New Pattern Recognition Method Based on Wavelet De-Noising and Kernel Principal Component Analysis
The background noise influences the face image recognition greatly. It is crucial to remove the noise signals prior to the face image recognition processing. For this purpose, the wavelet de-noising technology has combined with the kernel principal component analysis (KPCA) to identify face images in this paper. The wavelet de-noising technology was firstly used to remove the noise signals. Then the KPCA was employed to extract useful principal components for the face image recognition. By doing so, the dimensionality of the feature space can be reduced effectively and hence the performance of the face image recognition can be enhanced. Lastly, a support vector machine (SVM) classifier was used to recognize the face images. Experimental tests have been conducted to validate and evaluate the proposed method for the face image recognition. The analysis results have showed high performance of the newly proposed method for face image identification.
J. J. Zhang and L. J. Liang, "New Pattern Recognition Method Based on Wavelet De-Noising and Kernel Principal Component Analysis", Applied Mechanics and Materials, Vol. 235, pp. 74-78, 2012