CN116309161B - Method and device for improving perceived image color contrast of color vision defect person - Google Patents
Method and device for improving perceived image color contrast of color vision defect person Download PDFInfo
- Publication number
- CN116309161B CN116309161B CN202310273293.XA CN202310273293A CN116309161B CN 116309161 B CN116309161 B CN 116309161B CN 202310273293 A CN202310273293 A CN 202310273293A CN 116309161 B CN116309161 B CN 116309161B
- Authority
- CN
- China
- Prior art keywords
- color
- image
- original image
- pixel
- correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 208000006992 Color Vision Defects Diseases 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000004456 color vision Effects 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims description 38
- 239000003086 colorant Substances 0.000 claims description 21
- 208000036693 Color-vision disease Diseases 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 9
- 230000008447 perception Effects 0.000 claims description 7
- 238000002945 steepest descent method Methods 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 claims 1
- 238000006731 degradation reaction Methods 0.000 claims 1
- 230000004438 eyesight Effects 0.000 abstract description 7
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000004040 coloring Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 201000007254 color blindness Diseases 0.000 description 5
- 230000009466 transformation Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 201000000757 red-green color blindness Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 201000004569 Blindness Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 201000000763 red color blindness Diseases 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
A simple image re-coloring method is provided, and the color perception and visual detail of red-green vision defect people on an image are enhanced. In the color space of L.a.b., the corrected angle and color are determined by calculating the two-channel component values and the initial angle of the original picture pixels, the saturation value between the original image and the corrected image pixels is minimized, and the optimal value, namely the contrast enhancement image, is output. The invention also provides a device for improving the image color contrast under the vision of the color vision abnormality person, and the device is based on the color contrast which is easily confused by the color tone images of the image, so that the color contrast perceived by a normal observer and a color vision defect observer when the same image is seen is the same, and the purpose of improving the image color distinction of the color vision defect person is achieved.
Description
Technical Field
The invention belongs to the technical field of digital image processing, and particularly relates to a method and a device for improving the perceived image color contrast of a color vision defect person.
Background
Humans have the ability to sense color vision, which can perceive the frequency of light reflected from the surface of an object. However, color Vision Defects (CVD) cause a number of inconveniences. There is no clinically specific way to treat or ameliorate color vision deficiency. Therefore, the inconvenience of the person with color vision deficiency can be relieved only from the point of correcting color blindness.
The approach proposed by Rasche is to use affine transformations to preserve the perceived color differences between all color pairs, with the differences between the aliased color pairs as the primary target. But this approach does not capture multi-directional color changes nor ensure that the mapped colors are within the available color gamut. A technique for reducing the dimension of the color gamut while preserving visual detail, and a color quantization method are then presented to solve the color gamut problem, also known as delivering the recoloured image content with added information to the undercoloured viewer by a constrained multivariate optimization procedure. Jefferson first proposed a new method of selecting key colors using the difference between the two histograms, using a method of preprocessing conjugate gradients to optimize the combined objective function to preserve brightness, contrast, color in the gamut range, and its naturalness. A new algorithm is then proposed which shifts the chromaticity variation map of the defect cone to the other two functional cones. Huang JB proposes an improved recolouring algorithm that uses Gaussian Mixture Models (GMMs) to represent colour information, the centre of each gaussian distribution being similar to the key colours of the previous method, measuring the contrast between the two key colours by calculating the KL-divergence, interpolating the colours according to the posterior probability of each gaussian distribution and the corresponding mapping to ensure that the local colours are smooth in the recoloured image.
