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
- light source
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012937 correction Methods 0.000 title claims abstract description 30
- 230000003595 spectral effect Effects 0.000 claims abstract description 46
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000002310 reflectometry Methods 0.000 claims abstract 5
- 238000009826 distribution Methods 0.000 claims description 7
- 238000004737 colorimetric analysis Methods 0.000 claims description 6
- 230000004438 eyesight Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims 6
- 230000001537 neural effect Effects 0.000 claims 5
- 238000013480 data collection Methods 0.000 claims 2
- 238000013507 mapping Methods 0.000 abstract description 6
- 238000005286 illumination Methods 0.000 abstract description 5
- 230000006978 adaptation Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000009010 Bradford assay Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000011426 transformation method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000004456 color vision Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000000844 transformation Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Landscapes
- Color Image Communication Systems (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
Description
技术领域technical field
本发明属于彩色数字影像记录与再现技术领域，具体涉及一种基于典型色彩样本光谱反射率数据集的彩色数字影像色度校正方法及系统。The invention belongs to the technical field of color digital image recording and reproduction, and in particular relates to a color digital image chromaticity correction method and system based on a typical color sample spectral reflectance data set.
背景技术Background technique
彩色数字影像系统是客观事物信息记录与再现的重要载体之一。在实际应用中，受不同客观环境条件及不同彩色影像设备自身差异性的影响，彩色数字影像色度信息记录与再现的光源条件存在多样性。为保证彩色数字影像信息记录与再现过程中颜色信息的准确性，需要借助特定的色彩校正方法以实现不同光源条件下影像色度信息的准确映射。The color digital image system is one of the important carriers for the recording and reproduction of objective information. In practical applications, due to the influence of different objective environmental conditions and the differences of different color imaging devices, the light source conditions for the recording and reproduction of color digital image chromaticity information are diverse. In order to ensure the accuracy of color information in the process of recording and reproducing color digital image information, it is necessary to use specific color correction methods to achieve accurate mapping of image chromaticity information under different light source conditions.
针对此问题，目前业界最为常用的解决方法为利用色适应变换方法，以实现同一色彩信息在不同光照场景条件下的准确映射。该方法通过模拟人眼色觉适应特性，通过结合不同光源色度信息，实现由原始光源下物体色度信息到目标光源下物体色度信息的模拟预测，进而保证影像客体色彩信息传递的准确性。目前，在彩色数字影像记录与再现领域，业界提出了诸多经典色适应变换方法，如Von Kries方法,Wrong Von Kries方法，Bradford方法,Helson方法,Bartleson方法以及Hunt方法等。To solve this problem, the most commonly used solution in the industry is to use the color adaptation transformation method to realize accurate mapping of the same color information under different lighting scene conditions. By simulating the adaptation characteristics of human eye color vision and combining the chromaticity information of different light sources, the method realizes the simulation prediction from the chromaticity information of the object under the original light source to the chromaticity information of the object under the target light source, thereby ensuring the accuracy of the color information transmission of the image object. At present, in the field of color digital image recording and reproduction, many classic chromatic adaptation transformation methods have been proposed in the industry, such as Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method and Hunt method.
参考文献1.H.R.Kang.Computational color technology[M].Society of Photo Optical，2006.References 1.H.R.Kang.Computational color technology[M].Society of Photo Optical, 2006.
参考文献2.M.R.Luo.A review of chromatic adaptation transforms[J].Review of Progress inColoration and Related Topics，2000.Reference 2.M.R.Luo.A review of chromatic adaptation transforms[J].Review of Progress inColoration and Related Topics，2000.
此类方法通过人眼色觉适应机理的模拟，在一定程度上解决了彩色数字影像系统不同光源条件下色度信息准确映射的问题。然而，由于上述色适应变换方法的构建皆基于人眼视觉心理物理学实验，即上述方法主要以人眼视觉主观匹配为构建基础，故在色度校正的客观准确性方面存在较为明显的缺陷。为此，在目前研究应用领域，已有研究者致力于从客观角度构建色度校正方法，以实现更高精度的彩色数字影像色度校正，如参考文献3所述。This kind of method solves the problem of accurate mapping of chromaticity information under different light source conditions in color digital image systems to a certain extent by simulating the adaptation mechanism of human eye color vision. However, since the construction of the above-mentioned chromatic adaptation transformation methods is based on the psychophysical experiment of human eye vision, that is, the above-mentioned method is mainly based on the subjective matching of human eye vision, there are obvious defects in the objective accuracy of chromaticity correction. For this reason, in the current research and application field, researchers have devoted themselves to constructing a chromaticity correction method from an objective perspective to achieve higher-precision color digital image chromaticity correction, as described in Reference 3.
参考文献3.Rok Kreslin et al.Linear Chromatic Adaptation Transform Based on DelaunayTriangulation[J].Mathematical Problems in Engineering，2014.Reference 3. Rok Kreslin et al. Linear Chromatic Adaptation Transform Based on Delaunay Triangulation [J]. Mathematical Problems in Engineering, 2014.
然而，受理论方法水平等主客观因素的制约，上述客观方法在色度校正准确性方面同样存在诸如饱和色彩区域误差过大等较为明显的缺陷。针对以上问题，目前学术界与工业界尚未提出相应解决方法，以实现不同照明场景条件下影像色彩色度信息的准确映射与传递。However, restricted by subjective and objective factors such as the level of theoretical methods, the above-mentioned objective methods also have obvious defects in the accuracy of chromaticity correction, such as excessive errors in saturated color areas. In view of the above problems, the academic and industrial circles have not yet proposed a corresponding solution to realize the accurate mapping and transmission of image color and chromaticity information under different lighting scene conditions.
