CN104410850A - Colorful digital image chrominance correction method and system - Google Patents
Colorful digital image chrominance correction method and system Download PDFInfo
- Publication number
- CN104410850A CN104410850A CN201410819987.XA CN201410819987A CN104410850A CN 104410850 A CN104410850 A CN 104410850A CN 201410819987 A CN201410819987 A CN 201410819987A CN 104410850 A CN104410850 A CN 104410850A
- Authority
- CN
- China
- Prior art keywords
- grouping
- sample
- data set
- chrominance information
- subset
- 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
Landscapes
- Spectrometry And Color Measurement (AREA)
- Facsimile Image Signal Circuits (AREA)
- Color Image Communication Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a colorful digital image chrominance correction method and system. The colorful digital image chrominance correction method comprises the following steps: building a typical color sample spectral reflectivity data set, calculating chrominance information of each color sample in the data set under the condition with an original light source and grouping samples by taking main wavelength and color purity as basis, and solving the chrominance information of each color sample in each group of subset under the condition with a target light source; taking the chrominance information of each group of sample subset under the conditions with the original and target light sources as input-output end, and fitting and building a neural network; determining the corresponding neural network by a grouping and judging method on account of any chrominance information of the original light source, and forecasting the chrominance information under the corresponding target light source according to the neural network. By virtue of the colorful digital image chrominance correction method, the mapping accuracy of the colorful digital image chrominance information under different illumination conditions can be ensured; meanwhile, the method is convenient to implement.
Description
Technical field
The invention belongs to color digital image record and reproducing technology field, be specifically related to a kind of color digital image chromaticity correction method and system based on typical color sample light spectrum reflectivity data collection.
Background technology
Color digital image system is one of important carrier of objective things information record and reproduction.In actual applications, by the impact of different objective environment condition and different self otherness of chromatic image equipment, there is diversity in the light conditions of color digital image chrominance information record and reproduction.For ensureing the accuracy of colouring information in color digital image information record and reproducing processes, need by specific color correcting method to realize the accurate mapping of image chrominance information under Different Light condition.
For this problem, the solution that current industry is commonly used the most for utilizing chromatic adaptation transform method, to realize the accurate mapping of same color information under different light scene condition.The method, by simulation human eye chromatic adaptation characteristic, by conjunction with Different Light chrominance information, realizes by the simulation and forecast of object chrominance information under object chrominance information to target light source under original light source, and then ensures the accuracy that image object color information is transmitted.At present, at color digital image record and field of reproduction, industry proposes many classical chromatic adaptation transform methods, as Von Kries method, and Wrong Von Kries method, Bradford method, Helson method, Bartleson method and Hunt method etc.
List of references 1.H.R.Kang.Computational color technology [M] .Society of Photo Optical, 2006.
List of references 2.M.R.Luo.A review of chromatic adaptation transforms [J] .Review of Progress inColoration and Related Topics, 2000.
These class methods, by the simulation of human eye chromatic adaptation mechanism, to some extent solve the problem that chrominance information under color digital image system Different Light condition accurately maps.But, because the structure of above-mentioned chromatic adaptation transform method is all based on human eye vision psychophysics experiments, namely said method mainly with human eye vision subjective matching for basis of formation, therefore in the objective and accurate property of chromaticity correction, there is comparatively significantly defect.For this reason, studying application at present, existing researcher is devoted to build chromaticity correction method, to realize more high-precision color digital image chromaticity correction, as described in list of references 3 from objective angle.
List of references 3.Rok Kreslin et al.Linear Chromatic Adaptation Transform Based on DelaunayTriangulation [J] .Mathematical Problems in Engineering, 2014.
But by the restriction of the subjective and objective factors such as theoretical method level, there is the such as excessive grade of saturated color domain error comparatively significantly defect equally in above-mentioned objective method in chromaticity correction accuracy.For above problem, academic circles at present and industrial quarters not yet propose corresponding solution, to realize accurate mapping and the transmission of colors of image chrominance information under different light scene condition.
Summary of the invention
The object of the invention is to solve problem described in background technology, proposing a kind of color digital image chromaticity correction method and system based on typical color sample light spectrum reflectivity data collection.
