基于小波特征的非線性鑒別特征抽取技術(shù)
Wavelet Feature-Based Nonlinear Feature Extraction Technique
-
摘要: 該文提出了一種基于小波特征的非線性鑒別特征抽取方法,即在進(jìn)行非線性映射之前,首先利用小波變換對原始輸入圖像進(jìn)行預(yù)處理,獲取低頻平滑、水平細(xì)節(jié)和垂直細(xì)節(jié)等3個子圖的小波特征,然后在頻域上,對它們分別進(jìn)行核Fisher鑒別分析。對最終獲得的3組鑒別特征設(shè)計了一種特征融合的方法。在ORL標(biāo)準(zhǔn)人臉庫上的試驗結(jié)果表明所提方法不僅在識別性能上優(yōu)于現(xiàn)有的核Fisher鑒別分析方法,而且,在ORL人臉庫上的特征抽取速度提高了近13倍。
-
關(guān)鍵詞:
- 人臉識別; 核Fisher鑒別分析; 小波變換; 特征抽取
Abstract: The paper developes a novel nonlinear feature extraction method based on wavelet features. Its main idea is that wavelet transform is first employed to preprocess the original training images before the nonlinear mapping and three groups of wavelet features: lowest frequency subimage, horizontal detail and vertical detail, are derived respectively, What follows, Kernel Fisher Discriminant Analysis(KFDA) is performed on three classes of wavelet features. Three final discriminant feature vectors are obtained, from which a feature fusing method is developed. Finally, The experimental results on ORL face databases indicate that the proposed method is more effective than the current KFDA. And, more importantly, its consumed time in feature extraction is only one thirteenth of that of KFDA. Moreover, the experiments also demonstrate that this method is robust in uncontrolled lighting condition. -
高西奇,周洪祥,何振亞.基于小波變換的主元分析人臉圖像識別.東南大學(xué)學(xué)報,1996,26(2):137-141.[2]Sergent J. Microfenesis of face perception. in: H.D.EIIis. Aspects of Face Processing, Nijhoff, Dordrecht, 1986:80 - 104.[3]Liu C J, Wechsler Harry. A shape- and texture-based enhanced Fisher classifier for face recognition[J].IEEE Trans. on Image Processing.2001, 10(4):598-[4]Scholkopf Bernhard, Smola Alexander, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem[J].Neural Computation.1998, 10:1299-[5]Mika Sebastian, Ratsch Gunnar, Weston Jason, Scholkopf Bernhard, et al.. Fisher diseriminant analysis with kernels. In IEEE workshop on Networks for Signal Processing, 1999:41-48.[6]Baudat G, Anouar F. Generalized discriminant analysis using a kernel approach[J].Neural Computation.2000, 12( 10):2385-[7]Roth Volker, Steinhage Volker. Nonlinear discriminant analysis using kernel functions. In Proc. of Neural Information Processing systems, Denver, Nov. 1999:568 - 574.[8]Yang M H. Kernel eigenfaces vs. kernel fisherfaces: face recognition using kernel methods, Proc. of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition(RGR02), Washington DC, May 2002:215 - 220.[9]Vapnik V. The Nature of Statistical Learning Theory. New York:Springer-Verlag, 1995:302 - 309.[10]程云鵬.矩陣論.西安:西北工業(yè)大學(xué)出版社,1999:294-302. -
計量
- 文章訪問數(shù): 2219
- HTML全文瀏覽量: 89
- PDF下載量: 697
- 被引次數(shù): 0
下載:
