Abstract
In this paper, a new method for eyes localization is presented. By incorporating some geometrical constraints of eyes, our method includes such procedures as eyes image segmentation, eye candidates selection and eyeball detection. In order to locate the eyes more precisely, the valley map transformed from the grayscale face image using an arithmetical morphology method is successively binarized with a series of threshold values determined adoptively, and many possible eyeball candidates are extracted from them. The final position of the two eyes is obtained using a statistical method. Experimental results on AR and Yale face databases show that a locating rate of over 94% and an average locating disparity of below 2 pixels can be achieved.
Original language | English |
---|---|
Title of host publication | 2004 IEEE International Conference on Multimedia and Expo (ICME) |
Pages | 1199-1202 |
Number of pages | 4 |
Volume | 2 |
DOIs | |
Publication status | Published - 1 Dec 2004 |
Event | 2004 IEEE International Conference on Multimedia and Expo (ICME) - Taipei, Taiwan Duration: 27 Jun 2004 → 30 Jun 2004 |
Conference
Conference | 2004 IEEE International Conference on Multimedia and Expo (ICME) |
---|---|
Country/Territory | Taiwan |
City | Taipei |
Period | 27/06/04 → 30/06/04 |
Keywords
- Eye
- Image segmentation
- Image sequences
- Object detection
- Statistical analysis
ASJC Scopus subject areas
- General Engineering