Authentication of Individuals using Hand Geometry Biometrics: A Neural Network Approach

Abstract

Biometric based systems for individual authentication are increasingly becoming indispensable for protecting life and property. They provide ways for uniquely and reliably authenticating people, and are difficult to counterfeit. Biometric based authenticity systems are currently used in governmental, commercial and public sectors. However, these systems can be expensive to put in place and often impose physical constraint to the users. This paper introduces an inexpensive, powerful and easy to use hand geometry based biometric person authentication system using neural networks. The proposed approach followed to construct this system consists of an acquisition device, a pre-processing stage, and a neural network based classifier. One of the novelties of this work comprises on the introduction of hand geometry's related, position independent, feature extraction and identification which can be useful in problems related to image processing and pattern recognition. Another novelty of this research comprises on the use of error correction codes to enhance the level of performance of the neural network model. A dataset made of scanned images of the right hand of fifty different people was created for this study. Identification rates and Detection Cost Function (DCF) values obtained with the system were evaluated. Several strategies for coding the outputs of the neural networks were studied. Experimental results show that, when using Error Correction Output Codes (ECOC), up to 100% identification rates and 0% DCF can M. Faundez-Zanuy 123 202 M. Faundez-Zanuy et al.be obtained. For comparison purposes, results are also given for the Support Vector Machine method.

Projected texture for hand geometry based authentication

“…Jain et al [6] outlined the challenges in such an authentication system and proposes a simple set of hand measurements, inspired by the previous work. Even the most recent hand geometry algorithms [4] use extentions of the set of features outlined in [6]. The research in 2D hand geometry based authentication has progressed primarily in three different directions:…”

“…[4] to improve the verification accuracy. Even though the results showed improvements on the prior art, the comparisons are limited.…”

“…Fingerprints [11] and Palm prints [7,12] are ideal candidates for this due to their ease of acquisition along with the hand geometry. A third set of algorithms look at generic techniques to improve the classification process used for verification, such as feature discretization [8], use of error correcting codes and more powerful classifiers [4], etc.…”

Projected Texture for Object Classification

“…We compare the performance of three different feature sets in this experiment: i) Feat-1: A set of 17 features based of finger lengths, widths and heights, proposed by Jain et al [11], ii) Feat-2: A set of 10 features computed from palm contours proposed by Faundez et al [12], and iii) Feat-3: The proposed projected texture based features. Figure 8(a) shows the difference in deformation of the projected pattern based on the 3D shape of the palm.…”

“…We demonstrate the flexibility of our approach with a second application in hand geometry based person authentication, where one is required to capture minor variations between similar samples (hands) belonging to different people. The performance is compared with popular image based features [11,12].…”