Objective index method for evaluating improvement condition of dichroism contrast

Abstract

The invention discloses an objective index method for evaluating a dichroism contrast improvement condition. The method comprises the following steps: converting a normal image and a first image represented by a red-green-blue color space into a first conversion image and a second conversion image represented by a laboratory color space; obtaining an initial pixel in the first conversion image; respectively calculating the difference values of the brightness component, the red-green component and the yellow-blue component in the eyes of the person with normal color vision; target pixels which are difficult to distinguish are determined in the initial pixels according to the difference value; respectively calculating a plurality of experimental color differences in combination with the weight adjustment coefficient of the lightness difference; the plurality of experimental chromatic aberration are chromatic aberration of the target pixel in the eyes of the abnormal color vision person and the normal color vision person in the first conversion image and chromatic aberration of the target pixel in the eyes of the abnormal color vision person in the second conversion image, an objective index value corresponding to the first image is calculated in combination with a chromatic aberration value adjustment coefficient, and then an optimal image is screened out.

Description

Technical Field

[0001] This invention belongs to the field of image processing, and relates to, but is not limited to, an objective index method for evaluating the improvement of dichromatic contrast. Background Technology

[0002] With the development of multimedia displays such as images, videos, and 3D virtual technology, visual information provides us with a wealth of experiences. Color is an important factor in visual information, and people with color vision deficiencies have difficulty distinguishing specific colors and cannot fully receive color information. In recent years, researchers have studied many methods to improve contrast for dichroic viewers by altering the colors in input normal images, thereby enhancing the presentation of the original image information.

[0003] In related technologies, the evaluation of the improvement results of the input normal image adopts subjective evaluation, but obtaining subjective evaluation values ​​requires a lot of effort and time, the process is cumbersome, and it increases the complexity of the evaluation.

[0004] Therefore, how to quickly and accurately evaluate the improvement effect of converting normal images into images suitable for color vision deficiencies has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide an objective index method for evaluating the improvement of dichromatic contrast, at least solving the problem that related technologies cannot quickly and accurately evaluate the improvement effect of converting normal images into images suitable for color vision abnormalities.

[0006] According to a first aspect of the present invention, an objective index method for evaluating the improvement of dichroic contrast is provided, comprising: The normal image and the first image, represented in the red-green-blue color space, are respectively converted into a first converted image and a second converted image, represented in the laboratory color space; the first image is an image that has been adjusted from the normal image to be suitable for recognition by people with color vision deficiencies. In the first converted image, an initial pixel is obtained; and in the first converted image, the first difference of the first brightness component, the second difference of the first red-green component, and the third difference of the first yellow-blue component of the initial pixel in the eyes of a person with normal color vision are calculated. Based on the first difference, the second difference, and the third difference, a target pixel that is difficult to distinguish is determined in the initial pixel; Based on a preset weighting coefficient for brightness difference and the target pixel, a first laboratory color difference, a second laboratory color difference, and a third laboratory color difference are calculated respectively; the first laboratory color difference and the second laboratory color difference are the color difference of the target pixel in the eyes of a person with normal color vision and a person with abnormal color vision in the first converted image, respectively; the third laboratory color difference is the color difference of the target pixel in the eyes of a person with abnormal color vision in the second converted image. Based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and the preset color difference adjustment coefficient, the objective index value corresponding to each first image is calculated, and the optimal image is obtained in the first image based on the objective index value.

[0007] According to a second aspect of the present invention, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the method described in the first aspect.