Lee et al have improved classical linear transformation based simulation methods using blur parameters to simulate different degrees of color vision defects to improve the visual quality of individuals with color vision disturbances. Lau proposes a cluster-based approach to optimize the conversion of individual images, enhancing contrast in the compensated image by adjusting the color distribution in the target color gamut. Wang En et al propose a color blindness correction method based on image geometric transformation mapping, which performs corresponding geometric transformation on each plane of a color space according to the color proportions on both sides of the color plane in the image, and divides different color mapping areas, and generates an image with easily resolved colors through color transformation, but changes the overall color of the image, thereby interfering the cognition of the color vision impaired person on the original color. Milic proposes a color correction method based on a confusion line, the idea of which is to firstly group the colors of an input image by using chromaticity information and calculate the center color of each group, if two or more colors are distributed on the same confusion line, it is necessary to consider the image content and the color distribution and then remap the center color to the opposite direction of the confusion line vertical direction, and finally, calculate other colors in the group by using the remapped center color. The Milic approach sets the range of remapping of the center color to avoid new aliasing colors in the center color, but not in other colors than the center color. Tennenholtz proposes a natural contrast enhancement technique based on similarity, uses a similarity graph to explain details of image loss, measures similarity difference of each region of an image according to differences of variances of each pixel and neighborhood pixel values in an original image and a simulation image, thereby determining a confusing region, only changing partial regions, and enhancing color contrast. He Zhiliang et al combine K-means and systematic clustering algorithm to divide the original image, and regard Euclidean distance of the color in each area under LAB color space as the standard to measure the similarity of the color, and then confirm the area that the color of red green blindness is confused, replace this area with the color that the luminance is unanimous and the color is distinguished degree greatly, thus realize the purpose of color blindness image correction. Because of the need to segment the image, the speed of the algorithm is less than ideal for larger size images.
In addition to being able to modify the hue of an image Tanaka also proposes an efficient luminance modification method, in practice an optimization problem for defining the luminance component by the color differences in the input image. Later, suetake et al only carried out brightness correction around the object outline by considering the brightness correction of the C-O effect to achieve the Craik-O' Brien effect of the dichroism, but there was still room for improvement for some indistinguishable portions of the brightness modifier.
Disclosure of Invention
In order to overcome the drawbacks of the prior art, an object of the present invention is to provide a method and apparatus for improving the perceived image contrast of a color vision deficiency, which transfers the color information of the image deficiency axis to the normal axis based on the image color difference, and retains the color information and details of the image to the greatest extent, thereby indirectly improving the color resolution and perception level of the color vision deficiency, so that the perceived level of the color contrast of the same image by a normal triple-vision observer and the color vision deficiency observer is substantially the same.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a method for improving the perceived image color contrast of a color vision deficient person, comprising the steps of:
step 1, at L * a * b * Calculating pixels of the original image in a color space to obtain a of different pixel points * Component value sum b * Component values, calculating saturation difference between two pixels; the original image is a color image under the color vision of a normal triple viewer;
and 2, performing color correction on the original image by using a rotation operation, wherein the method comprises the following steps of:
step 21, pixel-by-pixel a according to the original image * Component value sum b * Component value and each pixel is at a * b * In plane with a * The initial angle of the shaft, determining a correction angle;
step 22, according to the correction angle and a * Component value sum b * The component values determine correction colors, and after the correction colors are determined, angle correction is performed;
and step 23, optimizing the obtained result by using a steepest descent method to obtain an optimal output image.
And step 1, calculating Euclidean distance of every two pixels in the original image, wherein the Euclidean distance is the saturation difference between every two pixels.
The step 21 uses the rotation operation to determine the required correction angle value for the color of the original image, and the step 22 determines the correction color according to the corrected angle, so as to enhance the contrast ratio of the confusing color and improve the perception level of the color vision defect person on the image.
The present invention also provides an apparatus for improving the perceived image color contrast of a color vision deficient person, comprising:
the input module is used for inputting an original image and a color vision defect simulation image, and judging whether a two-viewer can correctly distinguish the color of the image, namely, whether the image needs to be subjected to color correction or not;
the operation module is used for executing the method for improving the color contrast of the perceived image of the color vision defect person, and obtaining an optimal output image according to the original image;
the output module is used for outputting the optimal output image;
and the communication module is used for data transmission between the input module and the operation module and between the operation module and the output module.
Compared with the prior art, the invention has the beneficial effects that:
(1) Unlike other available method, the present invention has no change in image brightness, only change in hue of the image, and raised color resolution of the color vision defect.
