization parameter corresponding to the bright area, and the second normalization parameter is the dark area normalization parameter. Specifically, the server obtains the maximum and minimum values ​​of the pixel brightness values ​​in the target image, that is, obtains the maximum pixel brightness value R h and the minimum pixel brightness R l Then, the ratio of the maximum pixel brightness to the minimum pixel brightness is obtained to obtain the bright normalization parameter M corresponding to the bright area. h (i.e., M h =R h / R l ), and obtain the ratio of the minimum pixel brightness to the maximum pixel brightness, and obtain the dark normalization parameter M corresponding to the dark area l (i.e., M l =R l / R h ); Then, the image information of the bright area is obtained from the bright area, and the bright normalization parameter M is used hThe image information of the bright area is normalized to uniformly reduce the brightness of the bright area and reduce the influence of the overbrightness of the picture on the extraction of image feature information. The corresponding image feature information is subsequently extracted from the bright area after the brightness adjustment. Similarly, for the dark area, the image information of the dark area is obtained from the dark area and the dark normalization parameter M is used. l The image information of the dark area is normalized to uniformly increase the brightness of the dark area, reduce the impact of the dark picture on the extraction of image feature information, and subsequently extract the corresponding image feature information from the dark area after brightness adjustment.

[0084] It can be understood that the first area can also be a dark area, and the corresponding second area is a bright area. The first normalization parameter is a dark normalization parameter corresponding to the dark area, and the second normalization parameter is a bright normalization parameter.

[0085] By independently processing the first area and the second area of ​​different brightness, the brightness of the first area is unified by using the first normalization parameter corresponding to the first area, and the second area is unified by using the second normalization parameter of the second area, so as to reduce the influence of the picture being too bright or too dark on the extraction of image feature information, so that the first area and the second area are under the same light ratio, and then the grayscale entropy value, image detail information and color feature information under the same light ratio are calculated, so as to extract richer and more accurate image feature information.

[0086] Among them, the first image information includes first grayscale information of each pixel in the first area, and the second image information includes second grayscale information of each pixel in the second area; the grayscale feature information includes a grayscale entropy value; based on the first normalization parameter, the first image information of the first area is normalized, and the first image feature information is determined according to the normalized first image information, which may include: based on the first normalization parameter, the first grayscale information of each pixel in the first area is normalized, and the entropy value of the first grayscale information after the normalization is calculated to obtain the first grayscale entropy value; based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the normalized second image information, which may include: based on the second normalization parameter, the second grayscale information of each pixel in the second area is normalized, and the entropy value of the second grayscale information after the normalization is calculated to obtain the second grayscale entropy value.

[0087] Specifically, the grayscale normalization for the first region can be expressed by the following formula (1), and the grayscale normalization for the second region can be expressed by the following formula (2), as follows:

[0088] hist gs1 (K1) = M h ×C(K1)(1)

[0089] hist gs2 (K2) = M l ×C(K2)(2)

[0090] Among them, hist gs1 (K1) represents the normalized grayscale information of each pixel in the first region; hist gs2 (K2) represents the normalized grayscale information of each pixel in the second region; M h represents the normalized parameter of the first region; M l represents the normalization parameter of the second area; K1 represents the pixel brightness value of each pixel in the first area, and K2 represents the pixel brightness value of each pixel in the second area; C(·) represents the process of converting the pixel brightness value of the pixel into a grayscale value, that is, C(K1) represents the grayscale value of the pixel in the first area, and C(K2) represents the grayscale value of the pixel in the second area.

[0091] After obtaining the normalized grayscale information of the first region, the grayscale entropy value corresponding to the first region can be calculated by the following formula (3):

[0092]

[0093] After obtaining the normalized grayscale information of the second region, the grayscale entropy value corresponding to the second region can be calculated using the following formula (4).

[0094]

[0095] By performing normalization processing on the first region and the second region respectively, using the second normalization parameter M l The brightness of the second area is uniformly brightened, and the first normalization parameter M is used h The brightness of the first area is uniformly reduced so that the first area and the second area are under the same light ratio condition, and then the grayscale entropy value under the same light ratio is calculated to extract an accurate dynamic range entropy value.