[0008] According to a third aspect of the present invention, a computer storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0009] According to the scheme provided by the embodiments of the present invention, a normal image and a first image represented in red-green-blue color space are respectively converted into a first converted image and a second converted image represented in laboratory color space; the first image is an image in which the normal image is adjusted to be recognizable by a person with color vision deficiency; initial pixels are obtained in the first converted image; and a first difference in the first brightness component, a second difference in the first red-green component, and a third difference in the first yellow-blue component of the initial pixels in the eyes of a person with normal color vision are calculated; based on the first difference, the second difference, and the third difference, target pixels that are difficult to distinguish are determined in the initial pixels; and a weighting system based on the preset brightness difference is used to adjust the initial pixels. The first laboratory color difference, the second laboratory color difference, and the third laboratory color difference are calculated based on the target pixel and the number of pixels, respectively. The first laboratory color difference and the second laboratory color difference are the color differences of the target pixel in the first converted image as seen by a person with normal color vision and a person with abnormal color vision, respectively. The third laboratory color difference is the color difference of the target pixel in the second converted image as seen by a person with abnormal color vision. Based on the first laboratory color difference, the second laboratory color difference, the third laboratory color difference, and a preset color difference adjustment coefficient, an objective index value corresponding to each first image is calculated, and the optimal image is obtained in the first image based on the objective index value. In this process, because humans are more sensitive to differences in brightness, the first laboratory color difference, the second laboratory color difference, and the third laboratory color difference are calculated through a preset brightness difference weight adjustment coefficient. This allows for an accurate and effective evaluation of the improvement effect of converting normal images into images suitable for recognition by people with abnormal color vision. Subsequently, based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and the preset color difference adjustment coefficient, the objective index value corresponding to each first image is calculated, and the optimal image is obtained from the first image based on the objective index value. This solves the problem of excessive contrast in the color conversion result. Through the above method, the improvement effect of converting normal images into images suitable for color vision abnormalities can be effectively and accurately evaluated. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 A flowchart illustrating an objective index method for evaluating the improvement of dichromatic contrast provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the effect of converting a normal image into a first image according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0013] It should be noted that the terms "first, second, and third" used in the embodiments of the present invention are only used to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, and third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0014] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which these embodiments of the invention pertain. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0015] Figure 1 This is a flowchart illustrating an objective index method for evaluating the improvement of dichromatic contrast provided in an embodiment of the present invention. The objective index method for evaluating the improvement of dichromatic contrast provided in an embodiment of the present invention can be executed by an electronic device, such as a computer or server.

[0016] like Figure 1 As shown, the objective index methods for evaluating the improvement in dichromatic contrast include: S101. Convert the normal image and the first image represented in the red-green-blue color space into the first converted image and the second converted image represented in the laboratory color space, respectively; the first image is the normal image adjusted to be suitable for recognition by people with color vision deficiency.

[0017] In embodiments of this invention, color vision deficiency is a visual impairment that makes it difficult for patients to distinguish certain color combinations. The most common types are red-green color blindness, blue-yellow color blindness, and the less common total color blindness. A normal image refers to an image taken under standard lighting conditions, without special processing, and conforming to human visual perception. Adjusting the normal image to a first image suitable for individuals with color vision deficiency helps them more easily distinguish color information in the image. The red-green-blue color space is an abbreviation for red, green, and blue, the three primary colors of light. The laboratory color space is CIE 1976. Color space (abbreviated as) A color space is a color space defined to correspond to the characteristics of human vision. Color space has three coordinates. For brightness ( It is black. (It is white) Corresponding to red and green components, Corresponding to the yellow and blue components.

[0018] Furthermore, the RGB values ​​are normalized to the 0-1 range, and a specific transformation matrix (based on the RGB color space definition) is used to convert the normalized RGB values ​​to XYZ values ​​to determine the XYZ value corresponding to the reference white point (e.g., D65). A transformation formula is then applied to convert the XYZ values ​​to Lab* values. Based on the above method, the normal image represented in the red-green-blue color space is converted to the first transformed image, and the first image represented in the red-green-blue color space is converted to the second transformed image.

[0019] like Figure 2 As shown, Figure 2 This is a schematic diagram illustrating the effect of converting a normal image into a first image according to an embodiment of the present invention. A normal image in the RGB color space is converted to the HSL color space (i.e., a hue-saturation-lightness color space, where H represents hue, S represents saturation, and L represents lightness) for hue conversion. One first image is output every 15° of hue. A total of 24 images are obtained, including four types: images that are invisible to those with color vision deficiencies but visible to those with normal color vision; images that are visible to those with color vision deficiencies but invisible to those with normal color vision; images that are visible to both; and images that are invisible to both. Subsequently, an objective evaluation value is calculated for each first image, and the optimal image is selected from the 24 images based on the objective evaluation value.

