TITLE:
Optimized Features Extraction of IRIS Recognition by Using MADLA to Ensure Secure Authentication
AUTHORS:
S. Pravinthraja, K. Umamaheswari
KEYWORDS:
GLCM, Deep Learning, Strong Features Extraction, MADMM, Iris Recognition
JOURNAL NAME:
Circuits and Systems,
Vol.7 No.8,
June
27,
2016
ABSTRACT: Nowadays, Iris recognition is a method of biometric
verification of the person authentication process based on the human iris
unique pattern, which is applied to control system for high level security. It
is a popular system for recognizing humans and essential to understand it. The
objective of this method is to assign a unique subject for each iris image for
authentication of the person and provide an effective feature representation of
the iris recognition with the image analysis. This paper proposed a new optimization
and recognition process of iris features selection by using proposed Modified
ADMM and Deep Learning Algorithm (MADLA). For improving the performance of the
security with feature extraction, the proposed algorithm is designed and used
to extract the strong features identification of iris of the person with less
time, better accuracy, improving performance in access control and in security
level. The evaluations of iris data are demonstrated the improvement of the
recognition accuracy. In this proposed methodology, the recognition of the iris
features has been improved and it incorporates into the iris recognition
systems.