(2) The invention uses the steepest descent method to solve the optimal solution, and the method is simple and efficient and has high operation speed.
Drawings
Fig. 1 is a flow chart of the present invention.
Fig. 2 shows images used in an embodiment of the present invention, where (a) is an original image, (b) is a red blind analog image, and (c) is a green blind analog image.
Fig. 3 shows the results of an embodiment of the present invention, wherein (a) is a color corrected image and (b) is a red blind simulated image after color correction.
Fig. 4 shows the results of an embodiment of the invention, wherein (a) is a color corrected image and (b) is a color corrected green blind simulated image.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.
The invention mainly aims to study the image which is difficult to distinguish by the color of the color vision defect person, and the color contrast is enhanced by correcting the color of the image, so that the color resolution and the identification of the color vision defect person on the image are realized, and the perceptibility of the color vision defect person and a normal observer on the same image is the same, thereby improving the perception level of the color vision defect person.
Specifically, referring to fig. 1, the method for improving the color vision defect perceived image color contrast of the present invention modifies the chromaticity value of the image pixel, thereby enhancing the contrast of the image color, and achieving the purpose of color vision correction, and comprises the following steps:
step 1, at L * a * b * Calculating pixels of the original image in a color space to obtain a of different pixel points * Component value sum b * Component values, and calculates the saturation difference between two pixels. In the invention, the original image is a color image under the color vision of a normal triple viewer.
For example, the saturation difference between two pixels is the euclidean distance between two pixels in the original image.
And 2, determining a required correction angle value for the color of the original image by using rotation operation, and determining a correction color according to the corrected angle so as to enhance the contrast ratio of the confusing color, improve the perception level of the color vision defect person on the image, and enhance the contrast ratio of the confusing color so as to improve the perception level of the color vision defect person on the image. The method comprises the following specific steps:
step 21, pixel-by-pixel a according to the original image * Component value sum b * Component value and each pixel is at a * b * In plane with a * The initial angle of the shaft, determining a correction angle;
step 22, according to the correction angle and a * Component value sum b * The component values determine correction colors, and after the correction colors are determined, angle correction is performed;
a between the red-green color blindness pair original image color and perceived color * The components have a weaker correlation. That is, in perception of a person with loss of color vision, a * The original color information in (a) is significantly lost. The information on the axis can thus be transferred toWill be a * Mapping information of (c) to b in CIELAB color space * On the shaft. Calculating saturation difference between ith pixel and jth pixel of original image, and determining initial angle theta according to corresponding pixel value i And a corrected angle θ' i And calculating saturation differences among pixels of the corrected image.
a′ i * ＝C ij *cos(θ′ i )
b′ i * ＝C ij *sin(θ′ i )
a′ j * ＝C ij *cos(θ′ j )
b′ j * ＝C ij *sin(θ′ j )
Wherein C is ij Is that the ith pixel and the jth pixel in the original image are in a * b * Saturation difference in plane, C' ij Is that the ith pixel and the jth pixel in the recoloured image are in a * b * Saturation difference on plane;a is the i-th pixel in the original image * Component value sum b * Component value,/->A is the j-th pixel in the original image * Component value sum b * Component values, a' i * ,b′ i * Is the ab channel component value, a ', of the ith pixel in the color corrected image' j * ,b′ j * Is the ab channel component value of the j-th pixel in the image after color correction; a, a i * And a' i * Represents the component from green to red, +.>And b' i * Representing the blue to yellow component.
θ i 、θ j Respectively, the ith pixel and the jth pixel in the original image are in a * b * In plane with a * Initial angle of axis, θ' i To theta i Corrected angle, θ' j To theta j The corrected angle;
wherein the method comprises the steps ofIs a unit vector with a direction of 0 deg.. />For vector->Sum vector->Is included in the bearing. sign (x) is a function defining a sign, which is defined as
Wherein delta ij The absolute value of cosine of the initial angle is obtained by taking alpha as a parameter, taking a real number, and the absolute value is represented by the absolute value.
And step 23, optimizing the obtained result by using a steepest descent method to obtain an optimal output image.
