Feasibility of Hough-transform-based iris localisation for real-time-application

摘要

We present a fast method for locating iris features in frontal face images based on the Hough transform. it consists of an initial iris detection step and a tracking step which uses iris features from initialisation for speeding lip computation. The purpose of research was to evaluate the feasibility of the method for tracking at 200 frames per second or higher. Processing speed of the prototypical implementation on a 266 Mhz Pentium II PC is approximately 6 seconds for initial iris detection and about 0.05 seconds for each tracking step. Further speed-up using faster equipment seems feasible. The algorithm was applied to images of subjects taken under normal room lighting conditions. Tests showed robustness with respect to shadowing and partial occlusion of the iris. The localisation error was below two pixels. Accuracy for tracking was within one pixel. A reduction of the number of pixels, which are processed in the tracking step by 90% showed a modest degradation of the results.