Face recognition based on NSA multiscale model
-
1.
Institute of Image & Graphic, Department of Computer Science, Sichuan University, Chengdu 610064, China;
-
2.
Southwest Petroleum Institute, Chengdu 610500, China
-
Corresponding author:
YOU Zhi-sheng, zsyou@mail.sc.cninfo.net
;
-
Received Date:
2004-08-02
Accepted Date:
2004-10-12
-
Abstract
A multiscale mode named neural networks scale autoregressive(NSA) is presented.The model uses neural networks to represent the map between the pixels residing at images of various resolutions;in stead of the assumption of linearity in linear scale autoregressive(LSA) model.Then back-propagation algorithm is used in the neural networks training to decide the map,finally,the identified map is used to estimate images at finer resolution from coarser versions.Similarity in contrast is used to gauge the degree of similarity between estimated images and target images.The model is applied in face recognition and image segmentation approach using gradient operator is proposed to increase the recognition accuracy.Experimental results show that similarity between image estimated by NSA model and target image is 95.3634%.The NSA-based face recognition system is robust to illumination.
-
-
References
[1]
|
MARAGOS P.Pattern spectrum and multiscale shape representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):701~716. |
[2]
|
MALLAT S.A wavelet tour of signal processing[M].2nd ed,Beijing:China Machine Press,2002.230~238(in Chinese). |
[3]
|
BURRUS C S,GOPINATH R A,GUO H T.Introduction to wavelets and wavelet transforms[M].New Jersey:Prentice Hall,1998.159~164. |
[4]
|
BANHAM M R,KATSAGGELOS A K.Spatially adaptive wavelet-based multiscale image restoration[J].IEEE Transactions on Image Processing,1996,5(4):619~634. |
[5]
|
DAOUDI K,FRAKT A B,WILLSKY A S.Multiscale autoregressive models and wavelets[J].IEEE Transactions of Information Theory,1999,45(3):828~845. |
[6]
|
BOUMAN C,LIU B.Multiple resolution segmentation of textured images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(2):99~113. |
-
-
Proportional views
-