Learning Sparse Features in Granular Space for Multi-View Face Detection

Authors:
Chang Huang;Haizhou Ai;Yuan Li;Shihong Lao
Affiliations:
Tsinghua University, China;Tsinghua University, China;Tsinghua University, China;Omron Corporation, Japan
Venue:
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Year:
2006

Citing 0
Cited 7

High-Performance Rotation Invariant Multiview Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses

International Journal of Computer Vision
Human detection in video over large viewpoint changes

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
A novel distribution-based feature for rapid object detection

Neurocomputing
Face detection based on multi-block LBP representation

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Visual tracking based on Distribution Fields and online weighted multiple instance learning

Image and Vision Computing
A survey on recent object detection techniques useful for monocular vision-based planetary terrain classification

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel sparse feature set is introduced into the Adaboost learning framework for multi-view face detection (MVFD), and a learning algorithm based on heuristic search is developed to select sparse features in granular space. Compared with Haar-like features, sparse features are more generic and powerful to characterize multi-view face pattern that is more diverse and asymmetric than frontal face pattern. In order to cut down search space to a manageable size, we propose a multi-scaled search algorithm that is about 6 times faster than brute-force search. With this method, a MVFD system is implemented that covers face pose changes over +/-45° rotation in plane (RIP) and +/-90° rotation off plane (ROP). Experiments over well-know test set are reported to show its high performance in both accuracy and speed.