Iris anti-spoofing under varying illumination conditions
Abhilasha Malhotra, Rashmi Gupta · 2016
Today iris recognition systems are extensively used for security and authentication purposes due to their simplicity and high reliability. But these systems face a major challenge of being spoofed by high quality printed iris images or pictures captured by camera. The problem is aggravated by use of varying illumination conditions in an attack access attempt. This paper investigates spoofing attempts and suggests a simple approach based on statistical parameters to counter against such attacks in the event of varying illumination sources. Self Quotient Image (SQI) is used to combat varying lighting conditions. A feature score is computed based on the statistical parameters. A binary Support Vector Machine (SVM) classifier is used to classify the image under test as real or spoof by matching the feature score of the trained images to that of the test image. The experimental results show that the proposed method performs better than other state-of-the-art techniques.