Conference paper

 
Hradiš, M., Herout, A., Zemčík, P.: Local Rank Patterns - Novel Features for Rapid Object Detection, In: Proceedings of International Conference on Computer Vision and Graphics 2008, Heidelberg, DE, Springer, 2008, p. 1-12, ISSN 0302-9743
Publication language:english
Original title:Local Rank Patterns - Novel Features for Rapid Object Detection
Title (cs):Local Rank Patterns - nové příznaky pro rychlou detekci objektů
Pages:1-12
Proceedings:Proceedings of International Conference on Computer Vision and Graphics 2008
Conference:International Conference on Computer Vision and Graphics 2008
Series:Lecture Notes in Computer Science
Place:Heidelberg, DE
Year:2008
Journal:Lecture Notes in Computer Science, No. 12, DE
ISSN:0302-9743
Publisher:Springer Verlag
URL:http://pcl210-01.fit.vutbr.cz/trenovadlo/index.php [HTML]
URL:http://www.fit.vutbr.cz/research/groups/graph/publi/2008/2008-Hradis-ICCVG-LRP.pdf [PDF]
Keywords
WadlBoost, Local Rank Differences, Local Rank Patterns, object detection
Annotation
This paper presents Local Rank Patterns (LRP) - novel features for rapid object detection in images which are based on existing features Local Rank Differences (LRD). The performance of the novel features is thoroughly tested on frontal face detection task and it is compared to the performance of the LRD and the traditionally used Haar-like features. The results show that the LRP surpass the LRD and the Haar-like features in the precision of detection and also in the average number of features needed for classification. Considering recent successful and efficient implementations of LRD on CPU, GPU and FPGA, the results suggest that LRP are good choice for object detection and that they could replace the Haar-like features in some applications in the future.
BibTeX:
@INPROCEEDINGS{
   author = {Michal Hradiš and Adam Herout and Pavel Zemčík},
   title = {Local Rank Patterns - Novel Features for Rapid Object
	Detection},
   pages = {1--12},
   booktitle = {Proceedings of International Conference on Computer Vision
	and Graphics 2008},
   series = {Lecture Notes in Computer Science},
   journal = {Lecture Notes in Computer Science},
   number = {12},
   year = {2008},
   location = {Heidelberg, DE},
   publisher = {Springer Verlag},
   ISSN = {0302-9743},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=8838}
}