The color correction objective function is defined as:
objective functionThe aim is to minimize the saturation difference between the color corrected image and the original image, thereby minimizing the difference between the corrected image and the original image; where n is the number of pixels of the original image.
To be used forThe optimal solution of the objective function is obtained by using the steepest descent method and is expressed as follows:
f is the result obtained by the most rapid descent method and θ i (k+1) Represents θ i The result of the (k+1) th iteration, θ j (k+1) Represents θ j The result of the (k+1) th iteration, θ i (k) Represents θ i The k-th iteration result, θ j (k) Represents θ j The k-th iteration result; mu (mu) 1 、μ 2 Respectively the parameter theta i And parameter theta j Is an iterative update amount mu 1 (k) Is the parameter theta i The k-th iteration update amount, μ 2 (k) Is the parameter theta j When the threshold value is smaller than the given parameter epsilon, the objective function obtains the optimal solution to obtain a color corrected image closest to the original image and also an output image.
The experimental images of the invention are shown in fig. 2-4, and the source Dan Yuanshi of the test image is a color blindness detection chart. The images in fig. 2 are respectively:
(a) The original image, namely the figure "6" can be observed under the color vision of the normal triple-vision person, and the figure or pattern can not be read under the color vision of the red color blindness and the green color blindness.
(b) The simulation image simulates a color image under the vision of a person with abnormal color vision, and information in the image is unrecognizable to the person with the color blindness.
(c) The simulation image simulates a color image under the vision of a color vision abnormality person, and information in the image is unrecognizable to a green blind crowd.
The images in fig. 3 are respectively:
(a) Color corrected images, i.e. color contrast enhanced images.
(b) After the color correction, the red blind simulation image can read the number of '6' from both a normal triple-vision person and a color vision defect person after the color contrast is enhanced.
The images in fig. 4 are respectively:
(a) Color corrected images, i.e. color contrast enhanced images.
(b) After the color correction, the green blind simulation image can read the number of '6' from both the normal triple vision person and the color vision defect person after the color contrast is enhanced.
Therefore, after the image which is originally incapable of distinguishing the colors of the color vision defect person is processed by the method, namely, after the colors of the image are corrected, the red-green color blindness can successfully acquire the information and the details in the image, and the purpose of distinguishing the correct colors of the color vision defect person can be achieved.
The invention also provides a corresponding device, which comprises:
the input module is used for inputting an original image and a color vision defect simulation image, and judging whether a two-viewer can correctly distinguish the color of the image, namely, whether the image needs to be subjected to color correction or not;
the operation module is used for executing the method for improving the color contrast of the perceived image of the color vision defect person, and obtaining an optimal output image according to the original image;
the output module is used for outputting the optimal output image;
and the communication module is used for data transmission between the input module and the operation module and between the operation module and the output module.
In the present invention, the input module may be a camera, such as a computer camera, a smart phone camera, or a camera matched with a wearable device. The computing module may obviously be carried on various types of processors, such as those of smartphones, or VR devices and other wearable devices. The output module is a display screen for displaying images, such as a computer display screen, a smart phone display screen, or display screens of some VR devices.
Specifically, when the input module is a computer camera, the operation module is carried on the computer processor, and the output module is a computer display screen. When the input module is a camera of the smart phone, the operation module is loaded on a processor of the smart phone, and the output module is a display screen of the smart phone. When the input module is a camera of the wearable device, the operation module can be carried on a processor of a computer, a smart phone or an intelligent VR device, and the output module can be a display screen of the computer, the smart phone or the VR device.
In the test process of the invention, intel (R) Core (TM) i5-8250U CPU@1.60GHz1.80GHzs is adopted as a processor, and the processor has 8GB of memory and GPU: NVIDIA GeForce 940MX may be able to meet the computational requirements.
