Enhanced omnidirectional image unwrapping for face detection

Y. Dupuis; A. Mendoza Quispe; P. Vasseur; B. Castaneda; Nicolas Ragot

Enhanced omnidirectional image unwrapping for face detection

Y. Dupuis, A. Mendoza Quispe, P. Vasseur, B. Castaneda, Nicolas Ragot

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

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.

Original language	Spanish
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Pages	263-267
Number of pages	5
State	Published - 28 Jan 2014
Externally published	Yes

Cite this

@inproceedings{b2d9f78b0f13465eae8642334f818c1a,

title = "Enhanced omnidirectional image unwrapping for face detection",

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.",

author = "Y. Dupuis and Quispe, {A. Mendoza} and P. Vasseur and B. Castaneda and Nicolas Ragot",

year = "2014",

month = jan,

day = "28",

language = "Espa{\~n}ol",

pages = "263--267",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

}

TY - GEN

T1 - Enhanced omnidirectional image unwrapping for face detection

AU - Dupuis, Y.

AU - Quispe, A. Mendoza

AU - Vasseur, P.

AU - Castaneda, B.

AU - Ragot, Nicolas

PY - 2014/1/28

Y1 - 2014/1/28

N2 - 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.

AB - 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.

M3 - Contribución a la conferencia

SP - 263

EP - 267

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

ER -