CN101036606A - Method for rectifying the daltonism on the basis of self-adapted mapping - Google Patents
Method for rectifying the daltonism on the basis of self-adapted mapping Download PDFInfo
- Publication number
- CN101036606A CN101036606A CN 200710039657 CN200710039657A CN101036606A CN 101036606 A CN101036606 A CN 101036606A CN 200710039657 CN200710039657 CN 200710039657 CN 200710039657 A CN200710039657 A CN 200710039657A CN 101036606 A CN101036606 A CN 101036606A
- Authority
- CN
- China
- Prior art keywords
- color
- mapping
- image
- face
- original image
- 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.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of image process and the vision resume, specifically a Daltonism antidote based on the adaptive mapping. The method firstly builds a Daltonism simulation model, then makes the analysis process on the original image, to divide the project area according to the obtained number of color and the color distribution, finally builds the one-to-one mapping relation from the normal color space to the color blindness color surface according to the size of the color frequence and the projecting, and rectifies the original image according to mapping relation. The aim of the invention is to advance the ability of distinguishing the color for the Daltonism antidote, to make the information not displayed in the original image clearly display in the rectified image and the image process is carried through outside the eye, which does not damage the eyes, thereby having stronger feasibility about the cure and the rectification for the Daltonism.
Description
Technical field
The invention belongs to Flame Image Process and recovery of vision technical field, be specifically related to a kind of anerythrochloropsia antidote based on the self adaptation mapping.
Technical background
Achromatopsia and color weakness are the vision diseases of harm humans health, and it has brought adverse effect to patient's daily life, a lot of restraints of trade entering of achromate.Research to achromatopsia, color weakness is more with the research of physiology and medical science aspect, but does not have to propose to treat preferably the effective way of this vision disease all the time.According to statistics, the male who suffers from achromatopsia or color weakness has 8% approximately, and the women has 0.5% approximately.The sensitization pyramidal cell that the reason of the overwhelming majority achromatopsia and color weakness is to transmit on the retina colouring information unusually or incomplete so that shortage is distinguished certain or certain varicolored ability.It mainly shows is to distinguish some colors well.The difference obvious color is very similar in achromatopsia and color weakness patient in a lot of normal visions, even can not make a distinction fully.Achromatopsia can be divided into achromatopsia and partial color blindness (dichromat) again by clinical manifestation, because achroous ratio is very little, the achromatopsia of being mentioned in the literary composition of back all is meant partial color blindness (being the dichromat).Partial color blindness is divided into protanopsia, deuteranopsia and tritanopsia again according to the unusual difference of cone cell, and wherein the ratio that accounts for of protanopsia and deuteranopsia is maximum, therefore we mainly study in this literary composition to as if protanopsia and deuteranopsia.
According to the triple channel model of vision, model [4]-[7 of much achromate's vision being studied] have been set up.These models have nothing in common with each other, but they have a something in common, all be to start with from the triple channel of vision with setting up, so these models all have certain interlinking, and optional wherein a kind of model carries out corrigent method and can be generalized to other models.Present stage utilizes these scale-model investigation achromatopsia, color weakness treatment or corrigent method to have much, as document [8]-[11], but also practicable without comparison treatment or antidote.Some method has related to the operation of people's intraccular part, also only has theory significance at present.By the technology of being handled by the image before the eyes perception is come achromatopsia is corrected, to improve the ability that achromatopsia loyalty person obtains colouring information, the needs of more realistic application.
From the principle angle, the achromate lacks the sensitization pyramidal cell, but is not the effect of removing a certain photoreceptor cell simply, but the result of various cell comprehensive functions.We do not go to inquire into from biological angle at this, cause the undistinguishable reason of some color but go to analyze from its mathematical model, are the example explanation below with the protanopsia.The protanopsia simplified model formula (4) that provides from above as can be known, be mapped on the plane of R=G in the color of RGB cubic space direction along the L axle, be mapped on the same point at the axial color relation of L like this, therefore the color in this direction must just be confused, for example red and green just on this direction, so protanopsia can not make a distinction red and green.Because the color on the just R=G face that protanopsia can be seen, have a look at outer Flame Image Process if come round, make protanopsia see that with the same color of normal person be impossible, but we can improve the protanopsia patient obtains information from image ability by the distribution that changes the color in the original image, and those color differentiatings of obscuring are easily come.Briefly, improve resolution exactly, and reduce low even not have the resolution of the color of appearance those frequencies of occurrences to the high color of the frequency of occurrences in the image.Reach above purpose, we will set up a kind of man-to-man mapping relations from the RGB color cube to R=G color face, and making does not have same color on two or more the color corresponding color face in the cube.The number of colours of different images, distribution of color difference are so the mapping relations of setting up also are different.Image after correcting there is the following requirement: still far away as far as possible after the colour switching of still approaching as far as possible after the near colour switching of original color space distance, distance.Relation between the distribution of color of the image after feasible like this rectification has kept the similarity with former figure, has improved the discrimination of color simultaneously.
