Face recognition under varying illumination using Mahalanobis self-organizing map

被引：8

作者：

Aly S. ^{[1
]}

Tsuruta N. ^{[2
]}

Taniguchi R.-I. ^{[1
]}

机构：

[1] Department of Intelligent Systems, Graduate School of Information science and electrical Engineering, Kyushu University, Nishi-ku, Fukuoka 819-039

[2] Department of Electronics Engineering and Computer Science, Fukuoka University, Fukuoka

来源：

Artificial Life and Robotics | 2008年 / 13卷 / 1期

关键词：

Face recognition; Illumination variation; Mahalanobis distance; Self-organizing map;

D O I：

10.1007/s10015-008-0555-z

中图分类号：

学科分类号：

摘要：

We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases. © International Symposium on Artificial Life and Robotics (ISAROB). 2008.

引用

页码：298 / 301

页数：3

共 13 条

[1]

Zhao W., Chellappa R., Phillips P., Et al., Face recognition: A literature survey, Am Computing Surveys, 35, 4, pp. 399-459, (2003)

[2]

Li S., Jain A., Handbook of Face Recognition, (2005)

[3]

Du B., Shan S., Qing L., Et al., Empirical comparisons of several preprocessing methods for illumination insensitive face recognition, Proceedings of IEEE International Conference on Acoustic, Speech, and Signal Processing, 2, pp. 981-984, (2005)

[4]

Chen W., Er M., Wu S., Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain, IEEE Trans On Systems, Man, and Cypernetics-part B: Cypernetics, 36, 2, pp. 458-466, (2006)

[5]

Aly S., Sagheer A., Tsuruta N., Et al., Face recognition across illumination, Artif Life Robotics, 12, pp. 33-37, (2008)

[6]

Belhumeur P., Hespanha J., Kriegman D., Eigenfaces vs. fisherfaces: Recognition using class specific linear projection, IEEE Trans PAMI, 19, pp. 711-720, (1997)

[7]

Georghiades A., Kriegman D., Belhumeur P., From few to many: generative models for recognition under variable pose and illumination, IEEE Trans PAMI, 40, pp. 643-660, (2001)

[8]

Kohonen T., Self-Organizing Maps, (1997)

[9]

Lawarance S., Giles C., Tsoi A., Et al., Face recognition: A convolutional neural network approach, IEEE Trans NN, 8, 1, pp. 98-113, (1997)

[10]

Tan X., Liu J., Chen S., Et al., Recognizing partially ocluded, expresion variant faces from single training image per person with som and soft k-nn ensemble, IEEE Trans NN, 16, 4, pp. 875-886, (2005)

← 1 2 →