In order to solve the problems of face detection under rotation in image plane and facial features localization

a hierarchical approach was presented.Corner detection

AdaBoost algorithm and C-V method were integrated into the approach.First

four kinds of detectors were trained by AdaBoost algorithm for detecting faces

eyes

noses and mouths.Second

the corners were extracted from image.The corners were regarded as candidate eyes and used to construct candidate face regions as input to the face detector.Third

the eye regions

nose regions and mouth regions were detected using the feature detectors

and the feature contours and feature points were extracted from the feature regions by C-V method.The experiments on CMU rotated face test set result a 94.6% correct rate with 24 false alarms

and the position of the extracted feature points were accurate.Results show that the proposed approach is efficient.