A new algorithm for eye detection in facial images was proposed. First
in a known facial image
the noises were cleaned with Median filtering method.Then
several areas where the gray-scale gra-dient was largest were chosen to be the candidates for brow- and- eye region.Finally
the exact positions
scales and directions of eyes were located by using SIFT algorithm. The experimental results demonstrated that the proposed algorithm has the advantages of higher accuracy rate and smaller computational complexity.
. Lowe D G. Distinctive image features from scale-invariant keypoints [J].International J. Computer Vision, 2004,60(2):91-110.
. Gizatdinova Yulia, Surakka Veikko. Feature-based detection of facial landmarks from neutral and expressive facial images [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2006,28(1):135-139.