Technical scheme of the present invention, for providing a kind of color digital image chromaticity correction method, comprises the following steps:
Step 1, chooses M typical color sample, is formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each typical color sample visible-range
s;
Step 2, in step 1 each typical color sample spectral reflectance data based on, utilize following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is parameter;
Step 3, calculates typical color sample chroma-data set G
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to typical color sample chroma-data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T, obtain T subset;
Step 4, for gained typical case color sample chroma-data set G after step 3 two groupings
st subset, respectively with object light source L
tfor lighting source E (λ), utilize the equations of colorimetry described in step 2 object light source L
tthe chrominance information of each sample in subset under condition;
Step 5, for each subset, the source light source L of this subset of gained of dividing into groups with step 3 respectively
sunder condition, this chrominance information of various kinds is input, and solve the object light source Lt condition of this subset of gained with step 4 under, this chrominance information of various kinds is for output, trains corresponding BP neural net;
Step 6, for chrominance information Cs a certain under the light conditions of source, calculate dominant wavelength and colorimetric purity information, according to the packet mode of step 3, determine corresponding subset and BP neural net, and the chrominance information Ct utilizing this BP neural network prediction chrominance information Cs corresponding under object light conditions.
And, in step 3 with dominant wavelength to data set G
swhen dividing into groups first using dominant wavelength be all samples of negative value as one group, be according to be averaged grouping afterwards with dominant wavelength by other sample; Be that secondary divides into groups foundation subsequently with colorimetric purity by the above-mentioned gained all grouping subsets of dividing into groups first, be averaged grouping.
The invention provides a kind of color digital image chromaticity correction system, comprise with lower module:
Typical case's color sample light spectrum data set builds module, for choosing M typical color sample, is formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each typical color sample visible-range
s;
Typical case's color sample chroma-data set computing module, based on the spectral reflectance data for each typical color sample in typical color sample light spectrum data set structure module, utilizes following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is parameter;
Data set grouping module, for calculating typical color sample chroma-data set G
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to typical color sample chroma-data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T, obtain T subset;
Grouping subset chrominance information solves module, for the rear gained typical case color sample chroma-data set G that divides into groups for data set grouping module secondary
st subset, respectively with object light source L
tfor lighting source E (λ), utilize described colorimetry equations object light source L
tthe chrominance information of each sample in subset under condition;
Neural metwork training module, for for each subset, respectively with the source light source L of this subset of data set grouping module grouping gained
sunder condition, this chrominance information of various kinds is input, solves with subset chrominance information of dividing into groups the object light source L that module solves this subset of gained
tunder condition, this chrominance information of various kinds is output, trains corresponding BP neural net;
Chromaticity correction module, for for chrominance information Cs a certain under the light conditions of source, calculate dominant wavelength and colorimetric purity information, according to the packet mode of data set grouping module, determine corresponding subset and BP neural net, and the chrominance information Ct utilizing this BP neural network prediction chrominance information Cs corresponding under object light conditions.
And, in data set grouping module with dominant wavelength to data set G
swhen dividing into groups first using dominant wavelength be all samples of negative value as one group, be according to be averaged grouping afterwards with dominant wavelength by other sample; Be that secondary divides into groups foundation subsequently with colorimetric purity by the above-mentioned gained all grouping subsets of dividing into groups first, be averaged grouping.
A kind of color digital image chromaticity correction technical scheme based on typical color sample light spectrum reflectivity data collection that the present invention proposes, under the prerequisite determining typical color sample light spectrum reflectivity data collection and chromaticity correction source and object light source, in conjunction with dominant wavelength and colorimetric purity group technology, built the relevance model of same color card colourity difference under different lighting conditions by BP neural net, and then achieve accurate mapping and the transmission of colors of image chrominance information under different light scene condition.What the method was ideal solves problem described in background technology part, thus can ensure the accuracy of color digital image information transmittance process, and then meets the demand of high-quality chromatic image information record and reproduction.Therefore, the invention solves the problem that colors of image chrominance information under different lighting condition is accurately transmitted, and implement convenient, at color digital image record and field of reproduction, there is stronger applicability.Because technical solution of the present invention has important application meaning, be subject to multiple project support: 1. fund 2014M5606253.2. National Nature fund project 61275172.3. State Cultural Relics Bureau's historical relic's protection field Science and Technology study general problem 2013-YB-HT-034.4. country 973 basic research sub-project 2012CB725302 on China's post-doctors face.Technical solution of the present invention is protected, will be significant to China's relevant industries competition first place in the world.
Accompanying drawing explanation
Fig. 1 is the flow chart of the embodiment of the present invention.
