Eye location method based on symmetry analysis and high-order fractal feature

A method for eye location in human facial images based on symmetry analysis and the lacunarity, which is a high-order fractal feature, is proposed. First, the valley field algorithm is applied to the facial image and the eye candidates are identified. Then, principal component analysis is used to detect the symmetry axis of the human face. The eye candidates are grouped to form eye-pair candidates, and the whole image is rotated around the symmetry axis. Finally, a novel approach to estimate lacunarity value is proposed to describe accurately the local structure of eye regions. By comparing the lacunarity values of two eye regions within each eye-pair candidate, the eye-pair candidate with minimum lacunarity value difference is identified as the true one. Numerical experiments demonstrate the effectiveness and reliability of this method.