Please wait a minute...
J4  2011, Vol. 45 Issue (2): 253-258    DOI: 10.3785/j.issn.1008-973X.2011.02.010
    
Robust algorithm for extracting skin pigment concentration
from color image
Xu Shu-chang1, ZHANG San-yuan2, ZHANG Yin2
1.Department of Information Science & Engineering, Hangzhou Normal University, Hangzhou 310036, China;
2. Department of Computer Science, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

To investigate the two most important pigments of human, melanin and hemoglobin, an image-channel-difference of optical density space based algorithm was proposed for automatically extracting melanin and hemoglobin concentration distribution map from single color image. The algorithm built mathematic model between pigment and digital image based on theoretical foundation of skin structure and its optical property. The input image firstly was divided into several sub-regions. Independent component analysis (ICA) technology was performed in every sub-region to calculate Separation Vector, which is successively verified by specified rules. All the valid Separation Vectors were then re-combined to form new vectors, from which the final separation vector with minimal deviation is selected. The pigment concentration distribution maps were displayed after obtaining the final global separation vector. The experiments show the effectiveness and great robustness of the proposed algorithm.



Published: 17 March 2011
CLC:  TP 391.4  
Cite this article:

Xu Shu-chang, ZHANG San-yuan, ZHANG Yin. Robust algorithm for extracting skin pigment concentration
from color image. J4, 2011, 45(2): 253-258.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.02.010     OR     http://www.zjujournals.com/eng/Y2011/V45/I2/253


基于彩色图像的皮肤色素浓度提取算法

为了研究人体皮肤中最重要的2种色素:黑色素与血色素,提出一种基于光密度空间的图像通道差的算法,从单张彩色图像中自动提取黑色素与血色素的浓度分布.该算法以皮肤的结构和光学属性为理论基础,构建色素与图像的数学模型.整个算法先将输入图像分为若干个子区域.在每个子区域利用独立成份分析ICA技术计算分离向量,根据归纳的原则对分离向量进行合理性验证.将所有合理的分离向量重组,生成新的向量,从中找出偏差最小的作为最终的全局分离向量,并以此计算色素浓度分布图.结果表明,该算法获得了理想的效果,并具有很好的鲁棒性.

[1] DAWSON J B, BARKER D J, ELLIS D J, et al. A theoretical and experimental study of light absorption and scattering by in vivo skin [J]. Physics in Medicine and Biology, 1980, 25 (4): 695-709.
[2] FEATURE J W, ELIS D J, LESLIE G. A portable reflectormeter for the rapid quantification of cutanaous haemoglobin and melanin [J]. Physics in Medicine and Biology, 1988, 33 (6): 711-722.
[3] FEATURE J W, SAFFAR M H, LESLIE G et al. A portable scanning reflectance spectrophotometer using visible wavelengths for the rapid measurement of skin pigments [J]. Physics in Medicine and Biology, 1989, 34 (7): 807-820.
[4] JONES M J, REHG J M. Statistical color models with application to skin detection [C] ∥Proceedings of Computer Vision and Pattern Recognition. Santa Barbara, USA: IEEE Computer Society, 1998, 1: 274-280.
[5] COTTON S, CLARIDEG E. Developing a predictive model of human skin colouring [C] ∥ Proceedings of the SPIE medical imaging. Newport Beach, USA: SPIE, 1996, 2708: 814-825.
[6] TAKIWAKI H, KANNO Y, MIYAOKA Y, et al. Computer simulation of skin color based on a multilayered skin model [J]. Skin Research and Technology. 1997, 3 (1): 36-41.
[7] CLARIDGE E, COTTON S, HALL P, et al. From colour to tissue histology: Physics based interpretation of images of pigmented skin lesions [J]. Medical Image Analysis, 2003, 7 (4): 489-505.
[8] 徐舒畅,张三元,张引.利用颜色模拟估算皮肤色素浓度[J].浙江大学学报:工学版,2009,43(6): 983-986.
XU Shuchang, ZHANG Sanyuan, ZHANG Yin. Estimation of skin pigments concentration by simulating skin color [J]. Journal of Zhejiang University: Engineering Science, 2009, 43(6): 983-986.
[9] KOBAYASHI M, ITO Y, SAKAUCHI N, et al. Analysis of nonlinear relation for skin hemoglobin imaging [J]. Optics Express, 2001, 9 (13): 802-812.

