Improved Boosting Algorithms Using Confidence-rated Predictions
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Saliency, Scale and Image Description
International Journal of Computer Vision
Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
WaldBoost " Learning for Time Constrained Sequential Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Learning a fast emulator of a binary decision process
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Local Rank Patterns --- Novel Features for Rapid Object Detection
ICCVG 2008 Proceedings of the International Conference on Computer Vision and Graphics: Revised Papers
GP-GPU Implementation of the "Local Rank Differences" Image Feature
ICCVG 2008 Proceedings of the International Conference on Computer Vision and Graphics: Revised Papers
Hi-index | 0.01 |
A currently popular trend in object detection and pattern recognition is usage of statistical classifiers, namely AdaBoost and its modifications. The speed performance of these classifiers largely depends on the low level image features they are using: both on the amount of information the feature provides and the executional time of its evaluation. Local Rank Differences is an image feature that is alternative to commonly used haar wavelets. It is suitable for implementation in programmable (FPGA) or specialized (ASIC) hardware, but --- as this paper shows --- it performs very well on graphics hardware (GPU) as well. The paper discusses the LRD features and their properties, describes an experimental implementation of LRD in graphics hardware, presents its empirical performance measures compared to alternative approaches and suggests several notes on practical usage of LRD and proposes directions for future work.