[0096] Among them, the first image information may also include first image detail information; the second image information may also include second image detail information; based on the first normalization parameter, the first image information of the first area is normalized, and the first image feature information is determined according to the first image information after the normalization process, which may be specifically: image detail information is acquired from the first area, and based on the first normalization parameter, the image detail information of the first area is normalized to acquire image feature information corresponding to the image detail information; similarly, based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the second image information after the normalization process, which may be specifically: image detail information is acquired from the second area, and based on the second normalization parameter, the image detail information of the second area is normalized to acquire image feature information corresponding to the image detail information.

[0097] By independently processing the first area and the second area with different brightness, the brightness of the first area is unified by using the first normalization parameter corresponding to the first area, and the second area is unified by using the second normalization parameter of the second area, so that the first area and the second area are under the same light ratio condition, and then the texture information, contrast and other image details under the same light ratio are calculated, so as to extract rich and accurate image detail information.

[0098] Among them, the first image information may also include first color information; the second image information may include second color information; based on the first normalization parameter, the first image information of the first area is normalized, and the first image feature information is determined according to the first image information after normalization, which may be specifically: color information is obtained from the first area, and based on the first normalization parameter, the color information of the first area is normalized to obtain the first image feature information corresponding to the color information; similarly, based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the second image information after normalization, which may be specifically: color information is obtained from the second area, and based on the second normalization parameter, the color information of the second area is normalized to obtain the second image feature information corresponding to the color information.

[0099] Specifically, color information is obtained from the first area by using a color model conversion algorithm to convert image data corresponding to the first area in RGB format into image data in HSV format, and then extracting different colors according to the value corresponding to the converted HSV. Similarly, the step of obtaining color information from the second area is the same as that of obtaining color information from the first area, and the only difference is that the data processing object is different. By independently processing the first area and the second area of ​​different brightness, the brightness of the first area is unified using the first normalization parameter corresponding to the first area, and the second area is unified using the second normalization parameter of the second area, so that the first area and the second area are under the same light ratio, and then the image color information such as saturation under the same light ratio is calculated, so as to extract rich and accurate color feature information.

[0100] S240: Determine an evaluation result of the target image according to the first image feature information and the second image feature information.

[0101] After the first image feature information and the second image feature information are obtained, it may be determined whether the first image feature information and the second image feature information meet a preset image quality parameter condition.

[0102] Specifically, the first image feature information at least includes grayscale feature information, image detail information and color feature information of the first region, and the second image feature information at least includes grayscale feature information, image detail information and color feature information of the second region. The grayscale feature information may be a grayscale entropy value of the corresponding region. If the first grayscale entropy value of the first region and the second grayscale entropy value of the second region are both greater than a preset entropy value threshold, the first grayscale entropy value and the second grayscale entropy value are both valid entropy values ​​and meet the preset image quality parameter conditions; if either the first grayscale entropy value of the first region or the second grayscale entropy value of the second region is not greater than the preset entropy value threshold, the grayscale entropy value less than the entropy value threshold is an invalid entropy value and does not meet the preset image quality parameter conditions.

[0103] Similarly, a corresponding information threshold is set for the image detail information. If the image detail information of the first area and the image detail information of the second area are both greater than the preset information threshold, the image detail information of the first area and the image detail information of the second area are both valid values ​​and meet the preset image quality parameter conditions; if the image detail information of the first area and the image detail information of the second area are both greater than any one of the preset information thresholds but not greater than the preset information threshold, the image detail information less than the information threshold is invalid information and does not meet the preset image quality parameter conditions. A corresponding information threshold is set for color information. If the color feature information of the first area and the color feature information of the second area are both greater than the preset information threshold, the color feature information of the first area and the color feature information of the second area are both valid values ​​and meet the preset image quality parameter conditions; if the color feature information of the first area and the color feature information of the second area are both greater than any one of the preset information thresholds but not greater than the preset entropy value threshold, the color feature information less than the entropy value threshold is invalid information and does not meet the preset image quality parameter conditions.

[0104] Among them, if any one of the first image feature information or the second image feature information does not meet the preset image quality parameter conditions, the evaluation result of the target image is determined as a non-high dynamic range image. It can be understood that when any one of the grayscale feature information, image detail information or color feature information in the first area and the second area does not meet the preset image quality parameter conditions, the target image is a non-high dynamic range image. At this time, the reason for the relatively large image light of the target image may be that a foreign object blocks the front of the camera lens during the process of the camera device shooting the target image, resulting in the brightness of the local area image being too dark, or the camera lens is directly facing the light source in the shooting scene, resulting in the brightness of the local area image being too bright, etc. Further, if the evaluation result of the target image is a non-high dynamic range image, abnormal information can be output to the terminal based on the evaluation result of "non-high dynamic range image", so that the user knows that the captured image is abnormal.

