Conference paper

Kadlček, F., Fučík, O.: Evolutionary Design of Local Binary Pattern Feature Shapes for Object Detection, In: 2012 NASA/ESA Adaptive Hardware and Systems (AHS-2012) Conference, Nuremberg, DE, IEEE CS, 2012, p. 1-8, ISBN 978-1-4673-1914-0

Publication language:

english

Original title:

Evolutionary Design of Local Binary Pattern Feature Shapes for Object Detection

Title (cs):

Evoluční návrh geometrických tvarů příznaků Local Binary Pattern pro rozpoznávání objektů

Pages:

1-8

Proceedings:

2012 NASA/ESA Adaptive Hardware and Systems (AHS-2012) Conference

Conference:

NASA/ESA Conference on Adaptive Hardware and Systems 2012

Series:

CFP1263A-USB

Place:

Nuremberg, DE

Year:

2012

ISBN:

978-1-4673-1914-0

Publisher:

IEEE Computer Society

Files:

Keywords

Local Binary Pattern (LBP), AdaBoost, Evolutionary design, feature shapes

Annotation

This paper deals with the evolutionary design of application specific feature shapes of Local Binary Pattern (LBP) features for object detection in image processing applications. LBP features are very often utilized in image classification systems which are used for pattern recognition. By using genetic algorithm the application of specific weak classifiers' feature shapes, which are highly optimized to achieve a better accuracy of the AdaBoost strong classifier, are being evolved.

Abstract

BibTeX:

@INPROCEEDINGS{
   author = {Filip Kadlček and Otto Fučík},
   title = {Evolutionary Design of Local Binary Pattern Feature Shapes
	for Object Detection},
   pages = {1--8},
   booktitle = {2012 NASA/ESA Adaptive Hardware and Systems (AHS-2012)
	Conference},
   series = {CFP1263A-USB},
   year = {2012},
   location = {Nuremberg, DE},
   publisher = {IEEE Computer Society},
   ISBN = {978-1-4673-1914-0},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9987}
}

You are in section

Conference paper