Eye detection algorithm base on area-blocks pairing and multi-angle template matching
CCDC'09 Proceedings of the 21st annual international conference on Chinese Control and Decision Conference
Robust facial expression recognition in the presence of rotation and partial occlusion
Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference
Hi-index | 0.00 |
In many applications such as face detection/recognition a major phase would be eye detection. In addition, its wide use as a part of serious applications, made it an important task should be worked on. Using color characteristics is a useful way to detect eyes. We use special color space, YCbCr which its components give us worthwhile information about eyes. We make two maps according to its components and merge them to obtain a final map. Candidates are generated on this final map. We apply an extra phase on candidates to determine suitable eye pair. The extra phase consists of flexible thresholding and geometrical tests. Flexible thresholding makes generating candidates more carefully and geometrical tests allow proper candidates to be selected as eyes. Simulation results on CVL and Iranian Databases showed this phase improved the correct detection rate by about 12.4% and reach 98.5% success rate on the average.