发明内容Contents of the invention
本发明的目的是为了解决背景技术中所述问题，提出一种基于典型色彩样本光谱反射率数据集的彩色数字影像色度校正方法及系统。The object of the present invention is to solve the problems described in the background technology, and propose a color digital image chromaticity correction method and system based on a typical color sample spectral reflectance data set.
本发明的技术方案为提供一种彩色数字影像色度校正方法，包括以下步骤：The technical solution of the present invention is to provide a color digital image chromaticity correction method, comprising the following steps:
步骤1，选取M个典型色彩样本，以各典型色彩样本可见光范围内的光谱反射率数据构成典型色彩样本光谱反射率数据集Gs；Step 1, select M typical color samples, and use the spectral reflectance data of each typical color sample in the visible light range to form a typical color sample spectral reflectance data set G s ;
步骤2，以步骤1中各典型色彩样本的光谱反射率数据为基础，利用如下色度学公式分别计算各样本在源光源Ls条件下的色度信息，并组成典型色彩样本色度数据集Gc，Step 2: Based on the spectral reflectance data of each typical color sample in step 1, use the following chromaticity formula to calculate the chromaticity information of each sample under the condition of source light source L s , and form a typical color sample chromaticity data set G c ,
X＝k∫x(λ)E(λ)S(λ)dλ,X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,Y=k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,Z=k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],k=100/[∫y(λ)E(λ)dλ],
其中，X、Y、Z表示色度三刺激值，λ表示可见光各波段波长；x(λ)、y(λ)、z(λ)为人眼视觉匹配函数，照明光源E(λ)采用源光源Ls相应的相对光谱功率分布曲线，颜色物体光谱反射率S(λ)采用样本相应可见光范围内的光谱反射率数据，k为参数；Among them, X, Y, and Z represent the tristimulus value of chromaticity, and λ represents the wavelength of each band of visible light; x(λ), y(λ), z(λ) are human visual matching functions, and the illumination source E(λ) adopts the source light source The relative spectral power distribution curve corresponding to L s , the spectral reflectance S(λ) of the color object adopts the spectral reflectance data in the corresponding visible light range of the sample, and k is a parameter;
步骤3，计算典型色彩样本色度数据集Gc中各样本主波长及色纯度信息，以主波长为分组依据对典型色彩样本色度数据集Gs进行首次分组，随后以色纯度为分组依据对首次分组所得集合进行二次分组，记最终分组数量为T，得到T个子集；Step 3, calculate the dominant wavelength and color purity information of each sample in the typical color sample chromaticity data set Gc , group the typical color sample chromaticity data set G s for the first time based on the dominant wavelength, and then use the color purity as the grouping basis Perform secondary grouping on the set obtained from the first grouping, record the final grouping number as T, and obtain T subsets;
步骤4，针对步骤3二次分组后所得典型色彩样本色度数据集Gs的T个子集，分别以目的光源Lt为照明光源E(λ)，利用步骤2中所述色度学公式求解目的光源Lt条件下子集中各样本的色度信息；Step 4, for the T subsets of the typical color sample chromaticity data set G s obtained after the secondary grouping in step 3, respectively use the target light source L t as the lighting source E(λ), and use the chromaticity formula described in step 2 to solve The chromaticity information of each sample in the subset under the condition of the target light source L t ;
步骤5，针对各子集，分别以步骤3分组所得该子集的源光源Ls条件下各样本色度信息为输入端，以步骤4求解所得该子集的目的光源Lt条件下各样本色度信息为输出端，训练相应的BP神经网络；Step 5, for each subset, respectively use the chromaticity information of each sample under the condition of the source light source L s of the subset obtained by grouping in step 3 as the input terminal, and use the step 4 to obtain the obtained color of each sample under the condition of the target light source Lt of the subset The degree information is the output terminal, and the corresponding BP neural network is trained;
步骤6，针对源光源条件下某一色度信息Cs，计算主波长与色纯度信息，根据步骤3的分组方式，确定对应的子集及BP神经网络，并利用该BP神经网络预测色度信息Cs在目的光源条件下所对应的色度信息Ct。Step 6: Calculate the dominant wavelength and color purity information for a certain chromaticity information Cs under the condition of the source light source, determine the corresponding subset and BP neural network according to the grouping method in step 3, and use the BP neural network to predict the chromaticity information Cs The corresponding chromaticity information Ct under the condition of the target light source.
而且，步骤3中以主波长对数据集Gs进行首次分组时将主波长为负值的所有样本作为一组，之后将其它样本以主波长为依据进行平均分组；随后将上述首次分组所得所有分组子集以色纯度为二次分组依据，进行平均分组。Moreover, when the data set G s is grouped for the first time by the dominant wavelength in step 3, all samples whose dominant wavelength is a negative value are taken as a group, and then other samples are grouped on the basis of the dominant wavelength; The grouping subset takes the color purity as the secondary grouping basis, and carries out average grouping.
