Hybrid robust iris recognition approach using iris image pre-processing, two-dimensional gabor features and multi-layer perceptron neural network/PSO

ABSTRACT:

Computational knowledge is utilized to take care of truthful and entangled worldwide issues, however neural systems (NNs) and developmental figuring have likewise influenced these issues. Biometric attributes are relevant for identifying wrongdoing in security frameworks since they offer appealing highlights, for example, dependability and uniqueness. Albeit different techniques have been proposed for this target, highlight deficiencies, for example, computational many-sided quality, long run occasions, and high memory utilization remain. The present investigation proposes a novel human iris acknowledgment approach in light of a multi-layer perceptron NN and molecule swarm enhancement (PSO) calculations to prepare the system with a specific end goal to expand speculation execution.

A blend of these calculations was utilized as a classifier. A pre-handling step was performed on the iris pictures to enhance the outcomes and two-dimensional gabor piece highlight extraction was connected. The information was standardized, prepared, and tried utilizing the proposed technique. A PSO calculation was connected to prepare the NN for information arrangement. The exploratory outcomes demonstrate that the proposed strategy performs superior to anything numerous other surely understood methods. The benchmark Chinese Academy of Science and Institute of Automation (CASIA)- iris V3 and Center for Machine Learning and Intelligent Systems at the University of California, Irvine (UCI) machine learning store datasets were utilized for testing and correlation.

LEAVE A REPLY

Please enter your comment!
Please enter your name here