|
Abstract: According to the low chromatic difference and poor image quality characteristics of the pressed protuberant characters, the Eigenfaces method for the overall feature extraction and recognition is adopted. However, without considering the between-class variance, the Eigenfaces method can’t achieve ideal classifying results. A novel method based on the reconstruction errors for the character recognition is proposed. Firstly, a subspace is established for every class. Then, images of the test samples are reconstructed under every subspace. Finally, the recognition experiment is carried out according to the root mean square error between the original image and the reconstruction image. The proposed method makes full use of the features of the within-class and the variance of the between-class. The experiment results show that the method not only remarkably improves the recognition rate but also meets the real-time requirement.
Key words: Eigenfaces Subspace Reconstruction error Protuberant characters
CLC No:
TP274−3
教育部博士点基金资助项目(20060422011).
Received
20070627,
received
in
revised
form
20080123
|
| References
[1]
LU Changhou, CAO Jianhai, LI Xueyong, et al. Product quality on-line
testing for the pressed protuberant character on a metal tag[J]. Chinese
Journal of Mechanical Engineering, 2005, 41(2): 87-91.
[2]
QUAN Wei, ZHENG Nanning. Beer bottle raised character extraction and
recognition method based on active contour model [J]. Information and
Control, 2003, 32(4): 358-362.
[3]
LI Xin, XIA Dingyuan. The technique of real time dynamical images
capture in on-line recognition system[J]. Optical Communication
Technology, 2004(4): 62-64.
[4]
CAO Jianhai, LU Changhou. Locating a center-point of the circular
projection based on a gray-scale image and vector sum [J]. Journal of
Optoelectronics, Laser, 2004, 15(6): 714-718.
[5]
CAO Jianhai, LU Changhou. New method of feature extraction using wavelet
transform and DCT in OCR[J]. Journal of Optoelectronics、Laser, 2004,
15: 477-482.
[6]
ZHANG Chunyu, CHEN Mianshu, CHEN Hexin. A convey of front face
recognition[J]. Computer Engineering and Applications, 2002,
40(2): 62-65.
[7] TURK M, PENLAND A. Eigenfaces for recognition[J]. Journal of
Cognitive Neuroscience, 1991, 3(1): 71-86.
[8] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs.
fisherfaces: recognition using class specific linear projection[J]. IEEE
Transactions on Pattern Analysis and Machine Intelligence, 1997,
19(7): 711-720.
[9] YU Hua, YANG Jie. A direct LDA algorithm for high dimensional data
with application to face recognition[J]. Pattern Recognition, 2001,
34(10): 2 067-2 070.
[10] SHAN Shiguang, GAO Wen, CHEN Xilin, et al. Novel face recognition
based on individual eigensubspaces[C]// Proceedings of International
Conference on Signal Proce- ssing, Beijing, 2000, 3: 1 522-1 525.
[11] WANG Liwei, WANG Xiao, FENG Jufu. Subspace distance analysis with
application to adaptive Bayesian face recognition[J]. Pattern
Recognition, 2006, 39(3): 456-464.
[12] SUN Xichen, WANG Liwei, FENG Jufu. Further results on the subspace
distance[J]. Pattern Recognition, 2007, 40(1): 328-329. |