本发明提供一种彩色数字影像色度校正系统，包括以下模块：The invention provides a color digital image chromaticity correction system, comprising the following modules:
典型色彩样本光谱数据集构建模块，用于选取M个典型色彩样本，以各典型色彩样本可见光范围内的光谱反射率数据构成典型色彩样本光谱反射率数据集Gs；The typical color sample spectral data set building module is used to select M typical color samples, and form the typical color sample spectral reflectance data set G s with the spectral reflectance data in the visible light range of each typical color sample;
典型色彩样本色度数据集计算模块，用于以典型色彩样本光谱数据集构建模块中各典型色彩样本的光谱反射率数据为基础，利用如下色度学公式分别计算各样本在源光源Ls条件下的色度信息，并组成典型色彩样本色度数据集Gc，The typical color sample chromaticity data set calculation module is used to use the following chromaticity formula to calculate the conditions of each sample in the source light source L s based on the spectral reflectance data of each typical color sample in the typical color sample spectral data set construction module. The chromaticity information under , and constitute the typical color sample chromaticity data set G c ,
X＝k∫x(λ)E(λ)S(λ)dλ,X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,Y=k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,Z=k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],k=100/[∫y(λ)E(λ)dλ],
其中，X、Y、Z表示色度三刺激值，λ表示可见光各波段波长；x(λ)、y(λ)、z(λ)为人眼视觉匹配函数，照明光源E(λ)采用源光源Ls相应的相对光谱功率分布曲线，颜色物体光谱反射率S(λ)采用样本相应可见光范围内的光谱反射率数据，k为参数；Among them, X, Y, and Z represent the tristimulus value of chromaticity, and λ represents the wavelength of each band of visible light; x(λ), y(λ), z(λ) are human visual matching functions, and the illumination source E(λ) adopts the source light source The relative spectral power distribution curve corresponding to L s , the spectral reflectance S(λ) of the color object adopts the spectral reflectance data in the corresponding visible light range of the sample, and k is a parameter;
数据集分组模块，用于计算典型色彩样本色度数据集Gc中各样本主波长及色纯度信息，以主波长为分组依据对典型色彩样本色度数据集Gs进行首次分组，随后以色纯度为分组依据对首次分组所得集合进行二次分组，记最终分组数量为T，得到T个子集；The data set grouping module is used to calculate the dominant wavelength and color purity information of each sample in the typical color sample chromaticity data set G c , group the typical color sample chromaticity data set G s for the first time based on the dominant wavelength, and then use the color Purity is the basis for grouping. The set obtained by the first grouping is grouped twice, and the final grouping number is T, and T subsets are obtained;
分组子集色度信息求解模块，用于针对数据集分组模块二次分组后所得典型色彩样本色度数据集Gs的T个子集，分别以目的光源Lt为照明光源E(λ)，利用所述色度学公式求解目的光源Lt条件下子集中各样本的色度信息；The grouping subset chromaticity information solving module is used for T subsets of the typical color sample chromaticity data set G s obtained after secondary grouping by the data set grouping module, respectively using the target light source L t as the lighting source E(λ), using The chromaticity formula solves the chromaticity information of each sample in the subset under the condition of the target light source L t ;
神经网络训练模块，用于针对各子集，分别以数据集分组模块分组所得该子集的源光源Ls条件下各样本色度信息为输入端，以分组子集色度信息求解模块求解所得该子集的目的光源Lt条件下各样本色度信息为输出端，训练相应的BP神经网络；The neural network training module is used for each subset, using the chromaticity information of each sample under the condition of the source light source L s of the subset obtained by grouping the data set grouping module as the input terminal, and solving the obtained result by the chromaticity information solving module of the grouping subset The chromaticity information of each sample under the condition of the target light source L t of the subset is the output terminal, and the corresponding BP neural network is trained;
色度校正模块，用于针对源光源条件下某一色度信息Cs，计算主波长与色纯度信息，根据数据集分组模块的分组方式，确定对应的子集及BP神经网络，并利用该BP神经网络预测色度信息Cs在目的光源条件下所对应的色度信息Ct。The chromaticity correction module is used to calculate the dominant wavelength and color purity information for a certain chromaticity information Cs under the condition of the source light source, determine the corresponding subset and BP neural network according to the grouping method of the data set grouping module, and use the BP neural network The network predicts the chromaticity information Ct corresponding to the chromaticity information Cs under the condition of the target light source.
而且，数据集分组模块中以主波长对数据集Gs进行首次分组时将主波长为负值的所有样本作为一组，之后将其它样本以主波长为依据进行平均分组；随后将上述首次分组所得所有分组子集以色纯度为二次分组依据，进行平均分组。Moreover, when the data set G s is first grouped by the main wavelength in the data set grouping module, all samples with a negative value of the main wavelength are taken as a group, and then other samples are averagely grouped based on the main wavelength; then the above-mentioned first grouping All obtained grouping subsets are grouped on average based on the color purity as the secondary grouping basis.
