International Journal of Scientific & Technology Research Volume 1, Issue 2, March 2012 ISSN 2277-8616 1 IJSTR'2012 www.ijstr.org A DCT-based Local Feature Extraction Algorithm for Palm-print Recognition Hafiz Imtiaz , Shaikh Anowarul Fattah Abstract-- In this paper, a spectral feature extraction algorithm is proposed for palm-print recognition, which can efficiently capture the detail spatial variations in a palm-print image. The entire image is segmented into several spatial modules and the task of feature extraction is carried out using two dimensional discrete cosine transform (2D-DCT) within those spatial modules. A dominant spectral feature selection algorithm is proposed, which offers an advantage of very low feature dimension and results in a very high within-class compactness and between-class separability of the extracted features. A principal component analysis is performed to further reduce the feature dimension. 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 Terms--Feature extraction; classification; discrete cosine transform; dominant spectral feature; palm-print recognition; modularization  1 INTRODUCTION Conventional ID card and password based identification methods, although very popular, are no more reliable as before because of the use of several advanced techniques of forgery and password-hacking. As an alternative, biometrics, such as palm-print, finger-print, face and iris being used for authentication and criminal identification [7]. The main advantage of biometrics is that these are not prone to theft and loss, and do not rely on the memory of their users. Moreover, they do not change significantly over time and it is difficult for a person to alter own physiological biometric or imitate that of another person's. Among different biometrics, in security applications with a scope of collecting digital identity, the palm-prints are recently getting more attention among researchers [3], [9]. Palm-print recognition is a complicated visual task even for humans. The primary difficulty arises from the fact that different palm-print images of a particular person may vary largely, while those of different persons may not necessarily vary significantly. Moreover, some aspects of palm-prints, such as variations in illumination, position, and scale, make the recognition task more complicated [6]. Palm-print recognition methods are based on extracting unique major and minor line structures that remain stable throughout the lifetime. In this regard, generally, either line-based or texture-based feature extraction algorithms are employed [13]. In the line- based schemes, generally, different edge detection methods are used to extract palm lines (principal lines, wrinkles, ridges, etc.) [12], [10]. The extracted edges, either directly or being represented in other formats, are used for template matching. In cases where more than one person possesses similar principal lines, line based algorithms may result in ambiguous identification. In order to overcome this limitation, the texture-based feature extraction schemes can be used, where the variations existing in either the different blocks of images or the features extracted from those blocks are computed [1], [2], [14]. In this regard, generally, principal component analysis (PCA) or linear discriminant analysis (LDA) is employed directly on the palm-print image data or some popular transforms, such as Fourier and discrete cosine transforms (DCT), are used for extracting features from the image data. Given the extracted features, various classifiers, such as decision-based neural networks and Euclidean distance based classifier, are employed for palm-print recognition [12], [10]. Despite many relatively successful attempts to implement face or palm-print recognition system, a single approach, which combines accuracy, robustness, and low computational burden, is yet to be developed. In this paper, the main objective is to extract precisely spatial variations from each segment of the entire palm-print image instead of considering a global variation pattern. An efficient feature extraction scheme using 2D-DCT is developed, which operates within those spatial modules to obtain dominant spectral features. It is shown that the discriminating capabilities of the proposed features, that are extracted from the sub-images, are enhanced because of modularization of the palm-print image. Moreover, the improvement of the quality of the extracted features as a result of illumination adjustment has also been analyzed. Apart from considering only the dominant spectral features, further reduction of the feature dimension is obtained by employing the PCA. Finally, recognition task is carried out using a distance based classifier. ________________________________  Hafiz Imtiazis currently an Assistant Professor with the Dept. of EEE, Bangladesh University of Engineering and Technology, Dhaka-1000, Bangladesh. PH-+8801677103153. E-mail: hafizimtiaz@eee.buet.ac.bd  Shaikh Anowarul Fattah, Ph.D. is currently an Associate Professor with the Dept. of EEE, Bangladesh University of Engineering and Technology, Dhaka-1000, Bangladesh. E- mail: fattah@eee.buet.ac.bd