Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikačního výsledku
HRADIŠ, M.; HEROUT, A.; ZEMČÍK, P.
Originální název
Local Rank Patterns - Novel Features for Rapid Object Detection
Anglický název
Druh
Stať ve sborníku mimo WoS a Scopus
Originální abstrakt
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.
Anglický abstrakt
Klíčová slova
WadlBoost, Local Rank Differences, Local Rank Patterns, object detection
Klíčová slova v angličtině
Autoři
Rok RIV
2010
Vydáno
12.11.2008
Nakladatel
Springer Verlag
Místo
Heidelberg
Kniha
Proceedings of International Conference on Computer Vision and Graphics 2008
Edice
Lecture Notes in Computer Science
ISSN
0302-9743
Periodikum
Číslo
12
Stát
Spolková republika Německo
Strany od
1
Strany do
Strany počet
URL
https://www.fit.vut.cz/research/publication/8838/
BibTex
@inproceedings{BUT33447, author="Michal {Hradiš} and Adam {Herout} and Pavel {Zemčík}", title="Local Rank Patterns - Novel Features for Rapid Object Detection", booktitle="Proceedings of International Conference on Computer Vision and Graphics 2008", year="2008", series="Lecture Notes in Computer Science", journal="Lecture Notes in Computer Science", number="12", pages="1--12", publisher="Springer Verlag", address="Heidelberg", issn="0302-9743", url="https://www.fit.vut.cz/research/publication/8838/" }