According to above-mentioned requirements, the present invention proposes anerythrochloropsia antidote based on self adaptation mapping, improved the ability that anerythrochloropsia patient differentiates color and obtain colouring information from image effectively.
Summary of the invention
The objective of the invention is to propose a kind of anerythrochloropsia antidote, to improve the ability that the anerythrochloropsia patient differentiates color and obtain information from image based on the self adaptation mapping.
The step of the inventive method is: at first the achromatopsia model is carried out emulation, then original image being carried out sublevel handles, and mark off view field, and set up the mapping table of a normal color space in view of the above to achromatopsia color face, according to mapping table original image is corrected.
Below content of the present invention is further introduced:
1, sets up the simulation simplified model of achromatopsia
Normal person's eyes have three kinds of cone photoreceptor cells, are respectively L, M, S bores cell, the LMS spatial model [1] of these three kinds of cellularity eye-observation colors.We are converted to the LMS space with formula (1) for RGB image (R, G, B are respectively the red, green, blue component of color) commonly used
Achromatopsia, color weakness are that the variation by three kinds of pyramidal cell absorption characteristics causes.For protanopsia, when the color transition of RGB was the LMS space, it had been mapped to the color of RGB cubic space [2]-[3] (as Fig. 1) on the plane of R=G along the direction of L axle, can be represented by formula (2).
Therefore the color seen of protanopsia all concentrates on the plane of R=G, and this plane is called red-blind color face.On spatial color map to a face, most of colors can be lost.All all have been projected to same point along the axial color of L, have so just caused along the obscuring of L direction of principal axis color, and red and green is just in time in that this side up, so caused red green can not the differentiation.Similarly, for deuteranopsia, it is that the cubical color of RGB has been arrived [2]-[3] (as Fig. 2) on the plane of R=G along the direction projection of M axle, and the plane of R=G also is deuteranopic color face.
LMS is the color-aware space of people's intraccular part, differentiates the effect of color in order to observe anerythrochloropsia, and we are transformed into rgb space from the LMS space again with color, and the perception phantom that obtains achromatopsia at last is suc as formula (3)
Through calculating, obtain red-blind simplified model suc as formula (4)
Deuteranopic simplified model is suc as formula (5)
R, G, B are respectively the red, green, blue component of color in the above formula; L, M, S are the absorption value of three kinds of pyramidal cells on the retina; R
p, G
p, B
p, R
d, G
d, B
dBe respectively the RGB component of the color that protanopsia and deuteranopsia see; U is the transformation matrix from the rgb space to LMS; T
pFor protanopsia at the spatial projective transformation matrix of LMS, T is the general type of achromatopsia at the spatial projective transformation matrix of LMS.
2, mapping table is set up in sublevel processing and self adaptation mapping
Because each color component is with 8 binary representations in the general RGB image, each component has 256 rank, then in the RGB color space just to having 256
3Plant color, the sum of color is very huge like this, has brought very big operand for follow-up Flame Image Process work.So existing exponent number is compressed, the color component of establishing after the compression is the l rank, is equally divided into the l five equilibrium to 256, gets its intermediate value in by stages such as every and represents this interval color component, and l is just arranged in color space like this
3Plant color.It is too big that the l value can not be got, can not be too little, and the operand of too big Flame Image Process will be very huge, image after too little sublevel is handled can distortion, comprehensive above reason, generally get 1 be the integer of 8-16 for well, 512 kinds of color to 4096 kind of colors are then just arranged in the color space.