Embodiment
By reference to the accompanying drawings, the embodiment of the present invention is provided to specifically describe as follows.
A kind of color digital image chromaticity correction method based on typical color sample light spectrum reflectivity data collection of thering is provided of embodiment as shown in Figure 1, the ideal chromaticity correction problem solved under different images object and light scene condition, the accuracy of color digital image information transmittance process can be ensured, and then meet the demand of high-quality chromatic image information record and reproduction.Embodiment adopts 9297 color samples to build typical color sample set, using the matt color sample of 1250 Meng Saier as experimental check sample set, with D65 standard illuminants for source light source, light source for the purpose of A standard illuminants, carries out chromaticity correction with the method for the invention.And by Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, in 6 kinds of chromatic adaptation conversion such as Hunt method and list of references 3, totally 7 kinds of existing methods are in contrast for Kreslin method.It should be noted that, the present invention is not limited to above-mentioned image object and light source type, and for other image object and light source type, this method is applicable equally.
Computer software technology can be adopted to realize automatically running by those skilled in the art when technical solution of the present invention is specifically implemented.The method flow that embodiment provides comprises the following steps:
1) choose M typical color sample, formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each sample visible-range
s;
Those skilled in the art can preset the value of M voluntarily.During concrete enforcement, the maximization of sample set color gamut should be ensured as far as possible.Visible-range is generally 380nm-780nm.During concrete enforcement, in advance with the corresponding spectrum reflectivity information of each sample of spectrophotometer measurement, 380nm-780nm wave band data can be got.In embodiment, 6000 color samples prepared by uniform sampling in printing device colour gamut, 1687 Japanese typical pigments color samples and 1600 Meng Saier gloss color samples totally 9297 samples as typical sample collection (M=9297), this sample set has wide colour gamut, and sample distribution is even.During concrete enforcement, typical color sample light spectrum reflectivity data collection G can be generated in advance
sand input.
2) by 1) in each sample spectral reflectance data based on, utilize following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y=k ∫ y (λ) E (λ) S (λ) d λ, formula one
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is the parameter determined by y (λ), E (λ);
In an embodiment, this step realizes M=9297 typical color sample at source light source L
sunder chromatic value solve, namely each chromatic value forms typical color sample chroma-data set G
c.Wherein, source light source L
sbe set to D65 standard illuminants, namely E (λ) adopts the corresponding relative spectral power distributions curve of D65 standard illuminants.For each sample, S (λ) adopts the spectral reflectance data in corresponding visible-range respectively.
3) typical color sample chroma-data set G is calculated with the theoretical existing dominant wavelength of colorimetry and colorimetric purity computing formula
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T;
In an embodiment, with dominant wavelength to data set G
swhen dividing into groups first, be that all samples of negative value are as one group using dominant wavelength, be according to being averaged grouping (concrete packet count can be set by those skilled in the art) afterwards with dominant wavelength by other sample, the dominant wavelength of embodiment is 5 on the occasion of average number of packets, is divided into 6 groups together with negative value sample group; Be that secondary divides into groups foundation subsequently with colorimetric purity by above-mentioned gained 6 component group subset of dividing into groups first, be averaged grouping (concrete packet count can be set by those skilled in the art), the average number of packets of embodiment secondary grouping is 2, final T=12 grouping.Its dominant wavelength and colorimetric purity scope are respectively
First group: 380nm≤dominant wavelength≤480nm, colorimetric purity≤0.31;
Second group: 380nm≤dominant wavelength≤480nm, colorimetric purity > 0.31;
3rd group: 480nm < dominant wavelength≤503nm, colorimetric purity≤0.21;
4th group: 480nm < dominant wavelength≤503nm, colorimetric purity > 0.21;
5th group: 503nm < dominant wavelength≤569nm, colorimetric purity≤0.23;
6th group: 503nm < dominant wavelength≤569nm, colorimetric purity > 0.23;
7th group: 569nm < dominant wavelength≤588nm, colorimetric purity≤0.39;
8th group: 569nm < dominant wavelength≤588nm, colorimetric purity > 0.39;
9th group: 588nm < dominant wavelength≤780nm, colorimetric purity≤0.41;
Tenth group: 588nm < dominant wavelength≤780nm, colorimetric purity > 0.41;
11 group: dominant wavelength < 0, colorimetric purity≤0.18;
12 group: dominant wavelength < 0, colorimetric purity > 0.18;
Wherein, the computational methods of dominant wavelength and colorimetric purity can see J.Schanda.CIE colorimetry [M] .Wiley OnlineLibrary, and 2007, it will not go into details in the present invention.