In summary, the invention provides a simple image re-coloring method, which enhances the color perception and visual details of the image by red-green vision deficiency people. In the color space of L.a.b., the corrected angle and color are determined by calculating the two-channel component values and the initial angle of the original picture pixels, the saturation value between the original image and the corrected image pixels is minimized, and the optimal value, namely the contrast enhancement image, is output. The invention also provides a device for improving the image color contrast under the vision of the color vision abnormality person, and the device is based on the color contrast which is easily confused by the color tone images of the image, so that the color contrast perceived by a normal observer and a color vision defect observer when the same image is seen is the same, and the purpose of improving the image color distinction of the color vision defect person is achieved.
Claims (8)
1. A method for improving the perceived image color contrast of a color vision deficient subject, comprising the steps of:
step 1, at L * a * b * Calculating pixels of the original image in a color space to obtain a of different pixel points * Component value sum b * Component values, calculating saturation difference between two pixels; the original image is a color image under the color vision of a normal triple viewer;
and 2, performing color correction on the original image by using a rotation operation, wherein the method comprises the following steps of:
step 21, pixel-by-pixel a according to the original image * Component value sum b * Component value and each pixel is at a * b * In plane with a * The initial angle of the shaft, determining a correction angle;
step 22, according to the correction angle and a * Component value sum b * The component values determine correction colors, and after the correction colors are determined, angle correction is performed;
step 23, optimizing the obtained result by using a steepest descent method to obtain an optimal output image;
step 2 color correction objective functionThe definition is as follows:
wherein:
a′ i * ＝C ij *cos(θ′ i )
b′ i * ＝C ij *sin(θ′ i )
a′ j * ＝C ij *cos(θ′ j )
b′ j * ＝C ij *sin(θ′ j )
objective functionThe aim is to minimize the saturation difference between the color corrected image and the original image, thereby minimizing the difference between the corrected image and the original image; where n is the number of pixels of the original image, C ij Is that the ith pixel and the jth pixel in the original image are in a * b * Saturation difference in plane, C' ij Is that the ith pixel and the jth pixel in the recoloured image are in a * b * Saturation difference on plane; />A is the i-th pixel in the original image * Component value sum b * Component value,/->A is the j-th pixel in the original image * Component value sum b * Component values, a' i * ,b′ i * Is the ab channel component value, a ', of the ith pixel in the color corrected image' j * ,b′ j * Is the ab channel component value of the j-th pixel in the image after color correction; a, a i * And a' i * Represents the component from green to red, +.>And b' i * Representing a component from blue to yellow; θ i 、θ j Respectively, the ith pixel and the jth pixel in the original image are in a * b * In plane with a * Initial angle of axis, θ' i To theta i Corrected angle, θ' j To theta j The corrected angle;
wherein the method comprises the steps ofIs a unit vector with a direction of 0 DEG, +.>To the direction ofQuantity->Sum vector->Sign () is a function defining a symbol, defined as:
δ ij the absolute value of cosine of the initial angle is obtained by taking alpha as a parameter, taking a real number, and the absolute value is represented by the absolute value.
2. The method according to claim 1, wherein step 1 calculates euclidean distance between every two pixels in the original image, i.e. the saturation difference between the pixels.
3. The method according to claim 1 or 2, wherein the step 21 uses a rotation operation to determine a required correction angle value for the color of the original image, and the step 22 determines a correction color according to the corrected angle, so as to enhance the contrast of the confusing color and improve the perception level of the color vision defect.
4. The method for improving the color contrast of a color vision-deficient person's perceived image according to claim 1, wherein the method is characterized byAs an objective function and utilizing the fastestThe method for obtaining the optimal solution of the objective function by the degradation method is expressed as follows:
θ i (k+1) ＝θ i (k) +μ 1 (k)
θ j (k+1) ＝θ j (k) +μ 2 (k)
f is the result obtained by the most rapid descent method and θ i (k+1) Represents θ i The result of the (k+1) th iteration, θ j (k+1) Represents θ j The result of the (k+1) th iteration, θ i (k) Represents θ i The k-th iteration result, θ j (k) Represents θ j The k-th iteration result; mu (mu) 1 、μ 2 Respectively the parameter theta i And parameter theta j Is an iterative update amount mu 1 (k) Is the parameter theta i The k-th iteration update amount, μ 2 (k) Is the parameter theta j When the threshold value is smaller than the given parameter epsilon, the objective function obtains the optimal solution to obtain a color corrected image closest to the original image and also an output image.
