Thermal hand image segmentation for biometric recognition

TL;DR

This paper introduces a method for biometric recognition using thermal and visible hand images, demonstrating that thermal images are as effective as visible ones and combining both yields higher accuracy.

Contribution

The work presents a new database and a combined thermal-visible imaging approach for hand biometrics, improving identification accuracy and addressing thermal image challenges.

Findings

Thermal hand images are as effective as visible images for recognition.

Combining thermal and visible images improves identification accuracy.

Maximum identification rate achieved is 98.3% with 104 subjects.

Abstract

In this paper we present a method to identify people by means of thermal (TH) and visible (VIS) hand images acquired simultaneously with a TESTO 882-3 camera. In addition, we also present a new database specially acquired for this work. The real challenge when dealing with TH images is the cold finger areas, which can be confused with the acquisition surface. This problem is solved by taking advantage of the VIS information. We have performed different tests to show how TH and VIS images work in identification problems. Experimental results reveal that TH hand image is as suitable for biometric recognition systems as VIS hand images, and better results are obtained when combining this information. A Biometric Dispersion Matcher has been used as a feature vector dimensionality reduction technique as well as a classification task. Its selection criteria helps to reduce the length of the vectors used to perform identification up to a hundred measurements. Identification rates reach a maximum value of 98.3% under these conditions, when using a database of 104 people.