Scale Invariant Face Detection and Classification Method Using Shift Invariant Features Extracted from Log-Polar Image

摘要

This paper presents a scale invariant face detec- tion and classification method which uses shift invariant features extracted from a Log-Polar image. Scale changes of a face in an image are represented as shift along the horizontal axis in the Log-Polar image. In order to obtain scale invariant features, shift invariant features are extracted from each row of the Log- Polar image. Autocorrelation, Fourier spectrum, and PARCOR coefficients are used as shift invariant features.