[0105] Among them, if the first image feature information and the second image feature information both meet the preset image quality parameter conditions, the evaluation result of the target image is determined as a high dynamic range image, and the weight corresponding to each image quality parameter is obtained; according to each image quality parameter and the weight corresponding to each image quality parameter, the dynamic range quality value of the target image is obtained. It can be understood that when the grayscale information, contrast information or color information in the first area and the second area meet the preset image quality parameter conditions, the target image is a high dynamic range image, and the weights of the first image feature information and the second image feature information can be set according to the display requirements of the dark area and the bright area, and then the first image feature information and the second image feature information are weightedly calculated to obtain the dynamic range quality value of the target image. Specifically, the dynamic range quality value of the target image can be calculated by the following formulas (5), (6), and (7):

[0106] F=F1+F2(5)

[0107] F1=A1×Entropy gs1 +A2×T1+A3×C1(6)

[0108] F2=B1×Entropy gs2 +B2×T2+B3×C2(7)

[0109] Among them, A=A1+A2+A3, B=B1+B2+B3, A+B=1.

[0110] Where F represents the dynamic range quality value; F1 represents the dynamic range quality value of the first region; F2 represents the dynamic range quality value of the second region; Entropy gs1 Represents the first grayscale entropy value of the first area, Entropy gs2 represents the second grayscale entropy value of the second area; T1 represents the image detail information of the first area, T2 represents the image detail information of the second area, C1 represents the color feature information of the first area, and C2 represents the color feature information of the second area.

[0111] In the above image processing method, the target image to be evaluated is obtained, and the target image is divided into a first area and a second area according to the pixel brightness value of the target image; then the first image feature information and the second image feature information are extracted from the first area and the second area respectively; wherein the image feature information at least includes grayscale feature information, image detail information and color feature information; finally, the evaluation result of the target image is determined according to the first image feature information and the second image feature information. The image is segmented according to the pixel brightness information in the target image, and then the image feature information is extracted from the areas of different brightness in the target image respectively, so as to reduce the influence of the brightness in the image on the image information in the target image, improve the representation ability of the image feature information on the information in the target image, and improve the accuracy of the subsequent evaluation of the target image.

[0112] See also Figure 4 , the following combination Figure 4 The image processing method provided in this application is further described. Figure 4 As shown, the image processing method includes:

[0113] Step 1, bright and dark area segmentation: obtain the image to be evaluated, and segment the preprocessed image into a bright area and a dark area according to the pixel brightness value of the image to be evaluated.

[0114] Step 2: Whether the image light ratio reaches the judgment threshold T: Get the average brightness L of the bright area h And the average brightness of the dark area L l , determine the mean brightness Lh The average brightness of the dark area L l The ratio (L h / L l ) whether it reaches the high dynamic image determination threshold T; if L h / L l ≥T, the image to be evaluated is likely to be a high dynamic range image. At this time, execute the next step to enter the high dynamic range image quality test step. If L h / L l <T, the possibility that the image to be evaluated is a high dynamic range image is small, and the normal image quality test step is entered at this time.

[0115] It can be understood that when the image light of the image to be evaluated is less than the judgment threshold T, the possibility that the image to be evaluated is a high dynamic range image is small, the possibility of too bright or too dark appearing in the image to be evaluated is small, and the brightness of the entire image is relatively even, so there is no need to perform image processing by targeted partitioning.

[0116] Step 3: Calculate the light ratio normalization factor M, which includes the highlight normalization factor M corresponding to the bright area. h and the low light normalization factor M corresponding to the dark area l .

[0117] Specifically, the maximum and minimum values ​​of the pixel brightness values ​​in the target image are obtained, that is, the maximum pixel brightness value R h and the minimum pixel brightness R l Then, the ratio of the maximum pixel brightness to the minimum pixel brightness is obtained to obtain the bright normalization parameter M corresponding to the bright area. h (i.e., M h =R h / R l ), and obtain the ratio of the minimum pixel brightness to the maximum pixel brightness, and obtain the dark normalization parameter M corresponding to the dark area l (i.e., M l =R l / R h )

[0118] Step 4, normalization of grayscale values: Normalization of grayscale values ​​of bright areas can be achieved by the following formula (8), and normalization of grayscale values ​​of dark areas can be achieved by the following formula (9), as follows:

