Council for Innovative Research International Journal of Computers & Technology www.cirworld.com Volume 4 No. 2, March-April, 2013, ISSN 2277-3061 613 | Page wwwijctonline.com Segmentation of Palmprint into Region of Interest (ROI): A Survey Sneha M. Ramteke1, Prof. S. S. Hatkar2 1Student of M.TECH.,Department of CSE, SGGSIE&T, Nanded. sneharamteke87@gmail.com 2Associate Professor, Department of CSE,SGGSIE&T, Nanded. shubhanand.hatkar@yahoo.com Abstract:Palmprint is one of the most reliable physiological characteristics that can be used to distinguish between individuals. Palmprint recognition process consists of image acquisition, pre-processing, feature extraction, matching and result. One of the most important stages in these methods is pre-processing which contains some operations such as filtering, Region Of Interest (ROI) extraction, normalization. This paper provides a survey on various different methods to segmentation of palmprint into ROI and extraction of principle lines. ROI segmentation of palmprint is to automatically and reliably segment a small region from the captured palmprintimage.We pay more attention towards more essential stage of palm localization, segmentation and ROI extraction. Finally some conclusion and suggestion is offered. Keywords:Biometrics, Palmprint, ROI, Region based segmentation, Image pre-processing, principle line extraction. 1. INTRODUCTION Palmprint is one of the most reliable features in personal identification because of its stability and uniqueness [1] [2]. The inner surface of the palm normally contains three flexion creases, secondary creases and ridges. The flexion creases are also called principal lines and secondary creases are called wrinkles. Many feature of a palmprint can be used to uniquely identify a person. Six major types of features can be observed on a palm (figure 1). Palmprint recognition consists of images acquisition in which image is capture with the help of device. Preprocessing is to setup a coordinate system to align palmprint images and to segment a part of palmprint image for palmprint feature extraction. One key feature in palmprint identification is deciding how the image is to be taken for identification purposes. The images taken generally involve the entire hand of the subject. The problem with using the entire hand is that the area of the hand except for the palm can also be included in the identification process. In some cases, this may lead to obfuscation of the image and thus, may lead to faulty identification. One way to resolve this issue is by cropping the entire image to give that area of the image which contains the palm itself. This area is termed the ROI. The main problem in palmprint recognition system is how to extract the ROI and the features of palmprint. Most of the preprocessing algorithms segment square regions for feature extraction but some of them segment circular and half elliptical regions. The square region is easier for handling translation variation, while the circular and half elliptical regions may be easier for handling rotation variation. This paper focuses on problem based on the pre- processing section which is important in providing high accuracy in pattern recognition. Many papers which have discussed about preprocessing and feature extraction, So we discuss and give more attention to an individual part of an preprocessing because until we can’t get a proper ROI region, we will unable to get high accuracy further. Fig.1 Different Features of Palm. The remaining section is organized as follows: Section 2 gives the details about the acquisition of palm images. Section 3 describes survey of various methods of segmentation of ROI which are used previously. Finally section 5 gives the discussion and conclusions. 2. PALMPRINT ACQUISITION During image acquisition a palmprint image is captured by a palmprint scanner or camera and store in grayscale file. Then the AC signal is converted into a digital signal, which is transmitted to a computer for further processing. It is the first process in palmprint recognition systems. Researchers utilize four different types of sensors to collect palmprint images, CCD-based palmprint scanners, digital cameras, digital scanners and video cameras. A CCD-based palmprint scanner developed by the Hong Kong Polytechnic University.