Title :
Enhanced omnidirectional image unwrapping for face detection
Author :
Dupuis, Y. ; Mendoza Quispe, A. ; Vasseur, P. ; Castaneda, B. ; Ragot, N.
Author_Institution :
CEREMA, Le Grand-Quevilly, France
Abstract :
This paper introduces a new framework to improve the performance of Viola and Jones face detector on omnidirectional unwrapped images. First, an optimization scheme is used to improve the unwrapped image specifically for rectangular Haar-like features. Then, we compare our unwrapping approach to the performance obtained with spherical unwrapping. The impact of the decision boundary and candidate window density are also investigated. Our work suggests that our new unwrapping technique improves significantly the performance of Viola and Jones detector on omnidirectional unwrapped images.
Keywords :
Haar transforms; face recognition; optimisation; Haar-like features; Jones face detector; Viola face detector; enhanced omnidirectional image unwrapping; face detection; omnidirectional unwrapped images; optimization scheme; spherical unwrapping; Detectors; Face; Face detection; Optimization; Polynomials; Robot sensing systems; Training; Face detection; Omnidirectional Vision; Unwrapping;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7025052