[0119] hist gs1 (K1) = M h ×C(K1)(8)

[0120] hist gs2 (K2) = M l ×C(K2)(9)

[0121] Among them, hist gs1 (K1) represents the normalized grayscale information of each pixel in the bright area; hist gs2 (K2) represents the normalized grayscale information of each pixel in the dark area; M h Represents the normalized parameter of the bright area; M l represents the normalization parameter of the dark area; K1 represents the pixel brightness value of each pixel in the bright area, and K2 represents the pixel brightness value of each pixel in the dark area; C(K1) represents the process of converting the pixel brightness value of the pixel in the bright area into a grayscale value, that is, the grayscale value of the pixel in the bright area; C(K2) represents the process of converting the pixel brightness value of the pixel in the dark area into a grayscale value, that is, the grayscale value of the pixel in the dark area.

[0122] Step 5, calculation of entropy values ​​of bright and dark areas: After obtaining the normalized grayscale information of the bright area, the bright grayscale entropy value corresponding to the bright area can be calculated by the following formula (10), and after obtaining the normalized grayscale information of the dark area, the dark grayscale entropy value corresponding to the bright area can be calculated by the following formula (11). The specific formulas are as follows:

[0123]

[0124]

[0125] Step 6, judging the validity of the entropy values ​​of the bright and dark areas: if the bright grayscale entropy value of the bright area and the dark grayscale entropy value of the dark area are both greater than the preset entropy value threshold, then the bright grayscale entropy value and the dark grayscale entropy value are both valid entropy values, meeting the preset image quality parameter conditions, saving the bright grayscale entropy value and the dark grayscale entropy value, and executing steps 7 and 8; if any one of the bright grayscale entropy value of the bright area and the dark grayscale entropy value of the dark area is not greater than the preset entropy value threshold, then the grayscale entropy value less than the entropy value threshold is an invalid entropy value, which does not meet the preset image quality parameter conditions. At this time, the dynamic range value of the input image to be evaluated is invalid, the input image needs to be rechecked, and image abnormality information can be output.

[0126] Step 7, extracting image detail information of bright and dark areas: extracting image detail information t1 from the bright area, and extracting image detail information t2 from the dark area; then normalizing the image detail information t1 using the bright normalization factor (specifically, it can be implemented by the following formula (12)) to obtain image detail information in the bright area, and normalizing the image detail information t2 using the dark normalization factor (specifically, it can be implemented by the following formula (13)) to obtain image detail information in the dark area;

[0127] T1=M h *f1(t1)(12)

[0128] T2=M l *f1(t2)(13)

[0129] Wherein, T1 is the normalized image detail information of the bright area, and T2 is the normalized image detail information of the dark area; f1(·) represents the process of extracting image detail information from image information, f1(t1) represents the image detail information extracted from the bright area, and f1(t2) represents the image detail information extracted from the dark area.

[0130] Step 8, extracting color feature information of bright and dark areas: extracting image color information c1 from the bright area, and extracting image color information c2 from the dark area; then normalizing the image color information c1 using the bright normalization factor (specifically, it can be implemented by the following formula (14)) to obtain color feature information in the bright area, and normalizing the image color information c2 using the dark normalization factor (specifically, it can be implemented by the following formula (15)) to obtain color feature information in the dark area;

[0131] C1=M h *f2(c1)(14)

[0132] C2=M l *f2(c2)(15)

[0133] Wherein, C1 is the normalized image detail information of the bright area, and C2 is the normalized image detail information of the dark area; f2(·) represents the process of extracting color feature information from the image information, f2(c1) represents the image detail information extracted from the bright area, and f2(c2) represents the image detail information extracted from the dark area.

[0134] Step 9, determine the validity of the image detail information and color feature information: if the image detail information and color feature information of the bright area, and the image detail information and color feature information of the dark area are all greater than the preset information threshold, then the image detail information and color feature information of the bright area, and the image detail information and color feature information of the dark area are all valid values, meet the preset image quality parameter conditions, save the image detail information and color feature information of the bright area, and the image detail information and color feature information of the dark area, and execute step 10; if any one of the image detail information and color feature information of the first area, and the image detail information and color feature information of the dark area is not greater than the preset information threshold, then the image detail information or color feature information less than the information threshold is invalid information, does not meet the preset image quality parameter conditions, at this time, the dynamic range value of the input image to be evaluated is invalid, the input image needs to be rechecked, and image abnormality information can be output.