4) for 3) the rear the data obtained collection G of secondary grouping
seach subset, utilize 2 respectively) described in method solve object light source L
tunder condition, each chrominance information organizing each sample in subset, wraps with object light source L
tfor lighting source E (λ) solves by formula one;
In an embodiment, for 3) the data obtained collection G
s12 subsets, utilize 2 respectively) Chinese style one, light source L for the purpose of standard illuminants A
t, each chrominance information organizing each sample in subset under solving object light conditions.
5) for each subset, respectively with 3) the source light source L of grouping gained this group subset
sunder condition, this chrominance information of various kinds is input, with 4) solve the object light source L of this group subset of gained
tunder condition, this chrominance information of various kinds is output, trains corresponding BP neural net;
In embodiment, with 3) in divide into groups each subset of obtaining at source light source L
schrominance information under condition as input data, with 4) in each group of subset solving at target light source L
tchrominance information under condition, as output data, builds BP neural net.Wherein, for 3) middle gained 12 grouping subset, 12 BP neural nets need be built altogether.During concrete enforcement, can see BP neural net existing techniques in realizing.
Like this, based on packet samples collection chrominance information each under packet samples collection chrominance information each under the light conditions of source and object light conditions, neural net can be built, for chrominance information under the light conditions of follow-up source based on chrominance information under group-discriminate acquisition object light conditions for each corresponding grouped data matching.
6) for chrominance information Cs a certain under the light conditions of source, the theoretical existing dominant wavelength of colorimetry and colorimetric purity computing formula is utilized to calculate its dominant wavelength and colorimetric purity information, and in conjunction with 3) described grouping situation, determine the subset corresponding with it and BP neural net, and utilize its chrominance information Ct corresponding under object light conditions of this BP neural network prediction.
In an embodiment, for certain color sample chrominance information Cs under the light conditions of source, its CIEXYZ value is (84,89,99) the theoretical existing dominant wavelength of colorimetry and colorimetric purity computing formula is utilized to calculate its dominant wavelength and colorimetric purity information, obtaining its dominant wavelength is 477nm, colorimetric purity is 0.01, then by embodiment 3) known its belong to first grouping, therefore utilize its chrominance information Ct under target light source condition of BP neural network prediction corresponding to first group of data, solve its CIEXYZ value is (97,88,33), with theoretical value (98,89,32) very close.
During concrete enforcement, in advance set up subset division and corresponding BP neural net to any object light conditions according to step 1 ~ 5 for any source light conditions, namely can be used for the prediction of corresponding chrominance information.
For the advantage of further proved inventive method in chromaticity correction precision, using the matt color sample of 1250 Meng Saier as experimental check sample set, with D65 standard illuminants for source light source, light source for the purpose of A standard illuminants, carries out chromaticity correction with the method for the invention.And by Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, in 6 kinds of chromatic adaptation conversion such as Hunt method and list of references 3, totally 7 kinds of existing methods are in contrast for Kreslin method.Experimental result shows, Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, the chromaticity correction precision that Hunt method and Kreslin method represent with colour difference formula CIEDE2000 is respectively 4.67,2.86,5.38,3.36,4.76,4.13,2.11, and chromaticity correction precision of the present invention is 1.53, accuracy benefits is obvious.Wherein, CIEDE2000 colour difference formula can see Ming R Luo.CIE 2000 color difference formula:CIEDE2000 [A] .In 9th Congress of the International Color Association [C], and it will not go into details in Year:554-9. the present invention.
The present invention is also corresponding provides a kind of color digital image chromaticity correction system, comprises with lower module:
Typical case's color sample light spectrum data set builds module, for choosing M typical color sample, is formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each typical color sample visible-range
s;
Typical case's color sample chroma-data set computing module, based on the spectral reflectance data for each typical color sample in typical color sample light spectrum data set structure module, utilizes following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is parameter;
Data set grouping module, for calculating typical color sample chroma-data set G
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to typical color sample chroma-data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T, obtain T subset;
Grouping subset chrominance information solves module, for the rear gained typical case color sample chroma-data set G that divides into groups for data set grouping module secondary
st subset, respectively with object light source L
tfor lighting source E (λ), utilize described colorimetry equations object light source L
tthe chrominance information of each sample in subset under condition;
Neural metwork training module, for for each subset, respectively with the source light source L of this subset of data set grouping module grouping gained
sunder condition, this chrominance information of various kinds is input, solves with subset chrominance information of dividing into groups the object light source L that module solves this subset of gained
tunder condition, this chrominance information of various kinds is output, trains corresponding BP neural net;
Chromaticity correction module, for for chrominance information Cs a certain under the light conditions of source, calculate dominant wavelength and colorimetric purity information, according to the packet mode of data set grouping module, determine corresponding subset and BP neural net, and the chrominance information Ct utilizing this BP neural network prediction chrominance information Cs corresponding under object light conditions.