本发明提出的一种基于典型色彩样本光谱反射率数据集的彩色数字影像色度校正技术方案，在确定典型色彩样本光谱反射率数据集以及色度校正源与目的光源的前提下，结合主波长及色纯度分组方法，通过BP神经网络构建同一颜色样本在不同照明条件下色度差异的关联性模型，进而实现了不同照明场景条件下影像色彩色度信息的准确映射与传递。此方法较为理想的解决了背景技术部分所述问题，从而可以保证彩色数字影像信息传递过程的准确性，进而满足高品质彩色影像信息记录与再现的需求。因此，本发明解决了不同照明条件下影像色彩色度信息准确传递的问题，且实施方便，在彩色数字影像记录与再现领域具有较强的适用性。由于本发明技术方案具有重要应用意义，受到多个项目支持：1.中国博士后面上基金2014M5606253.2.国家自然基金项目61275172.3.国家文物局文物保护领域科学和技术研究一般课题2013-YB-HT-034.4.国家973基础研究子项目2012CB725302。对本发明技术方案进行保护，将对我国相关行业竞争国际领先地位具有重要意义。A color digital image chromaticity correction technical scheme based on a typical color sample spectral reflectance data set proposed by the present invention, on the premise of determining the typical color sample spectral reflectance data set and the chromaticity correction source and target light source, combined with the dominant wavelength And the color purity grouping method, through the BP neural network to construct the correlation model of the chromaticity difference of the same color sample under different lighting conditions, and then realize the accurate mapping and transmission of image color and chromaticity information under different lighting scene conditions. This method ideally solves the problems mentioned in the background technology section, thereby ensuring the accuracy of the color digital image information transmission process, and further meeting the requirements for high-quality color image information recording and reproduction. Therefore, the present invention solves the problem of accurate transmission of image color and chromaticity information under different lighting conditions, is easy to implement, and has strong applicability in the field of color digital image recording and reproduction. Because the technical solution of the present invention has important application significance, it is supported by multiple projects: 1. China Postdoctoral Postgraduate Fund 2014M5606253. 2. National Natural Science Foundation of China Project 61275172. 3. General Project of Scientific and Technical Research in the Field of Cultural Relics Protection of the State Administration of Cultural Heritage 2013-YB-HT -034.4. National 973 Basic Research Subproject 2012CB725302. The protection of the technical solution of the present invention will be of great significance to the competition of the relevant industries in my country for the leading position in the world.
附图说明Description of drawings
图1为本发明实施例的流程图。Fig. 1 is a flowchart of an embodiment of the present invention.
具体实施方式Detailed ways
结合附图，提供本发明实施例具体描述如下。In conjunction with the accompanying drawings, the specific description of the embodiments of the present invention is provided as follows.
如图1所示实施例提供的一种基于典型色彩样本光谱反射率数据集的彩色数字影像色度校正方法，较为理想的解决了不同影像客体及照明场景条件下的色度校正问题，可以保证彩色数字影像信息传递过程的准确性，进而满足高品质彩色影像信息记录与再现的需求。实施例采用9297个色彩样本构建典型色彩样本集，以1250个孟赛尔无光泽色彩样本作为实验检验样本集，以D65标准照明体为源光源，以A标准照明体为目的光源，以本发明所述方法进行色度校正。并将Von Kries方法,Wrong Von Kries方法，Bradford方法,Helson方法,Bartleson方法，Hunt方法等6种色适应变换以及参考文献3中Kreslin方法共7种现有方法作为对照。需要说明的是，本发明并不局限于上述影像客体及光源类型，对于其它影像客体及光源类型，本方法同样适用。A color digital image chromaticity correction method based on a typical color sample spectral reflectance data set provided by the embodiment shown in Figure 1 ideally solves the chromaticity correction problem under different image objects and lighting scene conditions, and can ensure The accuracy of the color digital image information transmission process can meet the needs of high-quality color image information recording and reproduction. The embodiment adopts 9297 color samples to construct a typical color sample set, takes 1250 Munsell matte color samples as the experimental test sample set, takes the D65 standard illuminant as the source light source, and takes the A standard illuminant as the target light source, and the present invention The method performs colorimetric correction. And 6 kinds of chromatic adaptation transformations including Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, Hunt method and 7 existing methods including Kreslin method in Reference 3 were used as comparison. It should be noted that the present invention is not limited to the above image objects and light source types, and the method is also applicable to other image objects and light source types.
本发明技术方案具体实施时可由本领域技术人员采用计算机软件技术实现自动运行。实施例提供的方法流程包括以下步骤：When the technical solution of the present invention is specifically implemented, it can be automatically operated by those skilled in the art by using computer software technology. The method flow provided by the embodiment includes the following steps:
1)选取M个典型色彩样本，以各样本可见光范围内的光谱反射率数据构成典型色彩样本光谱反射率数据集Gs；1) Select M typical color samples, and use the spectral reflectance data of each sample in the visible light range to form a typical color sample spectral reflectance data set G s ;
本领域技术人员可以自行预设M的取值。具体实施时，应尽量保证样本集色彩色域的最大化。可见光范围一般为380nm—780nm。具体实施时，可预先用分光光度计测量各样本的相应光谱反射率信息，取380nm—780nm波段数据。实施例中，将打印设备色域内均匀采样制备的6000个色彩样本、1687个日本典型颜料色彩样本以及1600个孟赛尔光泽色彩样本共9297个样本作为典型样本集(M＝9297)，该样本集具有广阔的色域，且样本分布均匀。具体实施时，可以预先生成典型色彩样本光谱反射率数据集Gs并输入。Those skilled in the art can preset the value of M by themselves. During specific implementation, try to maximize the color gamut of the sample set. The visible light range is generally 380nm-780nm. During specific implementation, the corresponding spectral reflectance information of each sample can be measured in advance with a spectrophotometer, and the data in the 380nm-780nm band can be obtained. In the embodiment, a total of 9297 samples of 6000 color samples, 1687 Japanese typical pigment color samples and 1600 Munsell gloss color samples prepared by uniform sampling in the color gamut of printing equipment are used as a typical sample set (M=9297). The set has a wide color gamut with evenly distributed samples. During specific implementation, the typical color sample spectral reflectance data set G s may be pre-generated and input.