[0020] S102. Obtain the initial pixel in the first converted image; and calculate the first difference of the first brightness component, the second difference of the first red-green component, and the third difference of the first yellow-blue component corresponding to the initial pixel in the eyes of a person with normal color vision in the first converted image.

[0021] In an embodiment of the present invention, the first brightness component is a first... The first red-green component is the first component. The first yellow-blue component is the first. Components. Normal color vision refers to images observed by a human visual system with normal color vision (i.e., trichromatic vision). The pixels to be examined, i.e., the initial pixels, are selected from the first transformed image. The initial pixels consist of pixel pairs, such as the first pixel pair containing the i-th pixel and the j-th pixel.

[0022] Furthermore, the first difference of the first L* component, the second difference of the first a* component, and the third difference of the first b* component corresponding to the initial pixel in the first transformed image in the eyes of a person with normal color vision are calculated.

[0023] S103. Determine the indistinguishable target pixels in the initial pixels based on the first difference, the second difference, and the third difference.

[0024] In embodiments of the present invention, indistinguishable target pixels refer to two or more different pixels whose differences cannot be clearly perceived by a person with color vision deficiency under certain observation conditions. Based on a first difference, a second difference, and a third difference, further filtering is performed on the initial pixels to obtain indistinguishable target pixels. Target pixels consist of pixel pairs, such as a first pixel pair containing the i-th pixel and the j-th pixel.

[0025] S104. Based on the preset weight adjustment coefficient of brightness difference and the target pixel, calculate the first laboratory color difference, the second laboratory color difference and the third laboratory color difference respectively; the first laboratory color difference and the second laboratory color difference are the color difference of the target pixel in the eyes of a person with normal color vision and the color difference in the eyes of a person with abnormal color vision in the first converted image, respectively; the third laboratory color difference is the color difference of the target pixel in the eyes of a person with abnormal color vision in the second converted image.

[0026] In an embodiment of the present invention, laboratory color difference is the difference between the color perceived by a person with color vision deficiency and its actual value in the laboratory color space. The target pixel in the first converted image is calculated based on a preset weight adjustment coefficient for the lightness difference and the target pixel. The first laboratory color difference and the second laboratory color difference that will be generated in the eyes of a person with normal color vision and a person with color vision deficiency, as well as the third laboratory color difference generated in the eyes of a person with color vision deficiency by the target pixel in the second converted image, reflect the difference in color perception between a person with color vision deficiency and a person with normal color vision.

[0027] S105. Calculate the objective index value corresponding to each first image based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and the preset color difference value adjustment coefficient, and obtain the optimal image in the first image based on the objective index value.

[0028] In embodiments of the present invention, the optimal image is an image that, while maintaining the visual meaning of the normal image, adjusts color information in a normal image that is difficult for individuals with color vision deficiencies to distinguish, and is thus most clearly recognizable by them. Objective index values ​​can be used to evaluate the improvement effect of transforming a normal image into a first image. A preset color difference adjustment coefficient is used. Set to less than 1, calculate the objective index value corresponding to each first image based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory and the preset color difference value adjustment coefficient. Compare the objective index values ​​and find the first image with the best improvement effect among multiple first images, and take it as the optimal image.

[0029] In this experiment, the correlation coefficient between subjective evaluation values ​​and objective evaluation index values ​​of multiple experimental images is calculated based on a pre-set experimental setup. The reliability of the objective evaluation values ​​is then assessed. Pre-set adjustment coefficients for color difference and brightness difference can be set as follows: .