[0135] Step 10, calculating the high dynamic range quality value: performing weighted summation on the bright grayscale entropy value, image detail information and color feature information of the bright area, and the dark grayscale entropy value, image detail information and color feature information of the dark area to obtain the high dynamic range quality value, which can be specifically implemented by the following formulas (16) to (18):

[0136] F=F1+F2(16)

[0137] F1=A1×Entropy gs1 +A2×T1+A3×C1(17)

[0138] F2=B1×Entropy gs2 +B2×T2+B3×C2(18)

[0139] Among them, A=A1+A2+A3, B=B1+B2+B3, A+B=1.

[0140] Among them, F represents the dynamic range quality value; F1 represents the dynamic range quality value of the bright area; F2 represents the dynamic range quality value of the dark area; Entropy gs1 Indicates the bright grayscale entropy value of the bright area, Entropy gs2 represents the second grayscale entropy value of the dark area; T1 represents the image detail information of the bright area, T2 represents the image detail information of the dark area, C1 represents the color feature information of the bright area, and C2 represents the color feature information of the dark area.

[0141] Step 11: Output the image evaluation results.

[0142] The above image processing scheme takes into account the image quality impact caused by different light ratios of the image to be evaluated, and extracts the image light ratio of the bright area and the dark area of ​​the image to be evaluated, and obtains the brightness ratio of the bright area and the dark area. Then, after brightness normalization processing of the image data of the bright area and the image data of the dark area, the dynamic range entropy value (i.e., grayscale entropy value) of the bright area and the dark area, image detail information under the same light ratio, color feature information under the same light ratio and other image quality parameters are calculated respectively, and then the dynamic range image quality evaluation results are obtained based on the dynamic range entropy value, image detail information and color feature information. Compared with the existing dynamic range image quality evaluation method, it effectively reduces the impact of changes in equipment light ratio, truly reflects the dynamic range image quality level, and improves the evaluation accuracy.

[0143] In order to better implement the image processing method provided in the embodiment of the present application, on the basis of the image processing method provided in the embodiment of the present application, an image processing device is also provided in the embodiment of the present application, such as Figure 5 As shown, the image processing device 500 includes:

[0144] The target image acquisition module 510 is used to acquire the target image to be evaluated;

[0145] An image region segmentation module 520, configured to segment the target image into a first region and a second region according to pixel brightness values ​​of the target image;

[0146] A feature information extraction module 530 is used to extract first image feature information and second image feature information from the first region and the second region respectively; wherein the image feature information includes at least grayscale feature information, image detail information and color feature information;

[0147] The image information acquisition module 540 is used to determine the evaluation result of the target image according to the first image feature information and the second image feature information.

[0148] In some embodiments of the present application, the target image acquisition module 510 is also used to acquire the image to be evaluated, and divide the preprocessed image into a first area and a second area according to the pixel brightness value of the image to be evaluated; obtain the first area brightness mean of the first area and the second area brightness mean of the second area; obtain the image light ratio of the image to be evaluated according to the ratio of the second area brightness mean to the first area brightness mean; if the image light ratio is greater than a preset light ratio threshold, determine the image to be evaluated as a target image.

[0149] In some embodiments of the present application, the image region segmentation module 520 is also used to obtain the grayscale value corresponding to each pixel in the target image; determine the first pixel whose grayscale value is greater than the grayscale segmentation threshold and the second pixel whose grayscale value is not greater than the grayscale segmentation threshold based on the grayscale segmentation threshold and the grayscale value of each pixel; determine the area where the first pixel is located as the first area, and determine the area where the second pixel is located as the second area.

[0150] In some embodiments of the present application, the feature information extraction module 530 is also used to obtain the maximum pixel brightness and the minimum pixel brightness in the target image; obtain the first normalization parameter of the first area and the second normalization parameter of the second area based on the ratio between the maximum pixel brightness and the minimum pixel brightness; based on the first normalization parameter, normalize the first image information of the first area, and determine the first image feature information based on the normalized first image information; based on the second normalization parameter, normalize the second image information of the second area, and determine the second image feature information based on the normalized second image information.

