Palmprint Recognition Based on Subspace Analysis of Gabor Filter Bank

Palmprint Recognition Based on Subspace Analysis of Gabor Filter Bank

Moussadek Laadjel (Algerian National Centre for Research and Development, Algeria), Ahmed Bouridane (Northumbria University, UK), Fatih Kurugollu (Queen’s University Belfast, UK) and WeiQi Yan (Queen’s University Belfast, UK)
Copyright: © 2012 |Pages: 13
DOI: 10.4018/978-1-4666-1758-2.ch014

Abstract

This paper introduces a new technique for palmprint recognition based on Fisher Linear Discriminant Analysis (FLDA) and Gabor filter bank. This method involves convolving a palmprint image with a bank of Gabor filters at different scales and rotations for robust palmprint features extraction. Once these features are extracted, FLDA is applied for dimensionality reduction and class separability. Since the palmprint features are derived from the principal lines, wrinkles and texture along the palm area. One should carefully consider this fact when selecting the appropriate palm region for the feature extraction process in order to enhance recognition accuracy. To address this problem, an improved region of interest (ROI) extraction algorithm is introduced. This algorithm allows for an efficient extraction of the whole palm area by ignoring all the undesirable parts, such as the fingers and background. Experiments have shown that the proposed method yields attractive performances as evidenced by an Equal Error Rate (EER) of 0.03%.
Chapter Preview
Top

2 Region Of Interest Extraction

The first step of a palmprint recognition process is usually related to the localization and segmentation of the palmprint ROI. A ROI should include the most significant and discriminative patterns which are extracted from complete principal lines, wrinkles and texture. Although, many techniques for segmenting palmprint ROI have been proposed (Han, Chengb, Linb, & Fanb, 2003; Zhang, Kong, You, & Wong, 2003; Kumar, Wang, Shen, & Jain, 2003), the technique proposed by Zhang, Kong, You, and Wong (2003) is the most widely discussed in the literature. Typically, this method operates on a fixed square region inside the palm. However, this region is not proportional to the palm size and is thus unsuitable to extract all necessary palmprint information from complete lines and wrinkles. To address this problem, an improved ROI extraction technique is proposed in this paper and which can be described as follows:

Purchase this chapter to continue reading all 13 pages >

Complete Chapter List

Search this Book:
Reset