[0030] It is understood that, in the embodiments of the present invention, a normal image and a first image represented in red-green-blue color space are respectively converted into a first converted image and a second converted image represented in Lab color space; the first image is an image of a normal image adjusted to be suitable for recognition by a person with color vision deficiency; initial pixels are obtained in the first converted image; and the first difference of the first brightness component, the second difference of the first red-green component, and the third difference of the first yellow-blue component of the initial pixels in the eyes of a person with normal color vision are calculated in the first converted image; based on the first difference, the second difference, and the third difference, target pixels that are difficult to distinguish are determined in the initial pixels; based on a preset... The first, second, and third laboratory color differences are calculated based on the weighted adjustment coefficients for the brightness difference and the target pixel, respectively. The first and second laboratory color differences represent the color difference of the target pixel in the first converted image as perceived by a person with color vision deficiency and a person with normal color vision, respectively. The third laboratory color difference represents the color difference of the target pixel in the second converted image as perceived by a person with color vision deficiency. Based on the first, second, and third laboratory color differences and preset color difference adjustment coefficients, an objective index value is calculated for each first image, and the optimal image is obtained from the first images based on the objective index value. In this process, because humans are highly sensitive to brightness differences, the first, second, and third laboratory color differences are calculated using preset weighted adjustment coefficients for the brightness difference. This allows for an accurate and effective evaluation of the improvement effect of converting normal images into images suitable for recognition by people with color vision deficiency. Subsequently, based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and the preset color difference adjustment coefficient, the objective index value corresponding to each first image is calculated, and the optimal image is obtained from the first image based on the objective index value. This solves the problem of excessive contrast in the color conversion result. Through the above method, the improvement effect of converting normal images into images suitable for color vision abnormalities can be effectively evaluated.

[0031] In some embodiments of the present invention, obtaining the initial pixel in the first converted image in S102 can be achieved through S1021, as described in the following steps.

[0032] S1021. Set the neighborhood range in the first converted image, and use the pixels contained in the neighborhood range as the initial pixels.

[0033] In some embodiments of the present invention, a domain range is defined in the first transformed image, and all pixels contained within the domain range are used as initial pixels. The initial pixels are composed of pixel pairs, such as the first pixel pair containing the i-th pixel and the j-th pixel.

[0034] In some embodiments of the present invention, S103 can be implemented by S1031, as described in the following steps.

[0035] S1031. Calculate the target weight based on the first difference, the second difference, the third difference and the pixel weight formula, and obtain the target pixel based on the comparison result between the target weight and the preset weight.

[0036] In some embodiments of the present invention, the pixel weight formula is as follows: ; In the above formula, For the target weight, , and These are parameters with positive real values. The first difference, The second difference, The third difference is denoted as 'in', and 'in' is the first transformed image.

[0037] The target weight is used to determine whether a pair of pixels is difficult to distinguish.

[0038] Furthermore, by substituting the first, second, and third differences into the pixel weight formula above, the target weight is obtained. This target weight is calculated when the colors of the i-th and j-th pixels are difficult to distinguish in the eyes of someone with color vision deficiency. It will increase. Therefore, the calculated target weight is compared with the preset weight. When the target weight is not less than the preset weight, the i-th and j-th pixels are regarded as indistinguishable pixels, i.e., the target pixels.

[0039] In an embodiment of the present invention, S104 can be implemented by S1041 to S1044, as described in the following steps.

[0040] S1041. Calculate the second brightness component, the second red-green component, and the second yellow-blue component corresponding to the target pixel in the eyes of a person with normal color vision in the first converted image, and the third brightness component, the third red-green component, and the third yellow-blue component corresponding to the target pixel in the eyes of a person with abnormal color vision.

[0041] S1042. Calculate the fourth brightness component, fourth red-green component, and fourth yellow-blue component corresponding to the target pixel in the eyes of the person with color vision deficiency in the second converted image.

[0042] S1043. Calculate the first laboratory color difference based on the preset weight adjustment coefficient of the lightness difference, the second lightness component, the second red-green component, and the second yellow-blue component; and calculate the second laboratory color difference based on the preset weight adjustment coefficient of the lightness difference, the third lightness component, the third red-green component, and the third yellow-blue component.

[0043] In some embodiments of the present invention, after calculating the second lightness component, the second red-green component, the second yellow-blue component, the third lightness component, the third red-green component, the third yellow-blue component, the fourth lightness component, the fourth red-green component, and the fourth yellow-blue component, the first laboratory color difference is calculated using a preset weighting adjustment coefficient for the lightness difference and a first color difference formula, wherein the first laboratory color difference formula is as follows: ; In the above formula, The second brightness component, and The second red-green component, and The second yellow-blue component, The color difference is due to the first laboratory.

[0044] The target pixel is composed of pixel pairs, such as the first pixel pair containing the i-th pixel and the j-th pixel, and the second brightness component containing... The same applies to the others.