Wherein, in data set grouping module with dominant wavelength to data set G
swhen dividing into groups first using dominant wavelength be all samples of negative value as one group, be according to be averaged grouping afterwards with dominant wavelength by other sample; Be that secondary divides into groups foundation subsequently with colorimetric purity by the above-mentioned gained all grouping subsets of dividing into groups first, be averaged grouping.
Each module specific implementation is corresponding with each step, and it will not go into details in the present invention.
Specific embodiment described herein is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various amendment or supplement or adopt similar mode to substitute to described specific embodiment, but can't depart from spirit of the present invention or surmount the scope that appended claims defines.
Claims (4)
1. a color digital image chromaticity correction method, is characterized in that, comprises the following steps:
Step 1, chooses M typical color sample, is formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each typical color sample visible-range
s;
Step 2, in step 1 each typical color sample spectral reflectance data based on, utilize following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is parameter;
Step 3, calculates typical color sample chroma-data set G
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to typical color sample chroma-data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T, obtain T subset;
Step 4, for gained typical case color sample chroma-data set G after step 3 two groupings
st subset, respectively with object light source L
tfor lighting source E (λ), utilize the equations of colorimetry described in step 2 object light source L
tthe chrominance information of each sample in subset under condition;
Step 5, for each subset, the source light source L of this subset of gained of dividing into groups with step 3 respectively
sunder condition, this chrominance information of various kinds is input, solves the object light source L of this subset of gained with step 4
tunder condition, this chrominance information of various kinds is output, trains corresponding BP neural net;
Step 6, for chrominance information Cs a certain under the light conditions of source, calculate dominant wavelength and colorimetric purity information, according to the packet mode of step 3, determine corresponding subset and BP neural net, and the chrominance information Ct utilizing this BP neural network prediction chrominance information Cs corresponding under object light conditions.
2. color digital image chromaticity correction method according to claim 1, is characterized in that: in step 3 with dominant wavelength to data set G
swhen dividing into groups first using dominant wavelength be all samples of negative value as one group, be according to be averaged grouping afterwards with dominant wavelength by other sample; Be that secondary divides into groups foundation subsequently with colorimetric purity by the above-mentioned gained all grouping subsets of dividing into groups first, be averaged grouping.
3. a color digital image chromaticity correction system, is characterized in that, comprises with lower module:
Typical case's color sample light spectrum data set builds module, for choosing M typical color sample, is formed typical color sample light spectrum reflectivity data collection G with the spectral reflectance data in each typical color sample visible-range
s;
Typical case's color sample chroma-data set computing module, based on the spectral reflectance data for each typical color sample in typical color sample light spectrum data set structure module, utilizes following colorimetry formula to calculate each sample respectively at source light source L
schrominance information under condition, and form typical color sample chroma-data set G
c,
X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],
Wherein, X, Y, Z represent colourity tristimulus values, and λ represents each band wavelength of visible ray; X (λ), y (λ), z (λ) adopt source light source L for human eye vision matching function, lighting source E (λ)
scorresponding relative spectral power distributions curve, color object spectra reflectivity S (λ) adopts the spectral reflectance data in the corresponding visible-range of sample, and k is parameter;
Data set grouping module, for calculating typical color sample chroma-data set G
cin each sample dominant wavelength and colorimetric purity information, be that grouping is according to typical color sample chroma-data set G with dominant wavelength
sdivide into groups first, be that grouping foundation carries out secondary grouping to gained set of dividing into groups first subsequently with colorimetric purity, remember that final number of packet is T, obtain T subset;
Grouping subset chrominance information solves module, for the rear gained typical case color sample chroma-data set G that divides into groups for data set grouping module secondary
st subset, respectively with object light source L
tfor lighting source E (λ), utilize described colorimetry equations object light source L
tthe chrominance information of each sample in subset under condition;
Neural metwork training module, for for each subset, respectively with the source light source L of this subset of data set grouping module grouping gained
sunder condition, this chrominance information of various kinds is input, solves with subset chrominance information of dividing into groups the object light source L that module solves this subset of gained
tunder condition, this chrominance information of various kinds is output, trains corresponding BP neural net;
Chromaticity correction module, for for chrominance information Cs a certain under the light conditions of source, calculate dominant wavelength and colorimetric purity information, according to the packet mode of data set grouping module, determine corresponding subset and BP neural net, and the chrominance information Ct utilizing this BP neural network prediction chrominance information Cs corresponding under object light conditions.
