Deep Learning Based Iris Recognition for Voting System

EasyChair Preprint 3081

Abstract

In this paper, we are scanning an individual's iris and storing it in a voter's database by giving appropriate AADHAR card no. If an individual wants to cast a ballot, at that point their iris is distinguished and this recognized picture is contrasted with the picture in a voter's database..When the iris is recognized we get the information about the voter in our PC, then the person is allowed to vote. The current voting system is not secure, some individuals give dummy votes or they are registered at more than one place and some traditional model-based iris recognition gives high false detection rate and low processing speed. In this paper, the security of the voter is discussed and in general and the focus is on making the voting system more robust and reliable by eliminating dummy voters. This paper researches another profound learning-based methodology for iris acknowledgment and endeavors to improve the precision utilizing an increasingly streamlined system to all the more precisely recuperate the delegate highlights. We consider the AlexNet Convolutional Neural Network transfer learning model for iris images features extraction and recognition, which not only results in a simplified network but also results in outflanking coordinating exactness more than a few traditional and best in class calculations for iris acknowledgment.

Keyphrases: AlexNet CNN, Iris recognition, deep learning, image processing

@booklet{EasyChair:3081,
  author    = {Venkata Ganga Sunil Nagalla and Venkata Dhanush Vepuri and N Praveen},
  title     = {Deep Learning Based Iris Recognition for Voting System},
  howpublished = {EasyChair Preprint 3081},
  year      = {EasyChair, 2020}}