Scale invariant face detection and classification method using shift invariant features extracted from log-polar image

This paper presents a scale invariant face detection and classification met hod which uses shift invariant features extracted from a Log-Polar image. S cale changes of a face in an image are represented as shift along the horiz ontal axis in the Log-Polar image. In order to obtain scale invariant featu res, shift invariant features are extracted from each row of the Log-Polar image. Autocorrelations, Fourier spectrum, and PARCOR coefficients are used as shift invariant features. These features are then combined with simple classification methods based on Linear Discriminant Analysis to realize sca le invariant face detection and classification. The effectiveness of the pr oposed face detection method is confirmed by experiments using face images captured under different scales, backgrounds, illuminations, and dates. To evaluate the proposed face classification method, we performed experiments using 2, 800 face images with 7 scales under 2 different backgrounds and fa ce images of 52 persons.