The self adaptation mapping is meant the number of colours that is decided mapping face by the number of colours in the image, and divide different mapping area for the color of R>G and R≤G, the Euclidean distance of color is set up man-to-man mapping relations, the generally speaking different different mapping relations of image correspondence on the frequency that occurs according to every kind of color and they and the mapping face then.After the processing of original image sublevel, count total number of colours n in image this moment earlier
0, the number of times f that occurs of every kind of color
nAnd the spatial number of colours n of R>G
1, the spatial number of colours n of R≤G
2Then according to n
0, n
1, n
2The mapping face of division is in order to make n
0Plant color and can both project on the mapping face, the exponent number that two coordinate axess of mapping face are divided is k=[n
0 1/2K then can be represented on the mapping face altogether in]+1
2Plant color.The division of view field is by n on the mapping face
1, n
2Decision is at first to the k on the mapping face
2The ordering of kind of color is lined by line scan from the initial point (black) of mapping face along the direction of R=G axle until the summit (white) in the upper right corner of mapping face, and to the ordering of the color on the color face, first be black according to the order of this scanning, and last is white.Then the preceding n on the mapping face
1Plant color assignment and give the space of R>G, remaining k
2-n
1Plant color assignment and give the space (as shown in Figure 3) of R≤G, make the color of original R>G and R≤G lay respectively at the zones of different of mapping face like this, cause the color relation of obscuring to distinguish significantly easily.
Just come to determine the sequencing of mapping according to the frequency of color, the resolution of the high color of frequency is greatly improved, the whole resolution of this sampled images has also just obtained very big raising.So, after view field has divided, respectively of the big minispread of the color of R>G, R≤G in the native color space according to the color frequency of occurrences.Color for the R>G after the ordering, from the color that makes number one, it is corresponding with it to choose the nearest color of Euclidean distance in its corresponding view field, selected color relation removes from the colors list of view field, again remaining color is done similar operations successively, up to the color of all R>G in native color space all till its corresponding view field finds corresponding color.In like manner, also find corresponding with it color, for the k that has more in the view field from its corresponding view field for the color of R≤G
2-n
0Plant color, it is corresponding with it to no longer include the spatial color of R≤G, need not handle.So just, set up the man-to-man color map relation table of a normal color space to achromatopsia color face.Because distribution of color difference in the different images, resulting mapping table is also all different.
3, according to the mapping table of above-mentioned gained, the color of all pixels in the conversion original image just can obtain corrigent image.
Description of drawings
Fig. 1 is that the rgb space color is along L direction of principal axis projection.L, M, S are respectively LMS space coordinates component, and O is the corresponding black of initial point, and R is red (Red), G is green (Green), and B is blue (Bluc), and W is a white (White), Y is yellow (Yellow), and C is cyan (Cyan), and Ma is carmetta (Magenta).
Fig. 2 is that the rgb space color is along M direction of principal axis projection.
The division figure of Fig. 3, R=G color face.
Fig. 4, Fig. 5 and Fig. 6 are respectively the emulation of protanopsia detected image, rectification figure.The protanopsia detected image is to be specifically designed to detect the image whether people suffers from the protanopsia disease, the protanopsia image is observed the simulation result that original image (protanopsia detected image) obtains for the protanopsia patient, changing image is to the corrigent image of original image, and the protanopsia changing image is the simulation result that protanopsia patient viewing transformation image obtains.(annotate: owing to do not want multicolour pattern, can only provide black and white picture, cause pattern clear inadequately, especially red pattern in the original image and literal can not show.)
The specific embodiment
Be example with the protanopsia below, introduce the entire image correcting process, and in the end express the result that protanopsia is observed original image and changing image with the form of image.
1, protanopsia patient's vision is simulated
Choose 3 width of cloth protanopsia test patterns (original image) as object of correction, according to protanopsia simplified model (4) or simulate the result that the protanopsia patient sees that original image obtains, as the protanopsia image among Fig. 4, Fig. 6, and original image and protanopsia image be analyzed.
2, original image is corrected
The described to specifications method sublevel of original image is handled, and wherein l is taken as 16 rank, sets up the mapping relations table then, according to mapping table its color is corrected at last.For original image is carried out corrigent image, the protanopsia changing image is observed the image that correcting image obtains for the protanopsia patient as the changing image of Fig. 4-shown in Figure 6.Be that the example explanation is to the corrigent process of image below with Fig. 4, the original image of Fig. 4 is carried out after sublevel handles, statistics obtains 577 kinds of colors, wherein belong to R>G have 403 kinds, R≤G have 174 kinds, the R=G face just is divided into 625 kinds of colors in equal size like this, go forward 403 kinds color of R=G face is divided into the map section of R>G, and remaining color is divided into the map section of R≤G.Respectively the color of R>G, the R≤G frequency by color is sorted from big to small then, last to choose the nearest color of Euclidean distance from each self-corresponding map section successively corresponding with it, so just set up the color map table.According to the color map table, the conversion original image just can obtain correcting image, changing image process protanopsia analogue system, can obtain the protanopsia changing image again.
