DMCA
A Novel Pre-processing Technique for DCTdomain Palm-print Recognition
| Citations: | 2 - 0 self |
BibTeX
@MISC{Imtiaz_anovel,
author = {Hafiz Imtiaz and Shubhra Aich and Shaikh Anowarul Fattah},
title = {A Novel Pre-processing Technique for DCTdomain Palm-print Recognition},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
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 advanced
Keyphrases
novel pre-processing technique dctdomain palm-print recognition palm-print image principal line dominant dct-domain feature selection algorithm local zone discrete cosine transform identification method index term spectral feature extraction spatial variation conventional id card pre-processing step entire image novel pre-processing algorithm binary palm image between-class separability computational complexity low feature dimension several small spatial module palmprint image several advanced palm print recognition recent method dimensional discrete cosine transform different palm-print database recognition accuracy extracted feature two-dimensional discrete cosine transform feature extraction algorithm feature extraction palm-print recognition extensive experimentation detail variation high within-class compactness