[10] TSUMURA N, KOBAYASHI M, HANEISHI H, et al. Mapping pigmentation in human skin by Multivisiblespectral imaging by inverse optical scattering technique [C] ∥ Proceedings of 8th Color Imaging Conference. Scottsdale: IS&T, 2000, 81-84.
[11] TSUMURA N, HANEISHI H, MIYAKE Y. Independent component analysis of skin color image [J]. Journal of Optical Society of America, 1999, 16 (9): 2169-2176.
[12] TSUMURA N, OJIMA N, SATO K, et al. Imagebased skin color and texture analysis/synthesis by extracting hemoglobin and melanin information in the skin [C] ∥ Proceedings of ACM SIGGRAPH. San Diego, USA: IEEE Computer Society, 2003, 770-779.
[13] XU S, YE X, WU Y, GIRON F, et al. Automatic skin decomposition based on single image [J]. Computer Vision and Image Understanding, 2008, 110(1): 1-6.
[14] KRISHNASWAMY A, BARANSOKI G. V. G. A study on skin optics [R]. Canada: University of Waterloo, 2004.
[15] TAKIWAKI H. Measurement of skin color: practical application and theoretical considerations [J]. The Journal of Medical Investigation, 1998, 44(3/4): 121-126.
[16] BINGHAM E, HYV¨ARINEN A.. A fast fixedpoint algorithm for independent component analysis of complex valued signals [J]. International Journal of Neural Systems, 2000, 10 (1): 1-8.

[1] XU Song,SUN Xiu-xia,HE Yan. Iterative method of camera distortion calibration utilizing lines-imaging characteristics[J]. J4, 2014, 48(3): 404-413.
[2] . Augmented reality registration from nature features ased on planar color distribution[J]. J4, 2013, 47(12): 2243-2252.
[3] YANG Bang-hua, HE Mei-yan, LIU Li, LU Wen-yu. EEG classification based on batch incremental SVM in
brain computer interfaces
[J]. J4, 2013, 47(8): 1431-1436.
[4] YANG Bing, XU Duan-qing, YANG Xin, ZHAO Lei, TANG Da-wei. Painting image classification based on aesthetic style similarity rule[J]. J4, 2013, 47(8): 1486-1492.
[5] LOU Xiao-jun, SUN Yu-xuan, LIU Hai-tao. Clustering boundary over-sampling classification method for imbalanced data sets[J]. J4, 2013, 47(6): 944-950.
[6] MENG Zi-bo, JIANG Hong, CHEN Jing, YUAN Bo, WANG Li-qiang. Feature pruning based AdaBoost and its application in face detection[J]. J4, 2013, 47(5): 906-911.
[7] HE Zhi-xiang, DING Xiao-qing, FANG Chi, WEN Di. Multiview face detection based on LBP and CCS-AdaBoost[J]. J4, 2013, 47(4): 622-629.
[8] LIU Xiao-fang,YE Xiu-zi ,ZHANG San-yuan ,ZHANG Yin. Non-quadratic regularized edge-preserving reconstruction for
parallel magnetic resonance image
[J]. J4, 2012, 46(11): 2035-2043.
[9] ZHANG Yuan-hui,WEI Wei. Online angular velocity estimated visual measurement for ping pong robot[J]. J4, 2012, 46(7): 1320-1326.
[10] SHI Jin-he, SHENG Ji-zhong, WANG Pan. Feature extraction and classification of four-class
motor imagery EEG data
[J]. J4, 2012, 46(2): 338-344.
[11] ZHANG Da-wei, ZHU Shan-an. Face recognition based kernel neighborhood preserving
discriminant embedding
[J]. J4, 2011, 45(10): 1842-1847.
[12] SHU Zhen-yu, WANG Guo-zhao. Fast mesh segmentation algorithm based on tensor voting[J]. J4, 2011, 45(6): 999-1005.
[13] SHE Jing-Shan, MENG Meng, LUO Zhi-Ceng, MA Yu-Liang. Electromyography movement recognition of lower limb based on multiple kernel learning[J]. J4, 2010, 44(7): 1292-1297.
[14] XUE Ling-Yun, DUAN Hui-Long, XIANG Hua-Qi, FAN Ying-Le. Image restoration based on stochastic resonance mechanism of FitzHugh-Nagumo neuron[J]. J4, 2010, 44(6): 1103-1107.
[15] ZHANG Yuan-Hui, HUI Wei, YU Dan. Kalman tracking algorithm based on realtime vision of pingpong robot[J]. J4, 2009, 43(09): 1580-1584.