A Framework for iris partial recognition based on legendre wavelet filter

Autor: Sapiee Jamel, Sofia Najwa Ramli, Muktar Danlami, Mustafa Mat Deris
Předmět:
Zdroj: Scopus-Elsevier
Popis: An increasing need for biometrics recognition system has grown substantially to address the issues of recognition and identification especially in highly dense areas such as airport, train stations and for financial transaction. Evidences of these can be seen in some airports and also the implementation of these technologies in our mobile phones. Among the most popular biometric technologies include facial, fingerprints and iris recognition. The iris recognition is considered by many researchers to be the most accurate and reliable form of biometric recognition, because iris can neither be surgically operated with a chance of losing slight nor change due to ageing. However, presently most iris recognition system available can only recognize iris image with frontal-looking and high-quality images. Angular image and partially capture image cannot be authenticated with existing method of iris recognition. This research investigates the possibility of developing a framework for recognition partially captured iris image. The research also adopts the Legendre wavelet filter for the iris feature extraction. Selected iris images from CASIA, UBIRIS and MMU database were used to test the accuracy of the introduced framework. A threshold for the minimum iris image required was established.
Databáze: OpenAIRE