3, interpretation of result
Experimental result by Fig. 4-Fig. 6, as can be seen, protanopsia patient observes original image, has lost a lot of important information (shown in the protanopsia image), but can clearly obtain these information (shown in the protanopsia changing image) from corrigent image (changing image).In Fig. 4, the pattern camel is very clear in original image, has only the profile of a point fuzziness in the protanopsia image, yet in changing image and protanopsia changing image, can see the pattern of camel significantly.In original image, the color deflection of camel is red, and its background color partly is partial to cinerous, part is partial to kermesinus, deflection redness and bolarious distribution of color are in the space of R>G, be partial to the space of caesious distribution of color at R≤G, the color and the caesious color of deflection of being partial to redness from the protanopsia image as can be seen are more approaching in protanopsia, therefore can not be clear that the pattern of camel from image, can make a distinction with them and be partial to bolarious color.This is because deflection is red and the caesious color of deflection is relatively closed on after the L axle projects on the mapping face, projects behind the mapping face relative with them far away and be partial to bolarious color.Therefore the color of R>G, R≤G is projected different mappings face zone respectively, the color distinction of zones of different is very big, and the mapping relations of setting up are man-to-man, so the color relation of originally obscuring easily has been distinguished, originally the color that can distinguish still can distinguish, shown in changing image and protanopsia changing image.
Letter among Fig. 5 " RED " is very clear in original image, a bit can't see in the protanopsia image, but in changing image and protanopsia changing image, " RED " three letters is but very clear.In original image, letter " RED " is that the deflection redness is main, background color is that the deflection green is main, the distribution of color of deflection redness is in the space of R>G, the distribution of color of deflection green is in the space of R≤G, this two classes color along the projection of L direction of principal axis on mapping face very near or overlapping, so protanopsia be difficult to distinguish them, caused the result shown in the protanopsia image.When this two classes color is projected in different mapping face zones respectively, then the eclipsed situation of projection has just been avoided, and the distance on mapping face also widened, so this two classes color relation has been distinguished by protanopsia, letter " RED " just can present significantly; In the original image of Fig. 6, can see numeral " 823 ", in the protanopsia image, a bit can't see, yet in changing image and protanopsia changing image, can clearly see " 823 " three numerals.Situation and Fig. 5 of Fig. 6 are similar, and difference is that the background among Fig. 6 is that deflection is red, and the numeral deflection is green.
From above experimental result as can be known, the present invention can improve the resolution capability of protanopsia patient to color well, thereby has improved protanopsia patient obtains information from coloured image amount.Be to be that example explains with the protanopsia above, can obtain good effect equally for deuteranopsia.
List of references
[1]C.E.Martin,J.G.Keller,S.K.Rogers,M.Kabrisky.Color?blindness?and?a?color?human?visualsystem?model.IEEE?Transactions?on?Systems,Man,and?Cybernetics-Part?A:Systems?and?Humans,2000,30:494-500.
[2]H.Brettel,F.vienot,J.D.Mollon.Computerized?simulation?of?color?appearance?for?dichromats.J.Opt.Soc.Am.A,1997,14:2647-2655.
[3]F.vienot,H.Brettel,J.D.Mollon.Digital?video?colourmaps?for?checking?the?legibility?ofdisplays?by?dichromats.Color?reseach?and?application,1999,24:243-252.
[4]S.Nakauchi,S.Usui.Multilayered?neural?network?models?for?color?blindness.Neural?Networks1991,IEEE?International?Joint?Conference,1991,1:473-478.
[5]Y.H.Kuo,J.P.Hsu.MCFC-R:A?fuzzy?connectionist?model?for?color-blindness?plate?recognition.Neural?Networks?1996,IEEE?International?Conference,1996,2:718-723.
[6]W.Thomas,D.Ulrike,H.Rainer.Modeling?color?percepts?of?dichromats.Vision?Research,2004,44:2843-2855.
