Improved Boosting Algorithms Using Confidence-rated Predictions
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
On the approximation of curves by line segments using dynamic programming
Communications of the ACM
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Time Series Segmentation for Context Recognition in Mobile Devices
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Robust Object Detection via Soft Cascade
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Human dynamics: computation for organizations
Pattern Recognition Letters - Special issue: Advances in pattern recognition
High-Performance Rotation Invariant Multiview Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Speech "Siglet" Detection for Business Microscope (concise contribution)
PERCOM '08 Proceedings of the 2008 Sixth Annual IEEE International Conference on Pervasive Computing and Communications
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
Enhancing Human Face Detection by Resampling Examples Through Manifolds
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
| Hi-index | 0.00 |
Face detection has been well studied in terms of accuracy and speed. However, required memory size reduction is still poorly studied, which is becoming a critical issue as platforms for face detection go tiny. In this paper, we propose a novel compact weak classifier using Adaptive Look-Up-Table (ALUT) for face detection on resource-constrained devices such as wearable sensor nodes. ALUT gives good approximation of log-likelihood [3] with fewer data, thus enabling the drastic reduction of classifier data size, keeping high accuracy and low computation cost. To generate an optimal ALUT, a new cost function called Weighted Sum of Absolute Difference (WSAD) is also proposed for further improvement. In our experiment, the classifier data size is reduced by 43% and the computation cost is reduced by 15% with same accuracy, compared to a conventional fixed LUT classifier.