[0151] In some embodiments of the present application, the first image information includes first grayscale information; the second image information includes second grayscale information; the first image feature information includes a first grayscale entropy value, and the second image feature information includes a second grayscale entropy value; the feature information extraction module 530 is used to normalize the first grayscale information based on the first normalization parameter, calculate the entropy value of the normalized first grayscale information, and obtain the first grayscale entropy value; normalize the second grayscale information based on the second normalization parameter, calculate the entropy value of the normalized second grayscale information, and obtain the second grayscale entropy value

[0152] In some embodiments of the present application, the image information acquisition module 540 is further configured to determine the evaluation result of the target image as a high dynamic range image when both the first image feature information and the second image feature information meet the preset image quality parameter conditions, and obtain the weight corresponding to each image quality parameter;

[0153] According to each image quality parameter and the weight corresponding to each image quality parameter, a dynamic range quality value of the target image is obtained.

[0154] In some embodiments of the present application, the image information acquisition module 540 is further used to determine the evaluation result of the target image as a non-high dynamic range image when any one of the first image feature information or the second image feature information does not meet the preset image quality parameter conditions.

[0155] For the specific definition of the image processing device, please refer to the definition of the image processing method above, which will not be repeated here. Each module in the above-mentioned page display device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can 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.

[0156] In some embodiments of the present application, the image processing device 500 may be implemented in the form of a computer program. The computer program may be implemented in a computer program such as: Figure 6 The computer device shown in the figure is run on the computer device. The memory of the computer device can store various program modules constituting the image processing device 500, for example, Figure 5 The target image acquisition module 510, the image region segmentation module 520, the feature information extraction module 530 and the image information acquisition module 540 are shown. The computer program composed of various program modules enables the processor to execute the steps of the image processing method of each embodiment of the present application described in this specification.

[0157] For example, Figure 6 The computer device shown can be Figure 5 The target image acquisition module 510 in the image processing device 500 shown in the figure performs step S210. The computer device can perform step S220 through the image region segmentation module 520. The computer device can perform step S230 through the feature information extraction module 530. The computer device can perform step S240 through the image information acquisition module 540. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external computer device through a network connection. When the computer program is executed by the processor, an image processing method is implemented.

[0158] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In some embodiments of the present application, a computer device is provided, comprising one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor in the steps of the above-mentioned image processing method. The steps of the image processing method here may be the steps in the image processing method of each of the above-mentioned embodiments.

[0160] In some embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program, and the computer program is loaded by a processor, so that the processor executes the steps of the above-mentioned image processing method. The steps of the image processing method here can be the steps in the image processing method of each of the above-mentioned embodiments.

[0161] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Any reference to memory, storage, 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 may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above is a detailed introduction to an image processing method, device, computer equipment and storage medium provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An image processing method, characterized in that: include: Obtain the target image to be evaluated; According to the pixel brightness values ​​of the target image, the target image is divided into a first area and a second area; Extracting first image feature information and second image feature information from the first area and the second area respectively; wherein the image feature information includes at least grayscale feature information, image detail information and color feature information; Determining an evaluation result of the target image according to the first image feature information and the second image feature information; The grayscale feature information includes a grayscale entropy value, and determining the evaluation result of the target image according to the first image feature information and the second image feature information includes: If the first grayscale entropy value of the first area and the second grayscale entropy value of the second area are both greater than a preset entropy value threshold, and the image detail information and color feature information of the first area and the image detail information and color feature information of the second area are both greater than a preset information threshold, then the target image is determined as the evaluation result to be a high dynamic range image, and the first grayscale entropy value, image detail information and color feature information of the first area, and the second grayscale entropy value, image detail information and color feature information of the second area are weightedly summed to obtain a high dynamic range quality value; If the first grayscale entropy value of the first area and the second grayscale entropy value of the second area are both not greater than a preset entropy value threshold, or the image detail information and color feature information of the first area and the image detail information and color feature information of the second area are both not greater than a preset information threshold, determining that the target image is a non-high dynamic range image as the evaluation result; The extracting first image feature information and second image feature information from the first area and the second area respectively includes: Obtaining a maximum pixel brightness and a minimum pixel brightness in the target image; Acquire a first normalized parameter of the first area and a second normalized parameter of the second area according to a ratio between the maximum pixel brightness and the minimum pixel brightness; Based on the first normalization parameter, normalize the first image information of the first area, and determine first image feature information according to the normalized first image information; Based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the normalized second image information.