[7]P.Capilla,M.A.Diez-Ajenjo,M.J.Luque,J.Malo.Corresponding-pair?procedure:a?newapproach?to?simulation?of?dichromatic?color?perception.J.Opt.Soc.Am.A,2004,21:176-186.
[8]V.A.Kovalev.Towards?image?retrieval?for?eight?percent?of?color-blind?men.Proceedings?of?the17th?International?Conference?On?Pattern?Recognition(ICPR’04),2004,2:943-946.
[9]G.Laccarino,D.Malandrino,M.D.Percio?and?V.Scarano.Efricient?edge-services?for?colorblindusers.Proceedings?Of?The?15th?International?Conference?On?World,WWW,2006,May:22-26.
[10]Y.M.Ro,S.Yang.Color?adaptation?for?anomalous?trichromats.International?Journal?of?ImagingSystems?and?Technology,2004,14:16-20.
[11]K.Rasche,R.Geist,J.Westall.Detail?preserving?reproduction?of?color?images?formonochromats?and?dichromats.IEEE?Computer?Graphics?and?Applications,2005,25:22-30.
Claims (4)
1, a kind of anerythrochloropsia antidote based on the self adaptation mapping is characterized in that at first the anerythrochloropsia model being carried out emulation, then original image is carried out sublevel and handles, and mark off view field; Set up the mapping table of a normal color space in view of the above, original image is corrected according to mapping table to achromatopsia color face.
2, method according to claim 1 is characterized in that the emulation of described anerythrochloropsia model is as follows:
Red-blind simplified model is suc as formula (4):
Deuteranopic simplified model is suc as formula (5):
R, G, B are respectively the red, green, blue component of color in the above formula; R
p, G
p, B
p, R
d, G
d, B
dBe respectively the RGB component of the color that protanopsia and deuteranopsia see.
3, method according to claim 1 is characterized in that described that original image is carried out the step that sublevel handles is as follows:
If each color component is represented with 8 bits in the primary RGB image, totally 256 rank, so existing exponent number is compressed, if the color component after the compression is the l rank, be equally divided into the l five equilibrium to 256, get its intermediate value in by stages such as every and represent this interval color component, l is just arranged in color space like this
3Individual color dot; According to the needs of practical situation, the value of regulating l decides the resolution of color, and l gets 8 or 16.
4, method according to claim 1 is characterized in that described division view field and sets up the step of mapping table as follows:
After the processing of original image sublevel, count total number of colours n in image this moment earlier
0, every kind of color frequency f
nAnd the spatial number of colours n of R>G
1, the spatial number of colours n of R≤G
2Then according to n
0, n
1, n
2The mapping face of division; In order to make n
0Plant color and can both project on the mapping face, the exponent number that two coordinate axess of mapping face are divided is k=[n
0 1/2K then can be represented on the mapping face altogether in]+1
2Plant color; The division of view field is by n on the mapping face
1, n
2Decision is at first to the k on the mapping face
2The ordering of kind of color is lined by line scan from the black of mapping face along the direction of R=G axle until the white in the upper right corner of mapping face, and to the ordering of the color on the color face, first be black according to the order of this scanning, and last position is white; Then the preceding n on the mapping face
1Plant color assignment and give the space of R>G, remaining k
2-n
1Plant color assignment and give the space of R≤G, make the color relation of original R>G and R≤G lay respectively at the zones of different of mapping face like this, cause the color relation of obscuring to distinguish significantly easily;
After view field has divided, respectively of the big minispread of the color of R>G, R≤G in the native color space according to the color frequency of occurrences, color for the R>G after the ordering, from the color that makes number one, it is corresponding with it to choose the nearest color of Euclidean distance in its corresponding view field, selected color relation removes from the colors list of view field, again remaining color is done similar operations successively, up to the color of all R>G in native color space all till its corresponding view field finds corresponding color; In like manner, also find corresponding with it color from its corresponding view field for the color of R≤G; So just, set up the man-to-man color map relation table of a normal color space to achromatopsia color face; According to the mapping table of above-mentioned gained, the color of all pixels in the conversion original image just can obtain corrigent image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200710039657A CN101036606B (en) | 2007-04-19 | 2007-04-19 | Method for rectifying the daltonism on the basis of self-adapted mapping |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200710039657A CN101036606B (en) | 2007-04-19 | 2007-04-19 | Method for rectifying the daltonism on the basis of self-adapted mapping |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101036606A true CN101036606A (en) | 2007-09-19 |
