Novel Adaptive Auto-Correction Technique for Enhanced Fingerprint Recognition

Abstract

Fingerprints are the most used biometric trait in applications where high level of security is required. Fingerprint image may vary due to various environmental conditions like temperature, humidity, weather etc. Hence, it is necessary to design a fingerprint recognition system that is robust against temperature variations. Existing techniques such as automated and non-automated techniques are not real time analysis (adaptive). In this paper, we propose an adaptive auto correction technique called Reference Auto-correction Algorithm. This proposed algorithm corrects user reference fingerprint template automatically based on captured fingerprint template and the matching score obtained on daily basis to improve the recognition rate. Analysis is carried out on 250 fingerprint templates stored in the database of 10-users captured at varying temperature from 25 0 C to 0 0 C. The experimental result shows 40% improvement in the recognition rate after applying auto correction algorithm.

A Comprehensive Review of Unimodal and Multimodal Fingerprint Biometric Authentication Systems: Fusion, Attacks, and Template Protection

“…A total of 250 fingerprint templates from 10 individuals were gathered at 25°C to 0°C for analysis. The trial results showed that applying the auto-correcting technique increased the rate of identification by 40% (161).…”