A Novel Pre-processing Technique for DCTdomain Palm-print Recognition

Abstractó In this paper, a novel pre-processing algorithm is introduced to identify the principal lines from a palm-print image and a discrete cosine transform (DCT) domain feature extraction algorithm is then employed for palm-print recognition, which can efficiently capture the spatial variations in the principal lines of a palm-print image. The entire image is segmented into several small spatial modules. The task of feature extraction is carried out in local zones using two dimensional discrete cosine transform (2D-DCT). The proposed dominant DCT-domain feature selection algorithm offers an advantage of very low feature dimension and it is capable of capturing precisely the detail variations within the palmprint image. It is shown that because of the pre-processing step, the discriminating capabilities of the proposed features are enhanced, which results in a very high within-class compactness and between-class separability of the extracted features. From our extensive experimentations on different palm-print databases, it is found that the performance of the proposed method in terms of recognition accuracy and computational complexity is superior to that of some of the recent methods. Index Termsó Spectral feature extraction, binary palm image, two-dimensional discrete cosine transform, classification, palm- print recognition, entropy, modularization. CONVENTIONAL ID card and password based identification methods, although very popular, are no more reliable as before because of the use of several advance