Improved Boosting Algorithms Using Confidence-rated Predictions
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Statistical Learning of Multi-view Face Detection
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Fast rotation invariant multi-view face detection based on real adaboost
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Ethnicity estimation with facial images
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Makeup support system for visually impaired persons: overview of system functions
ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs
Ethnicity classification based on a hierarchical fusion
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Hi-index | 0.00 |
We have developed a group of vision-based face understanding technologies called OKAO Vision (OKAO means face in Japanese) including face detection, facial feature point detection, face recognition and facial attribute estimation Our face detection technology can detect both frontal and profile faces rotated to any angles Facial feature point detection, face recognition and facial attribute estimation are based on a common architecture: using Gabor wavelet transform coefficients as feature values and use SVM as classifier Our experiments show that this architecture is very powerful In this paper, we explain the key technologies of OKAO Vision and how these technologies are used in applications for entertainment, communication, security and intelligent interfaces.