In many application suck as face detection or 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.