Human Identification using Selected Features from Finger Geometric Profiles

TL;DR

This paper presents a finger biometric identification system using geometric features extracted from finger profiles, achieving high accuracy in unconstrained environments with optimized feature selection and classification methods.

Contribution

It introduces a novel hand image normalization technique and feature selection process that improve finger-based biometric identification accuracy.

Findings

Achieved 96.56% accuracy with RF classifier on right-hand images.

Selected 9 and 12 features per finger for improved classification.

Obtained an equal error rate of 0.078 for both hand types.

Abstract

A finger biometric system at an unconstrained environment is presented in this paper. A technique for hand image normalization is implemented at the preprocessing stage that decomposes the main hand contour into finger-level shape representation. This normalization technique follows subtraction of transformed binary image from binary hand contour image to generate the left side of finger profiles (LSFP). Then, XOR is applied to LSFP image and hand contour image to produce the right side of finger profiles (RSFP). During feature extraction, initially, thirty geometric features are computed from every normalized finger. The rank-based forward-backward greedy algorithm is followed to select relevant features and to enhance classification accuracy. Two different subsets of features containing nine and twelve discriminative features per finger are selected for two separate experimentations those use the kNN and the Random Forest (RF) for classification on the Bosphorus hand database. The experiments with the selected features of four fingers except the thumb have obtained improved performances compared to features extracted from five fingers and also other existing methods evaluated on the Bosphorus database. The best identification accuracies of 96.56% and 95.92% using the RF classifier have been achieved for the right- and left-hand images of 638 sub-jects, respectively. An equal error rate of 0.078 is obtained for both types of the hand images.