An Efficient and Automatic Iris Recognition System Using ICM Neural Network

An Efficient and Automatic Iris Recognition System Using ICM Neural Network

Guangzhu Xu (China Three Gorges University, P.R. China), Yide Ma (Lanzhou University, P.R. China) and Zaifeng Zhang (Lanzhou University, P.R. China)
DOI: 10.4018/978-1-60566-902-1.ch024
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Iris recognition has been shown to be very accurate for human identification. In this chapter, an efficient and automatic iris recognition system using Intersecting Cortical Model (ICM) neural network is presented which includes two parts mainly. The first part is image preprocessing which has three steps. First, iris location is implemented based on local areas. Then the localized iris area is normalized into a rectangular region with a fixed size. At last the iris image enhancement is implemented. In the second part, the ICM neural network is used to generate iris codes and the Hamming Distance between two iris codes is calculated to measure the dissimilarity. In order to evaluate the performance of the proposed algorithm, CASIA v1.0 iris image database is used and the recognition results show that the system has good performance.
Chapter Preview
Top

1 Iris Image Preprocessing

The iris image preprocessing part includes three steps: iris location (pupil location and iris outer boundary location), normalization and iris enhancement.

Complete Chapter List

Search this Book:
Reset