2)以1)中各样本的光谱反射率数据为基础，利用如下色度学公式分别计算各样本在源光源Ls条件下的色度信息，并组成典型色彩样本色度数据集Gc，2) Based on the spectral reflectance data of each sample in 1), use the following chromaticity formula to calculate the chromaticity information of each sample under the condition of the source light source L s , and form a typical color sample chromaticity data set G c ,
X＝k∫x(λ)E(λ)S(λ)dλ,X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ, 式一Y＝k∫y(λ)E(λ)S(λ)dλ, Formula 1
Z＝k∫z(λ)E(λ)S(λ)dλ,Z=k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],k=100/[∫y(λ)E(λ)dλ],
其中，X、Y、Z表示色度三刺激值，λ表示可见光各波段波长；x(λ)、y(λ)、z(λ)为人眼视觉匹配函数，照明光源E(λ)采用源光源Ls相应的相对光谱功率分布曲线，颜色物体光谱反射率S(λ)采用样本相应可见光范围内的光谱反射率数据，k为由y(λ)、E(λ)确定的参数；Among them, X, Y, and Z represent the tristimulus value of chromaticity, and λ represents the wavelength of each band of visible light; x(λ), y(λ), z(λ) are human visual matching functions, and the illumination source E(λ) adopts the source light source The relative spectral power distribution curve corresponding to L s , the spectral reflectance S(λ) of the color object adopts the spectral reflectance data in the corresponding visible light range of the sample, and k is a parameter determined by y(λ) and E(λ);
在实施例中，本步骤实现M＝9297个典型色彩样本在源光源LS下的色度值求解，各色度值即组成典型色彩样本色度数据集Gc。其中，源光源LS设为D65标准照明体，即E(λ)采用D65标准照明体相应的相对光谱功率分布曲线。针对各样本，S(λ)分别采用相应可见光范围内的光谱反射率数据。In the embodiment, this step realizes the calculation of the chromaticity values of M=9297 typical color samples under the source light source L S , and each chromaticity value constitutes the typical color sample chromaticity data set G c . Wherein, the source light source L S is set as the D65 standard illuminant, that is, E(λ) adopts the corresponding relative spectral power distribution curve of the D65 standard illuminant. For each sample, S(λ) uses the spectral reflectance data in the corresponding visible light range, respectively.
3)以色度学理论现有主波长及色纯度计算公式计算典型色彩样本色度数据集Gc中各样本主波长及色纯度信息，以主波长为分组依据对数据集Gs进行首次分组，随后以色纯度为分组依据对首次分组所得集合进行二次分组，记最终分组数量为T；3) Calculate the dominant wavelength and color purity information of each sample in the typical color sample chromaticity data set G c with the existing dominant wavelength and color purity calculation formula of colorimetry theory, and group the data set G s for the first time based on the dominant wavelength , and then use the color purity as the grouping basis to carry out secondary grouping on the collection obtained from the first grouping, and record the final grouping number as T;
在实施例中，以主波长对数据集Gs进行首次分组时，将主波长为负值的所有样本作为一组，之后将其它样本以主波长为依据进行平均分组(具体分组数可由本领域技术人员设定)，实施例的主波长正值平均分组数为5，和负值样本组一起共分6组；随后将上述首次分组所得6组分组子集以色纯度为二次分组依据，进行平均分组(具体分组数可由本领域技术人员设定)，实施例二次分组的平均分组数为2，最终得T＝12个分组。其主波长及色纯度范围分别为In an embodiment, when the data set G s is grouped for the first time with the dominant wavelength, all samples with a negative value of the dominant wavelength are taken as a group, and then other samples are averagely grouped based on the dominant wavelength (the specific number of groups can be provided by those skilled in the art Technicians set), the positive average grouping number of the dominant wavelength of the embodiment is 5, and is divided into 6 groups together with the negative sample group; then the 6 group sub-sets obtained by the above-mentioned first grouping take the color purity as the secondary grouping basis, Carry out average grouping (the specific grouping number can be set by those skilled in the art), the average grouping number of embodiment secondary grouping is 2, finally get T=12 groupings. Its dominant wavelength and color purity ranges are
第一组：380nm≤主波长≤480nm,色纯度≤0.31；The first group: 380nm≤dominant wavelength≤480nm, color purity≤0.31;
第二组：380nm≤主波长≤480nm,色纯度＞0.31；The second group: 380nm≤dominant wavelength≤480nm, color purity>0.31;
第三组：480nm＜主波长≤503nm,色纯度≤0.21；The third group: 480nm<dominant wavelength≤503nm, color purity≤0.21;
第四组：480nm＜主波长≤503nm,色纯度＞0.21；The fourth group: 480nm<dominant wavelength≤503nm, color purity>0.21;
第五组：503nm＜主波长≤569nm,色纯度≤0.23；The fifth group: 503nm<dominant wavelength≤569nm, color purity≤0.23;
第六组：503nm＜主波长≤569nm,色纯度＞0.23；The sixth group: 503nm<dominant wavelength≤569nm, color purity>0.23;
第七组：569nm＜主波长≤588nm,色纯度≤0.39；The seventh group: 569nm<dominant wavelength≤588nm, color purity≤0.39;
第八组：569nm＜主波长≤588nm,色纯度＞0.39；The eighth group: 569nm<dominant wavelength≤588nm, color purity>0.39;
第九组：588nm＜主波长≤780nm,色纯度≤0.41；The ninth group: 588nm<dominant wavelength≤780nm, color purity≤0.41;
第十组：588nm＜主波长≤780nm,色纯度＞0.41；The tenth group: 588nm<dominant wavelength≤780nm, color purity>0.41;
第十一组：主波长＜0,色纯度≤0.18；The eleventh group: dominant wavelength < 0, color purity ≤ 0.18;
第十二组：主波长＜0,色纯度＞0.18；The twelfth group: dominant wavelength<0, color purity>0.18;
其中，主波长及色纯度的计算方法可参见J.Schanda.CIE colorimetry[M].Wiley OnlineLibrary，2007，本发明不予赘述。Wherein, the calculation method of dominant wavelength and color purity can refer to J.Schanda.CIE colorimetry[M].Wiley Online Library, 2007, which will not be repeated in the present invention.