2. The method according to claim 1, characterized in that: The step of obtaining a target image to be evaluated includes: Acquire an image to be evaluated, and divide the image to be evaluated into a first area and a second area according to pixel brightness values ​​of the image to be evaluated; Obtaining a first area brightness average of the first area and a second area brightness average of the second area; Obtaining an image light ratio of the image to be evaluated according to a ratio of a brightness mean value of the second area to a brightness mean value of the first area; If the image light ratio is greater than a preset light ratio threshold, the image to be evaluated is determined as a target image.

3. The method according to claim 1, characterized in that The step of segmenting the target image into a first region and a second region according to pixel brightness values ​​of the target image comprises: Obtaining the grayscale value corresponding to each pixel in the target image; According to the grayscale segmentation threshold and the grayscale value of each pixel, determine a first pixel whose grayscale value is greater than the grayscale segmentation threshold and a second pixel whose grayscale value is not greater than the grayscale segmentation threshold; The area where the first pixel point is located is determined as a first area, and the area where the second pixel point is located is determined as a second area.

4. The method according to claim 1, characterized in that: The first image information includes first grayscale information of each pixel in the first area, and the second image information includes second grayscale information of each pixel in the second area; the grayscale feature information includes grayscale entropy value; The step of normalizing the first image information of the first area based on the first normalization parameter, and determining the first image feature information according to the normalized first image information includes: Normalizing the first grayscale information of each pixel in the first area based on the first normalization parameter, calculating the entropy value of the normalized first grayscale information, and obtaining a first grayscale entropy value; The step of normalizing the second image information of the second area based on the second normalization parameter, and determining the second image feature information according to the normalized second image information includes: The second grayscale information of each pixel in the second area is normalized based on the second normalization parameter, and the entropy value of the normalized second grayscale information is calculated to obtain a second grayscale entropy value.

5. The method according to claim 1, characterized in that The step of determining the evaluation result of the target image according to the first image feature information and the second image feature information includes: If both the first image feature information and the second image feature information meet the preset image quality parameter conditions, determining the evaluation result of the target image as a high dynamic range image, and obtaining the weight corresponding to each of the image quality parameters; According to each of the image quality parameters and the weight corresponding to each of the image quality parameters, a dynamic range quality value of the target image is obtained.

6. The method according to claim 1, characterized in that The step of determining the evaluation result of the target image according to the first image feature information and the second image feature information includes: If any one of the first image feature information or the second image feature information does not meet the preset image quality parameter condition, the evaluation result of the target image is determined as a non-high dynamic range image.

7. An image processing device, characterized in that: The device comprises: A target image acquisition module is used to acquire a target image to be evaluated; An image region segmentation module, used for segmenting the target image into a first region and a second region according to pixel brightness values ​​of the target image; A feature information extraction module, used to extract first image feature information and second image feature information from the first area and the second area respectively; wherein the image feature information at least includes grayscale feature information, image detail information and color feature information; An image information acquisition module, used to determine an evaluation result of the target image according to the first image feature information and the second image feature information; The grayscale feature information includes a grayscale entropy value, and determining the evaluation result of the target image according to the first image feature information and the second image feature information includes: If the first grayscale entropy value of the first area and the second grayscale entropy value of the second area are both greater than a preset entropy value threshold, and the image detail information and color feature information of the first area and the image detail information and color feature information of the second area are both greater than a preset information threshold, then the target image is determined as the evaluation result to be a high dynamic range image, and the first grayscale entropy value, image detail information and color feature information of the first area, and the second grayscale entropy value, image detail information and color feature information of the second area are weightedly summed to obtain a high dynamic range quality value; If the first grayscale entropy value of the first area and the second grayscale entropy value of the second area are both not greater than a preset entropy value threshold, or the image detail information and color feature information of the first area and the image detail information and color feature information of the second area are both not greater than a preset information threshold, determining that the target image is a non-high dynamic range image as the evaluation result; The extracting first image feature information and second image feature information from the first area and the second area respectively includes: Obtaining a maximum pixel brightness and a minimum pixel brightness in the target image; Acquire a first normalized parameter of the first area and a second normalized parameter of the second area according to a ratio between the maximum pixel brightness and the minimum pixel brightness; Based on the first normalization parameter, normalize the first image information of the first area, and determine first image feature information according to the normalized first image information; Based on the second normalization parameter, the second image information of the second area is normalized, and the second image feature information is determined according to the normalized second image information.

8. A computer device, characterized in that: The computer device comprises: one or more processors; A memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the image processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the image processing method according to any one of claims 1 to 6.

Images