4. color digital image chromaticity correction system according to claim 3, is characterized in that: in data set grouping module with dominant wavelength to data set G
swhen dividing into groups first using dominant wavelength be all samples of negative value as one group, be according to be averaged grouping afterwards with dominant wavelength by other sample; Be that secondary divides into groups foundation subsequently with colorimetric purity by the above-mentioned gained all grouping subsets of dividing into groups first, be averaged grouping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410819987.XA CN104410850B (en) | 2014-12-25 | 2014-12-25 | Colorful digital image chrominance correction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410819987.XA CN104410850B (en) | 2014-12-25 | 2014-12-25 | Colorful digital image chrominance correction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104410850A true CN104410850A (en) | 2015-03-11 |
| CN104410850B CN104410850B (en) | 2017-02-22 |
Family
ID=52648436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410819987.XA Expired - Fee Related CN104410850B (en) | 2014-12-25 | 2014-12-25 | Colorful digital image chrominance correction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104410850B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106053024A (en) * | 2016-06-27 | 2016-10-26 | 武汉大学 | LED light source preference prediction method for monochromatic objects |
| CN107093031A (en) * | 2017-05-10 | 2017-08-25 | 广东溢达纺织有限公司 | Color data Internet management method and system |
| CN107507250A (en) * | 2017-06-02 | 2017-12-22 | 北京工业大学 | A kind of complexion tongue color image color correction method based on convolutional neural networks |
| CN108519157A (en) * | 2018-03-16 | 2018-09-11 | 武汉大学 | A kind of generation of metamerism spectrum and evaluation method and system for light source detection |
| CN109274945A (en) * | 2018-09-29 | 2019-01-25 | 合刃科技（深圳）有限公司 | A kind of adaptive method and system for carrying out the reduction of image true color |
| CN110487403A (en) * | 2019-09-02 | 2019-11-22 | 常州市武进区半导体照明应用技术研究院 | A kind of prediction technique of LED light spectral power distributions |
| CN113936066A (en) * | 2021-09-29 | 2022-01-14 | 北京理工大学 | Method for characterizing wide color gamut and chromaticity of color imaging system based on digital calibration |
| CN116678839A (en) * | 2023-07-13 | 2023-09-01 | 季华实验室 | Luminescent material detection method, device, terminal equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101447020A (en) * | 2008-12-12 | 2009-06-03 | 北京理工大学 | Pornographic image recognizing method based on intuitionistic fuzzy |
| CN102075666A (en) * | 2009-11-25 | 2011-05-25 | 惠普开发有限公司 | Method and device used for removing background colors from image |
| WO2011103377A1 (en) * | 2010-02-22 | 2011-08-25 | Dolby Laboratories Licensing Corporation | System and method for adjusting display based on detected environment |
| CN102572450A (en) * | 2012-01-10 | 2012-07-11 | 中国传媒大学 | Three-dimensional video color calibration method based on scale invariant feature transform (SIFT) characteristics and generalized regression neural networks (GRNN) |
| CN104092919A (en) * | 2014-07-14 | 2014-10-08 | 武汉大学 | Chromatic adaptation transformation optimizing method and system for color digital imaging system |
-
2014
- 2014-12-25 CN CN201410819987.XA patent/CN104410850B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101447020A (en) * | 2008-12-12 | 2009-06-03 | 北京理工大学 | Pornographic image recognizing method based on intuitionistic fuzzy |
| CN102075666A (en) * | 2009-11-25 | 2011-05-25 | 惠普开发有限公司 | Method and device used for removing background colors from image |
| WO2011103377A1 (en) * | 2010-02-22 | 2011-08-25 | Dolby Laboratories Licensing Corporation | System and method for adjusting display based on detected environment |
| CN102572450A (en) * | 2012-01-10 | 2012-07-11 | 中国传媒大学 | Three-dimensional video color calibration method based on scale invariant feature transform (SIFT) characteristics and generalized regression neural networks (GRNN) |
| CN104092919A (en) * | 2014-07-14 | 2014-10-08 | 武汉大学 | Chromatic adaptation transformation optimizing method and system for color digital imaging system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106053024A (en) * | 2016-06-27 | 2016-10-26 | 武汉大学 | LED light source preference prediction method for monochromatic objects |