4)针对3)二次分组后所得数据集Gs的各个子集，分别利用2)中所述方法求解目的光源Lt条件下各组子集中各样本的色度信息，包以目的光源Lt为照明光源E(λ)按式一进行求解；4) For each subset of the data set G s obtained after the secondary grouping in 3), use the method described in 2) to solve the chromaticity information of each sample in each group subset under the condition of the target light source L t , including the target light source L t is the lighting source E(λ) to be solved according to Formula 1;
在实施例中，针对3)所得数据集Gs的12个子集，分别利用2)中式一，以标准照明体A为目的光源Lt，求解目的光源条件下各组子集中各样本的色度信息。In the embodiment, for 3) the 12 subsets of the obtained data set G s , use 2) Chinese formula 1 respectively, take the standard lighting body A as the target light source L t , and solve the chromaticity of each sample in each group of subsets under the target light source condition information.
5)针对各子集，分别以3)分组所得该组子集的源光源Ls条件下各样本色度信息为输入端，以4)求解所得该组子集的目的光源Lt条件下各样本色度信息为输出端，训练相应的BP神经网络；5) For each subset, the chromaticity information of each sample under the condition of the source light source L s of the group of subsets obtained by 3) grouping is used as the input terminal, and the chromaticity information of each sample is obtained under the condition of the target light source L t of the group of subsets obtained by solving 4). The sample chromaticity information is the output terminal, and the corresponding BP neural network is trained;
实施例中，以3)中分组得到的各子集在源光源Ls条件下的色度信息作为输入数据，以4)中求解的各组子集在目标光源Lt条件下的色度信息作为输出数据，构建BP神经网络。其中，针对3)中所得12个分组子集，共需构建12条BP神经网络。具体实施时，可参见BP神经网络现有技术实现。In the embodiment, the chromaticity information of each subset obtained by grouping in 3) under the condition of source light source L s is used as input data, and the chromaticity information of each group of subsets obtained in 4) under the condition of target light source L t is used as input data As output data, a BP neural network is constructed. Among them, for the 12 grouping subsets obtained in 3), a total of 12 BP neural networks need to be constructed. For specific implementation, reference may be made to the prior art implementation of the BP neural network.
这样，基于源光源条件下各分组样本集色度信息和目的光源条件下各分组样本集色度信息，可以针对各对应分组数据拟合构建神经网络，用于后续源光源条件下色度信息基于分组判别获取目的光源条件下色度信息。In this way, based on the chromaticity information of each grouped sample set under the condition of the source light source and the chromaticity information of each grouped sample set under the condition of the target light source, a neural network can be constructed for each corresponding grouped data, which is used for subsequent chromaticity information under the condition of the source light source based on Group discrimination to obtain chromaticity information under the target light source conditions.
6)针对源光源条件下某一色度信息Cs，利用色度学理论现有主波长及色纯度计算公式计算其主波长与色纯度信息，并结合3)所述分组情况，确定与其对应的子集及BP神经网络，并利用该BP神经网络预测其在目的光源条件下所对应的色度信息Ct。6) For a certain chromaticity information Cs under the condition of source light source, use the existing dominant wavelength and color purity calculation formula of chromatic theory to calculate its dominant wavelength and color purity information, and combine the grouping situation described in 3) to determine its corresponding sub Set and BP neural network, and use the BP neural network to predict its corresponding chromaticity information Ct under the condition of the target light source.
在实施例中，以某色彩样本在源光源条件下色度信息Cs为例，其CIEXYZ值为(84,89,99)利用色度学理论现有主波长及色纯度计算公式计算其主波长与色纯度信息，得其主波长为477nm，色纯度为0.01，则由实施例中3)可知其属于第一个分组，故利用第一组数据所对应BP神经网络预测其在目标光源条件下色度信息Ct，求解得其CIEXYZ值为(97,88,33)，与理论值(98,89,32)甚为接近。In the embodiment, taking the chromaticity information Cs of a certain color sample under the condition of the source light source as an example, its CIEXYZ value is (84, 89, 99), and its dominant wavelength is calculated by using the existing dominant wavelength and color purity calculation formula of the chromaticity theory According to the color purity information, the dominant wavelength is 477nm, and the color purity is 0.01, then it can be seen from 3) in the embodiment that it belongs to the first group, so the BP neural network corresponding to the first group of data is used to predict its performance under the target light source condition For the chromaticity information Ct, its CIEXYZ value is (97,88,33), which is very close to the theoretical value (98,89,32).
具体实施时，针对任意源光源条件到任意目的光源条件按照步骤1～5预先建立子集划分及相应BP神经网络，即可用于相应色度信息预测。During specific implementation, for any source light source condition to any destination light source condition, the subset division and the corresponding BP neural network are pre-established according to steps 1-5, which can be used for corresponding chromaticity information prediction.