[0045] The second laboratory color difference is calculated using a preset weighting adjustment coefficient for the lightness difference and the second experimental color difference formula, which is as follows: ; In the above formula, and The third brightness component, and The third red-green component, and The third yellow-blue component, This represents the color difference in the second experiment.

[0046] S1044. The third laboratory color difference is calculated based on the preset weight adjustment coefficient of the brightness difference, the fourth brightness component, the fourth red-green component, and the fourth yellow-blue component.

[0047] In some embodiments of the present invention, the third laboratory color difference is calculated based on a preset weighting adjustment coefficient for the lightness difference, a fourth lightness component, a fourth red-green component, a fourth yellow-blue component, and a third experimental color difference formula. The third experimental color difference formula is as follows: ; In the above formula, This is a preset weighting adjustment coefficient for the brightness difference. and The fourth brightness component, and This is the fourth red-green component. and The fourth yellow-blue component, The color difference is due to the third laboratory.

[0048] In some embodiments of the present invention, S105 can be implemented by S1051 to S1053, as described in the following steps.

[0049] S1051. Calculate the first contrast ratio evaluation value based on the color difference adjustment coefficient, the color difference of the third laboratory, the color difference of the first laboratory, and the first contrast ratio evaluation formula.

[0050] In some embodiments of the present invention, the first contrast evaluation formula is as follows: ; In the above formula, The set of target pixels. This is the preset color difference adjustment coefficient. This is the first contrast ratio evaluation value.

[0051] Furthermore, the color difference adjustment factor, the color difference of the third laboratory, and the color difference of the first laboratory are substituted into the first contrast ratio evaluation formula to calculate the first contrast ratio evaluation value.

[0052] S1052. Calculate the second contrast evaluation value based on the color difference adjustment coefficient, the first laboratory color difference, the second laboratory color difference, and the second contrast evaluation formula.

[0053] In some embodiments of the present invention, the second contrast evaluation formula is as follows: ; In the above formula, This is the second contrast ratio evaluation value.

[0054] Furthermore, the color difference adjustment factor, the color difference of the first laboratory and the color difference of the second laboratory are substituted into the second contrast evaluation formula to calculate the second contrast evaluation value.

[0055] S1053. Calculate the objective index value based on the first contrast evaluation value, the second contrast evaluation value, and the objective index value formula.

[0056] In an embodiment of the present invention, the formula for the objective index value is as follows: ; In the above formula, The first contrast ratio evaluation value, This is the second contrast evaluation value. Here, 'out' represents the objective index value, and 'out' represents the second transformed image. This is the preset color difference adjustment coefficient. This is the preset weighting adjustment coefficient for the brightness difference.

[0057] In some embodiments of the present invention, obtaining the optimal image in the first image based on the objective index value in S105 can be achieved through S105a, as described in the following steps.

[0058] S105a. Select the optimal objective evaluation value from the objective evaluation values, and take the first image corresponding to the optimal objective evaluation value as the optimal image.

[0059] In some embodiments of the present invention, each first image corresponds to an objective evaluation value, and the optimal objective evaluation value is selected from the objective evaluation values, and the first image corresponding to the optimal objective evaluation value is taken as the optimal image.

[0060] like Figure 3 As shown, the electronic device may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0061] in: The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.

[0062] Communication interface 504 is used to communicate with other electronic devices or servers.

[0063] The processor 502 is used to execute program 510, specifically the relevant steps in the above method embodiments.

[0064] Specifically, program 510 may include program code that includes computer operation instructions.

[0065] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The smart device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0066] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0067] Specifically, program 510 can be used to cause processor 502 to perform the operations corresponding to the methods described in the above method embodiments.

[0068] The specific implementation of each step in program 510 can be found in the corresponding descriptions of the steps and units in the above method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0069] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of the present invention can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present invention.

[0070] The methods described above according to embodiments of the present invention can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored on a remote recording medium or a non-transitory machine-readable medium and subsequently stored on a local recording medium, downloaded via a network. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0071] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments of the present invention.

[0072] The above embodiments are only used to illustrate the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of the present invention, and the patent protection scope of the embodiments of the present invention should be defined by the claims.

