Efficient iris recognition by characterizing key local variations
IEEE Transactions on Image Processing
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
This paper presents a new method of gaze tracking based on iris detection for images of human eyes captured by ordinary PC camera. In the basis of traditional iris detection, this paper improves the circle detection based on Hough transform by self-adopted angle step and in order to overcome the impact of light spot and noise, and presents the algorithm of interference-points elimination. The position user focus on screen is detected by comparing to the conference position after accurately calculating the centre pixel of pupil iris area. The proposed method is significant to the optimisation of network services and applications by apperceiving user experience UE through analysis sight movement sample of network user. Experimental results demonstrate the feasibility, the correct rate is 92%, 86% in 6 × 4, 8 × 6 screen block dividing respectively under normal circumstances.