CN101036606B CN101036606B (en) | 2010-05-19 |
Family
ID=38887922
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN200710039657A Expired - Fee Related CN101036606B (en) | 2007-04-19 | 2007-04-19 | Method for rectifying the daltonism on the basis of self-adapted mapping |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101036606B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108322719A (en) * | 2018-02-12 | 2018-07-24 | 京东方科技集团股份有限公司 | Head-up-display system and new line display methods, mobile devices |
CN110728724A (en) * | 2019-10-21 | 2020-01-24 | 深圳创维-Rgb电子有限公司 | Image display method, device, terminal and storage medium |
CN113658055A (en) * | 2021-07-08 | 2021-11-16 | 浙江一山智慧医疗研究有限公司 | Color mapping method and device for digital image, electronic device and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2149637Y (en) * | 1993-04-22 | 1993-12-15 | 战永刚 | Lenses of glasses with function of correcting sense of colour |
CN1157151C (en) * | 2000-12-26 | 2004-07-14 | 陈言 | Color vision detecting and correcting method and equipment and its application |
CN1895191A (en) * | 2006-05-11 | 2007-01-17 | 复旦大学 | Parachromatism and anomalous trichromatism correcting method based on BP nervous network |
-
2007
- 2007-04-19 CN CN200710039657A patent/CN101036606B/en not_active Expired - Fee Related
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106249406B (en) * | 2016-08-30 | 2019-05-14 | 陈晓冬 | Improve Color perception and corrects the artificial intelligence lens and design method of colour blindness anomalous trichromatism vision |
CN108322719A (en) * | 2018-02-12 | 2018-07-24 | 京东方科技集团股份有限公司 | Head-up-display system and new line display methods, mobile devices |
US10578865B2 (en) | 2018-02-12 | 2020-03-03 | Boe Technology Group Co., Ltd. | Head-up display apparatus, controlling method therer, and vehicle |
CN110728724A (en) * | 2019-10-21 | 2020-01-24 | 深圳创维-Rgb电子有限公司 | Image display method, device, terminal and storage medium |
CN113658055A (en) * | 2021-07-08 | 2021-11-16 | 浙江一山智慧医疗研究有限公司 | Color mapping method and device for digital image, electronic device and storage medium |
CN113658055B (en) * | 2021-07-08 | 2022-03-08 | 浙江一山智慧医疗研究有限公司 | Color mapping method and device for digital image, electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN101036606B (en) | 2010-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103065360B (en) | A kind of hair shape effect map generalization method and system | |
CN1302669C (en) | Device and method of colour compensation | |
US7873213B2 (en) | Systems and methods for color-deficient image enhancement | |
CN106548165A (en) | A kind of face identification method of the convolutional neural networks weighted based on image block | |
CN110276727B (en) | Color vision disorder-oriented color image color enhancement method | |
CN110363116A (en) | Irregular face antidote, system and medium based on GLD-GAN | |
CN106504212A (en) | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement | |
US10902801B2 (en) | Driving method and apparatus for display apparatus | |
CN103402117A (en) | Method for detecting color cast of video image based on Lab chrominance space | |
CN103839079A (en) | Similar image colorization algorithm based on classification learning | |
CN101036606B (en) | Method for rectifying the daltonism on the basis of self-adapted mapping | |
CN106650606A (en) | Matching and processing method of face image and face image model construction system | |
CN109035377A (en) | For obtaining the embossment sketch effect image processing method for being suitable for laser engraving | |
CN107481206A (en) | MIcrosope image background equalization Processing Algorithm | |
CN111915508A (en) | Image texture detail enhancement method for dyschromatopsia | |
Chen et al. | Color feature extraction of Hainan Li brocade image based on RGB and HSV | |
CN108846871A (en) | A kind of image processing method and device | |
CN113129390A (en) | Color blindness image re-coloring method and system based on joint significance | |
CN106447603A (en) | Color image graying method | |
CN106815602A (en) | A kind of runway FOD image detection method and devices based on multi-level features description | |
CN112331140B (en) | Display screen color cast Mura repairing method and device | |
CN106599185B (en) | HSV-based image similarity identification method | |
CN105844640A (en) | Color image quality evaluation method based on gradient | |
CN114511567B (en) | Tongue body and tongue coating image identification and separation method | |
CN111127333A (en) | Improved color enhancement method for color image facing to bicolor vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100519 Termination date: 20140419 |