为进一步证实本发明方法在色度校正精度方面的优势，以1250个孟赛尔无光泽色彩样本作为实验检验样本集，以D65标准照明体为源光源，以A标准照明体为目的光源，以本发明所述方法进行色度校正。并将Von Kries方法,Wrong Von Kries方法，Bradford方法,Helson方法,Bartleson方法，Hunt方法等6种色适应变换以及参考文献3中Kreslin方法共7种现有方法作为对照。实验结果显示，Von Kries方法,Wrong Von Kries方法，Bradford方法,Helson方法,Bartleson方法，Hunt方法以及Kreslin方法以色差公式CIEDE2000表示的色度校正精度分别为4.67、2.86、5.38、3.36、4.76、4.13、2.11，而本发明色度校正精度为1.53，精度优势明显。其中，CIEDE2000色差公式可参见Ming R Luo.CIE 2000 color difference formula:CIEDE2000[A].In 9th Congress of the International Color Association[C]，Year：554-9.本发明不予赘述。In order to further confirm the advantages of the inventive method in terms of chromaticity correction accuracy, 1250 Munsell matt color samples are used as the experimental test sample set, the D65 standard illuminant is the source light source, and the A standard illuminant is the target light source. The method of the present invention performs colorimetric correction. And 6 kinds of chromatic adaptation transformations including Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, Hunt method and 7 existing methods including Kreslin method in Reference 3 were used as comparison. The experimental results show that the chromaticity correction accuracy expressed by the color difference formula CIEDE2000 of Von Kries method, Wrong Von Kries method, Bradford method, Helson method, Bartleson method, Hunt method and Kreslin method are 4.67, 2.86, 5.38, 3.36, 4.76, 4.13 respectively , 2.11, and the chromaticity correction precision of the present invention is 1.53, and the precision advantage is obvious. Among them, the CIEDE2000 color difference formula can be found in Ming R Luo. CIE 2000 color difference formula: CIEDE2000[A]. In 9th Congress of the International Color Association[C], Year: 554-9. The present invention will not go into details.
本发明还相应提供一种彩色数字影像色度校正系统，包括以下模块：The present invention also correspondingly provides a color digital image chromaticity correction system, including the following modules:
典型色彩样本光谱数据集构建模块，用于选取M个典型色彩样本，以各典型色彩样本可见光范围内的光谱反射率数据构成典型色彩样本光谱反射率数据集Gs；The typical color sample spectral data set building module is used to select M typical color samples, and form the typical color sample spectral reflectance data set G s with the spectral reflectance data in the visible light range of each typical color sample;
典型色彩样本色度数据集计算模块，用于以典型色彩样本光谱数据集构建模块中各典型色彩样本的光谱反射率数据为基础，利用如下色度学公式分别计算各样本在源光源Ls条件下的色度信息，并组成典型色彩样本色度数据集Gc，The typical color sample chromaticity data set calculation module is used to use the following chromaticity formula to calculate the conditions of each sample in the source light source L s based on the spectral reflectance data of each typical color sample in the typical color sample spectral data set construction module. The chromaticity information under , and constitute the typical color sample chromaticity data set G c ,
X＝k∫x(λ)E(λ)S(λ)dλ,X＝k∫x(λ)E(λ)S(λ)dλ,
Y＝k∫y(λ)E(λ)S(λ)dλ,Y=k∫y(λ)E(λ)S(λ)dλ,
Z＝k∫z(λ)E(λ)S(λ)dλ,Z=k∫z(λ)E(λ)S(λ)dλ,
k＝100/[∫y(λ)E(λ)dλ],k=100/[∫y(λ)E(λ)dλ],
其中，X、Y、Z表示色度三刺激值，λ表示可见光各波段波长；x(λ)、y(λ)、z(λ)为人眼视觉匹配函数，照明光源E(λ)采用源光源Ls相应的相对光谱功率分布曲线，颜色物体光谱反射率S(λ)采用样本相应可见光范围内的光谱反射率数据，k为参数；Among them, X, Y, and Z represent the tristimulus value of chromaticity, and λ represents the wavelength of each band of visible light; x(λ), y(λ), z(λ) are human visual matching functions, and the illumination source E(λ) adopts the source light source The relative spectral power distribution curve corresponding to L s , the spectral reflectance S(λ) of the color object adopts the spectral reflectance data in the corresponding visible light range of the sample, and k is a parameter;
数据集分组模块，用于计算典型色彩样本色度数据集Gc中各样本主波长及色纯度信息，以主波长为分组依据对典型色彩样本色度数据集Gs进行首次分组，随后以色纯度为分组依据对首次分组所得集合进行二次分组，记最终分组数量为T，得到T个子集；The data set grouping module is used to calculate the dominant wavelength and color purity information of each sample in the typical color sample chromaticity data set G c , group the typical color sample chromaticity data set G s for the first time based on the dominant wavelength, and then use the color Purity is the basis for grouping. The set obtained by the first grouping is grouped twice, and the final grouping number is T, and T subsets are obtained;
分组子集色度信息求解模块，用于针对数据集分组模块二次分组后所得典型色彩样本色度数据集Gs的T个子集，分别以目的光源Lt为照明光源E(λ)，利用所述色度学公式求解目的光源Lt条件下子集中各样本的色度信息；The grouping subset chromaticity information solving module is used for T subsets of the typical color sample chromaticity data set G s obtained after secondary grouping by the data set grouping module, respectively using the target light source L t as the lighting source E(λ), using The chromaticity formula solves the chromaticity information of each sample in the subset under the condition of the target light source L t ;
神经网络训练模块，用于针对各子集，分别以数据集分组模块分组所得该子集的源光源Ls条件下各样本色度信息为输入端，以分组子集色度信息求解模块求解所得该子集的目的光源Lt条件下各样本色度信息为输出端，训练相应的BP神经网络；The neural network training module is used for each subset, using the chromaticity information of each sample under the condition of the source light source L s of the subset obtained by grouping the data set grouping module as the input terminal, and using the grouping subset chromaticity information solving module to solve the obtained The chromaticity information of each sample under the condition of the target light source L t of the subset is the output terminal, and the corresponding BP neural network is trained;
色度校正模块，用于针对源光源条件下某一色度信息Cs，计算主波长与色纯度信息，根据数据集分组模块的分组方式，确定对应的子集及BP神经网络，并利用该BP神经网络预测色度信息Cs在目的光源条件下所对应的色度信息Ct。The chromaticity correction module is used to calculate the dominant wavelength and color purity information for a certain chromaticity information Cs under the condition of the source light source, determine the corresponding subset and BP neural network according to the grouping method of the data set grouping module, and use the BP neural network The network predicts the chromaticity information Ct corresponding to the chromaticity information Cs under the condition of the target light source.