5. An apparatus for improving the perceived contrast of color of an image by a color vision deficiency, comprising:
the input module is used for inputting an original image and a color vision defect simulation image, and judging whether a two-viewer can correctly distinguish the color of the image, namely, whether the image needs to be subjected to color correction or not;
an operation module, configured to execute the method for improving color contrast of a color vision deficiency person perceived image according to any one of claims 1 to 4, and obtain an optimal output image according to the original image;
the output module is used for outputting the optimal output image;
and the communication module is used for data transmission between the input module and the operation module and between the operation module and the output module.
6. The device for improving the color contrast of an image perceived by a color vision deficiency of a person according to claim 5, wherein the input module is a computer camera, the operation module is mounted on a computer processor, and the output module is a computer display screen.
7. The device for improving the color contrast of an image perceived by a color vision deficiency of a mobile phone according to claim 6, wherein the input module is a camera of the mobile phone, the operation module is mounted on a processor of the mobile phone, and the output module is a display screen of the mobile phone.
8. The apparatus for improving color vision deficiency person perceived image color contrast according to claim 6, wherein the input module is a camera of a wearable device, the operation module is mounted on a processor of a computer, a smart phone or a smart VR device, and the output module is a display screen of the computer, the smart phone or the VR device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310273293.XA CN116309161B (en) | 2023-03-17 | 2023-03-17 | Method and device for improving perceived image color contrast of color vision defect person |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310273293.XA CN116309161B (en) | 2023-03-17 | 2023-03-17 | Method and device for improving perceived image color contrast of color vision defect person |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116309161A CN116309161A (en) | 2023-06-23 |
| CN116309161B true CN116309161B (en) | 2024-03-19 |
Family
ID=86835757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310273293.XA Active CN116309161B (en) | 2023-03-17 | 2023-03-17 | Method and device for improving perceived image color contrast of color vision defect person |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116309161B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184149A (en) * | 2006-11-14 | 2008-05-21 | 富士施乐株式会社 | Color processing apparatus and method |
| CN103593830A (en) * | 2013-11-29 | 2014-02-19 | 大连理工大学 | Low-light video image reinforcing method |
| CN106249406A (en) * | 2016-08-30 | 2016-12-21 | 喻阳 | Improve Color perception and correct artificial intelligence's lens and the method for designing of achromatopsia color weakness vision |
| CN106504212A (en) * | 2016-11-07 | 2017-03-15 | 湖南源信光电科技有限公司 | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement |
| CN107438178A (en) * | 2016-05-25 | 2017-12-05 | 掌赢信息科技（上海）有限公司 | A kind of image color antidote and electronic equipment |
| CN109300169A (en) * | 2018-09-06 | 2019-02-01 | 华东师范大学 | A kind of translucent image color transfer method based on linear transformation |
| CN110276727A (en) * | 2019-05-21 | 2019-09-24 | 杭州电子科技大学 | A kind of color image color Enhancement Method towards dyschromatopsia |
| EP3809327A1 (en) * | 2019-10-16 | 2021-04-21 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Subject recognition method, electronic device, and computer readable storage medium |
| CN114375569A (en) * | 2020-08-14 | 2022-04-19 | 华为技术有限公司 | Method and related device for processing image |
| CN115345788A (en) * | 2022-07-22 | 2022-11-15 | 内蒙古工业大学 | Method and device for improving image color contrast under vision of abnormal color vision person |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8712151B2 (en) * | 2011-02-14 | 2014-04-29 | Intuitive Surgical Operations, Inc. | Method and structure for image local contrast enhancement |
-
2023
- 2023-03-17 CN CN202310273293.XA patent/CN116309161B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101184149A (en) * | 2006-11-14 | 2008-05-21 | 富士施乐株式会社 | Color processing apparatus and method |