| CN106053024B (en) * | 2016-06-27 | 2018-08-10 | 武汉大学 | A kind of LED light source preference degree prediction technique towards monochromatic system object |
| CN107093031A (en) * | 2017-05-10 | 2017-08-25 | 广东溢达纺织有限公司 | Color data Internet management method and system |
| CN107507250A (en) * | 2017-06-02 | 2017-12-22 | 北京工业大学 | A kind of complexion tongue color image color correction method based on convolutional neural networks |
| CN108519157A (en) * | 2018-03-16 | 2018-09-11 | 武汉大学 | A kind of generation of metamerism spectrum and evaluation method and system for light source detection |
| CN108519157B (en) * | 2018-03-16 | 2019-07-09 | 武汉大学 | A kind of generation of metamerism spectrum and evaluation method and system for light source detection |
| CN109274945A (en) * | 2018-09-29 | 2019-01-25 | 合刃科技（深圳）有限公司 | A kind of adaptive method and system for carrying out the reduction of image true color |
| CN110487403A (en) * | 2019-09-02 | 2019-11-22 | 常州市武进区半导体照明应用技术研究院 | A kind of prediction technique of LED light spectral power distributions |
| CN113936066A (en) * | 2021-09-29 | 2022-01-14 | 北京理工大学 | Method for characterizing wide color gamut and chromaticity of color imaging system based on digital calibration |
| CN116678839A (en) * | 2023-07-13 | 2023-09-01 | 季华实验室 | Luminescent material detection method, device, terminal equipment and storage medium |
| CN116678839B (en) * | 2023-07-13 | 2023-11-10 | 季华实验室 | Luminescent material detection method, device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104410850B (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104410850A (en) | Colorful digital image chrominance correction method and system | |
| CN104217409B (en) | A kind of image color correction method based on simulated annealing optimization algorithm | |
| CN103854261B (en) | The bearing calibration of colour cast image | |
| CN104485068A (en) | Luminance-chrominance correction method and system of LED (Light Emitting Diode) display screen | |
| CN102611897A (en) | Method and system for carrying out vision perception high-fidelity transformation on color digital image | |
| US20200090601A1 (en) | Driving method and apparatus for display apparatus | |
| CN107346653A (en) | A kind of GAMMA curves adjusting process and device based on deep learning | |
| CN103474046B (en) | Method for improving color reproduction effect from digital camera to displayer | |
| CN105069234A (en) | Spectrum dimensionality reduction method and system based on visual perception feature | |
| CN104574371A (en) | High dynamic color digital camera characterization calibration method | |
| CN102945556B (en) | Seven look algorithm of color separations of Neugebauer equation are divided based on cell element | |
| CN103612483A (en) | Printing ink color matching method based on spectral matching | |
| CN107424197B (en) | Method for realizing cross-media color reproduction based on spectral domain mapping | |
| CN104092919B (en) | Chromatic adaptation transformation optimizing method and system for color digital imaging system | |
| CN104714451A (en) | Automobile paint automatic color matching system | |
| CN108844632B (en) | Method for evaluating metamerism difference of observers among different display devices | |
| US7659982B2 (en) | Quantitative evaluation of a color filter | |
| CN104616301A (en) | Intelligent robot color sensor based chrominance analysis method, device and system | |
| CN103973980A (en) | Method for acquiring multispectral images based on digital camera | |
| CN102231787B (en) | Image color correction method and device | |
| CN110324476B (en) | Method for representing color generation performance of mobile phone screen | |
| EP2866008B1 (en) | Tone type identification method | |
| CN104742517B (en) | Color free collection and matching device | |
| CN107766896B (en) | Spectrum dimensionality reduction method based on hue clustering | |
| CN108931299A (en) | A kind of colour measurement device and method based on embedded type camera |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170222 Termination date: 20201225 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |