期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：8
页码：471-479
出版社：Science and Information Society (SAI)
摘要：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 250C to 00C. The experimental result shows
40% improvement in the recognition rate after applying auto
correction algorithm.