| CN103593830A (en) * | 2013-11-29 | 2014-02-19 | 大连理工大学 | Low-light video image reinforcing method |
| CN107438178A (en) * | 2016-05-25 | 2017-12-05 | 掌赢信息科技（上海）有限公司 | A kind of image color antidote and electronic equipment |
| CN106249406A (en) * | 2016-08-30 | 2016-12-21 | 喻阳 | Improve Color perception and correct artificial intelligence's lens and the method for designing of achromatopsia color weakness vision |
| CN106504212A (en) * | 2016-11-07 | 2017-03-15 | 湖南源信光电科技有限公司 | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement |
| CN109300169A (en) * | 2018-09-06 | 2019-02-01 | 华东师范大学 | A kind of translucent image color transfer method based on linear transformation |
| CN110276727A (en) * | 2019-05-21 | 2019-09-24 | 杭州电子科技大学 | A kind of color image color Enhancement Method towards dyschromatopsia |
| EP3809327A1 (en) * | 2019-10-16 | 2021-04-21 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Subject recognition method, electronic device, and computer readable storage medium |
| CN114375569A (en) * | 2020-08-14 | 2022-04-19 | 华为技术有限公司 | Method and related device for processing image |
| CN115345788A (en) * | 2022-07-22 | 2022-11-15 | 内蒙古工业大学 | Method and device for improving image color contrast under vision of abnormal color vision person |
Non-Patent Citations (4)
| Title |
|---|
| Calculation of color difference and measurement of the spectrum of aerosol based on human visual system;Mengyan Dai 等;《SPIE》;20171024;1-9 * |
| 基于图像处理的色盲辅助矫正方法研究;刘雨君;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20220115(第01期);E073-252 * |
| 基于生成对抗网络的色觉测试图合成研究;郭斌全;《中国优秀硕士学位论文全文数据库信息科技辑》;20210515(第05期);I138-869 * |
| 基于色差模型的色觉缺陷图像辅助识别研究;赵航;《中国优秀硕士学位论文全文数据库信息科技辑》;20170315(第03期);I138-4772 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116309161A (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Smith et al. | Apparent greyscale: A simple and fast conversion to perceptually accurate images and video | |
| CN109979401B (en) | Driving method, driving apparatus, display device, and computer readable medium | |
| US8355574B2 (en) | Determination of main object on image and improvement of image quality according to main object | |
| CN109147005B (en) | Self-adaptive dyeing method and system for infrared image, storage medium and terminal | |
| CN102663741B (en) | Method for carrying out visual stereo perception enhancement on color digit image and system thereof | |
| Ribeiro et al. | Recoloring algorithms for colorblind people: A survey | |
| CN109801233B (en) | Method for enhancing true color remote sensing image | |
| US11044450B2 (en) | Image white balancing | |
| US7599553B2 (en) | Image processing apparatus and method that perform color matching using detected uniformity | |
| CN112614060A (en) | Method and device for rendering human face image hair, electronic equipment and medium | |
| US20020085752A1 (en) | Image processing apparatus and method | |
| CN115115554B (en) | Image processing method and device based on enhanced image and computer equipment | |
| CN111161683B (en) | Image processing method, image processor and display device | |
| CN107592909B (en) | Method for generating reduced reflectance contrast images and apparatus therefor | |
| CN107949862A (en) | Image processor | |
| CN113436284A (en) | Image processing method and device, computer equipment and storage medium | |
| CN114202491B (en) | Method and system for enhancing optical image | |
| CN116309161B (en) | Method and device for improving perceived image color contrast of color vision defect person | |
| WO2022120799A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN114266803A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN109119046B (en) | Adjusting system and adjusting method for gray scale brightness and memory | |
| CN112614471B (en) | Tone mapping method and system | |
| KR20160001897A (en) | Image Processing Method and Apparatus for Integrated Multi-scale Retinex Based on CIELAB Color Space for Preserving Color | |
| Shen et al. | A content‐dependent Daltonization algorithm for colour vision deficiencies based on lightness and chroma information | |
| Shih et al. | Enhancement and speedup of photometric compensation for projectors by reducing inter-pixel coupling and calibration patterns |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |