Title :
A new eye location method based on Ring Gabor Filter
Author :
Zhang, Yanfang ; Sun, Nongliang ; Gao, Yang ; Cao, Maoyong
Author_Institution :
Coll. of Inf. & Electr. Eng., Shandong Univ. of Sci. & Technol., Qingdao
Abstract :
The eyes are the most important facial landmarks on human face. It is significant to extract the feature of eyes efficiently. In order to improve the real-time and veracity performance of the eye location method, this paper presents a coarse-to-fine eye location method based on ring Gabor filter (RGF). First an elliptical Gabor filter is devised to convolute with the face image to highlight the eye region, which can be exploited to segment the two pupil regions efficiently. After getting the region of the pupil, a circular Gabor filter is used to locate the centre of the eyeball. Extensive experiments on the face base show that the method can locate the pupils accurately. Comparing with other algorithms, results prove that this method is robust to the variations of face poses, expressions, accessories and illuminations.
Keywords :
Gabor filters; elliptic filters; eye; face recognition; feature extraction; image segmentation; circular Gabor filter; elliptical Gabor filter; eye location; eye segmentation; face image; facial landmark; feature extraction; ring Gabor filter; Band pass filters; Eyes; Face detection; Face recognition; Feature extraction; Gabor filters; Image segmentation; Lighting; Robustness; Shape; Circular Gabor Filter; Elliptical Gabor Filter; Ring Gabor Filter; coarse-to-fine; eye location;
Conference_Titel :
Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-2502-0
Electronic_ISBN :
978-1-4244-2503-7
DOI :
10.1109/ICAL.2008.4636164