Claims

1. An objective index method for evaluating the improvement of dichromatic contrast, characterized in that, include: The normal image and the first image, represented in the red-green-blue color space, are respectively converted into the first converted image and the second converted image, represented in the laboratory color space. The first image is an image that has been adjusted from the normal image to be recognizable by a person with color vision deficiency; Obtain initial pixels from the first converted image; And calculate the first difference of the first brightness component, the second difference of the first red-green component, and the third difference of the first yellow-blue component of the initial pixel in the eyes of a person with normal color vision in the first converted image; Based on the first difference, the second difference, and the third difference, a target pixel that is difficult to distinguish is determined in the initial pixel; Based on a preset weighting coefficient for brightness difference and the target pixel, a first laboratory color difference, a second laboratory color difference, and a third laboratory color difference are calculated respectively; the first laboratory color difference and the second laboratory color difference are the color difference of the target pixel in the eyes of a person with normal color vision and a person with abnormal color vision in the first converted image, respectively; the third laboratory color difference is the color difference of the target pixel in the eyes of a person with abnormal color vision in the second converted image. Based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and the preset color difference adjustment coefficient, the objective index value corresponding to each first image is calculated, and the optimal image is obtained in the first image based on the objective index value.

2. The method according to claim 1, characterized in that, Obtaining initial pixels in the first converted image includes: In the first transformed image, a neighborhood is defined, and the pixels contained within the neighborhood are used as the initial pixels.

3. The method according to claim 1, characterized in that, The step of determining the indistinguishable target pixel in the initial pixels based on the first difference, the second difference, and the third difference includes: The target weight is calculated based on the first difference, the second difference, the third difference, and the pixel weight formula. The target pixel is then obtained based on the comparison between the target weight and the preset weight. The pixel weight formula is as follows: ； In the above formula, The target weight, , and These are parameters with positive real values. The first difference, This is the second difference. The third difference is denoted as in, and in is the first transformed image.

4. The method according to claim 1, characterized in that, The calculation of the first laboratory color difference, the second laboratory color difference, and the third laboratory color difference based on the preset weight adjustment coefficient of brightness difference and the target pixel includes: The second brightness component, the second red-green component, and the second yellow-blue component corresponding to the target pixel in the eyes of the person with normal color vision, and the third brightness component, the third red-green component, and the third yellow-blue component corresponding to the target pixel in the eyes of the person with abnormal color vision are calculated in the first converted image. Calculate the fourth brightness component, fourth red-green component, and fourth yellow-blue component corresponding to the target pixel in the eyes of the person with color vision deficiency in the second converted image; The first laboratory color difference is calculated based on the preset weight adjustment coefficient of the lightness difference, the second lightness component, the second red-green component, and the second yellow-blue component; and the second laboratory color difference is calculated based on the preset weight adjustment coefficient of the lightness difference, the third lightness component, the third red-green component, and the third yellow-blue component. The third laboratory color difference is calculated based on the preset weight adjustment coefficient of the brightness difference, the fourth brightness component, the fourth red-green component, and the fourth yellow-blue component.

5. The method according to claim 1, characterized in that, The objective index value corresponding to each first image is calculated based on the color difference of the first laboratory, the color difference of the second laboratory, the color difference of the third laboratory, and a preset color difference adjustment coefficient, including: The first contrast evaluation value is calculated based on the color difference adjustment coefficient, the third laboratory color difference, the first laboratory color difference, and the first contrast evaluation formula. The second contrast evaluation value is calculated based on the color difference adjustment coefficient, the first laboratory color difference, the second laboratory color difference, and the second contrast evaluation formula. The objective index value is calculated based on the first contrast evaluation value, the second contrast evaluation value, and the objective index value formula; wherein, the objective index value formula is as follows: ；； In the above formula, The first contrast evaluation value, This is the second contrast evaluation value. The objective index value is denoted as 'out', and the transformed image is 'out'. The preset color difference value adjustment coefficient, This is the preset weighting adjustment coefficient for the brightness difference.

6. The method according to claim 1, characterized in that, The step of obtaining the optimal image from the first image based on the objective index value includes: The optimal objective evaluation value is selected from the objective evaluation values, and the first image corresponding to the optimal objective evaluation value is taken as the optimal image.

Images