其中，数据集分组模块中以主波长对数据集Gs进行首次分组时将主波长为负值的所有样本作为一组，之后将其它样本以主波长为依据进行平均分组；随后将上述首次分组所得所有分组子集以色纯度为二次分组依据，进行平均分组。Among them, when the data set grouping module uses the main wavelength to group the data set G s for the first time, all samples with a negative value of the main wavelength are taken as a group, and then other samples are averagely grouped based on the main wavelength; then the above-mentioned first grouping All obtained grouping subsets are grouped on average based on the color purity as the secondary grouping basis.
各模块具体实现和各步骤相应，本发明不予赘述。The specific implementation of each module is corresponding to each step, and the present invention will not repeat them.
本文中所描述的具体实施例仅仅是对本发明精神作举例说明。本发明所属技术领域的技术人员可以对所描述的具体实施例做各种各样的修改或补充或采用类似的方式替代，但并不会偏离本发明的精神或者超越所附权利要求书所定义的范围。The specific embodiments described herein are merely illustrative of the spirit of the invention. Those skilled in the art to which the present invention belongs can make various modifications or supplements to the described specific embodiments or adopt similar methods to replace them, but they will not deviate from the spirit of the present invention or go beyond the definition of the appended claims range.
Claims (4)
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 | Method and system for generating and evaluating metamerism spectrum 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 | A Wide Color Gamut Chroma Characterization Method for 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 optimization method and system for color digital image 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 optimization method and system for color digital image 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 | Method and system for generating and evaluating metamerism spectrum for light source detection |
| CN108519157B (en) * | 2018-03-16 | 2019-07-09 | 武汉大学 | A method and system for generating and evaluating metamerism spectrum 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 | A Wide Color Gamut Chroma Characterization Method for 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 |
|---|---|---|
| CN104410850B (en) | Colorful digital image chrominance correction method and system | |
| CN109903256A (en) | Model training method, chromatic aberration calibrating method, device, medium and electronic equipment | |
| CN105069234B (en) | The spectrum dimension reduction method and system of a kind of view-based access control model Perception Features | |
| CN104217409B (en) | A kind of image color correction method based on simulated annealing optimization algorithm | |
| CN105973572B (en) | A kind of multi-colored led spectrum optimization method for realizing the optimal colour rendering of light source | |
| CN110231148B (en) | A method and system for evaluating the color rendering of an exhibition light source for color resolution | |
| CN113487681B (en) | Camera color calibration method based on spectral sensitivity curve and light source spectrum optimization | |
| CN110677954B (en) | Precise dimming method and system for super three-color LED light source | |
| CN107346653B (en) | GAMMA curve adjusting method and device based on deep learning | |
| CN103854261B (en) | The bearing calibration of colour cast image | |
| CN104092919B (en) | Chromatic adaptation transformation optimizing method and system for color digital imaging system | |
| CN105973470A (en) | Spectrum matching method for multicolor LED to realize chroma limitation | |
| CN104751819B (en) | Display device inverse characterizing method | |
| CN102799895B (en) | Based on the offset ink color matching method of least square method supporting vector machine | |
| CN104464623A (en) | Method and device for adjusting low gray scales of LED | |
| CN101778299A (en) | Method for color space conversion and system thereof | |
| CN113189021A (en) | Method for identifying rock color based on spectrum | |
| CN110163217B (en) | Method, apparatus and computer readable storage medium for color matching or color matching assistance | |
| CN103973980A (en) | Method for acquiring multispectral images based on digital camera | |
| US7659982B2 (en) | Quantitative evaluation of a color filter | |
| CN113033777A (en) | Vehicle-mounted atmosphere lamp chromaticity calibration method based on neural network calibration model | |
| CN104182627B (en) | A kind of display device color accurately predicts characterizing method | |
| CN104504262B (en) | Display colour filter transmitance spectral line distribution optimization method | |
| CN104813148A (en) | Method and apparatus for aligning measurements of color measurement instruments | |
| Li et al. | Spectral optimization of white LED based on mesopic luminance and color gamut volume for dim lighting conditions |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170222 Termination date: 20201225 |