ISSN: 2319-8753 International Journal of Innovative Research in Science, Engineering and Technology Vol. 2, Issue 4, April 2013 Copyright to IJIRSET www.ijirset.com 1006 Palmprint Recognition System Jaspreet Kour 1 , Shreyash Vashishtha 2 , Nikhil Mishra 3 , Gaurav Dwivedi 4 , Prateek Arora 5 Associate Professor, Dept. of Electronics & Instrumentation Engineering, Galgotias College of Engineering and Technology, Greater Noida, India 1 B.Tech. Student, Dept. of Electronics & Instrumentation Engineering, Galgotias College of Engineering and Technology, Greater Noida, India 2,3,4,5 Abstract: Palmprint recognition being one of the important aspects of biometric technology is one of the most reliable and successful identification methods. In this paper, several existing palmprint recognition algorithms have been studied and analyzed. A simple approach to preprocessing and roi extraction has been discussed. The available databases have also been analyzed and the most efficient of all will be used for the development of the proposed system. Keywords: Palmprint, Biometrics, CASIA, PolyU, IITD, Preprocessing, Feature extraction, matching. I. INTRODUCTION Palmprint recognition is one of the biometrics available at the present. Biometric systems are used to authenticate the identity by measuring the physiological and/or behavioral characteristics. So, the two main categories of biometrics are ‘physiological’ and/or ‘behavioral’. The physiological category includes the physical human traits such as palmprint, hand shape, eyes, veins, etc. The behavioral category includes the movement of the human, such as hand gesture, speaking style, signature etc. The measurement of these traits helps in authentication using the biometric systems. One of the most successful biometric systems is the palmprint recognition system. This system recognizes on the basis of the palm print of a person. It is reliable due to the fact that the print patterns are always unique, even in the monozygotic twins. The interesting part is that the ridge structure is permanent. This ridge structure is formed at about the thirteenth week of the embryonic development. This formation gets completed by the eighteenth week. The palmprint recognition system has advantages over the other physiological biometric systems. Some of the advantages are fixed line structure, low intrusiveness, low cost capturing device, low resolution imaging. Thus palmprint recognition is a very interesting research area. A lot of work has already been done in this area, but there is still a lot of scope to make the systems more efficient. Here, we have tried to analyze the already existing systems and thereby propose a new approach. II. LITERATURE REVIEW In order to provide an accurate and efficient authentication system, there has been substantial research in the area of palmprint recognition system. For this, a number of relevant papers have been reviewed. Tee Connie et al’ have proposed an automated palmprint recognition system [1] . In its proposed approach, they have used Principal Component Analysis (PCA), Fischer Discriminant Analysis (FDA) and Independent Component Analysis (ICA) for the feature extraction from the roi images. Patprara Tunkpien used the approach of compact extraction of principle lines from the palmprint images by using filtering operations consecutively [2] . Here, the image is first smoothed and then worked upon. For this, the palmprint images are passed through several filters. Palmprint recognition with PCA and ICA [3] have been presented by Tee Connie et al. K.Y. Rajput et al used the Kekre Fast Codebook Generation [4] algorithm for the feature extraction. I Ketut Gede Darma Putr and Erdiawan have used the two dimensional Gabor [5, 7] for the development of a high performance palmprint identification. Sina Akbari Mistani et al proposed an approach which makes use of the multispectral analysis [6] of the hybrid features to improve the performance of the palmprint recognition system. David Zhang et al have proposed an online palmprint identification system [8] . This system was developed to make authentication possible in the real time also. Hafiz Imtiaz et all have proposed a novel preprocessing technique for DCT domain palmprint recognition [9] in which the task of feature extraction is carried out in local zones using 2 dimensional Discrete Cosine Transform (2D-DCT). A survey of all the palmprint recognition systems [10, 11] has also been studied. An automated palmprint recognition system [1] evaluated the results in terms of correct recognition rate and verification rate. Correct recognition rate is the percentage of people that can be identified by the system. Verification rate can be calculated by using False Acceptance Rate (FAR), False Rejection Rate (FRR), as well as Equal Error Rate (EER). FAR is the percentage of accepted not genuine claims over the total number of not genuine accesses. FRR is the percentage of rejected genuine claims over the total number of genuine accesses. ERR is the system threshold value when FAR is equal to FRR. For a biometric to work effectively, FAR and FRR must be as low as possible. Total Success Rate (TSR) is the verification rate of the system. Principal Component Analysis (PCA) [3] is used for dimensionality reduction. It is useful as it decreases the dimension of the images and scales the dimensions according to their importance. It makes use of