DocumentCode
2627190
Title
Practical study on real-time hand detection
Author
Zondag, Jorn Alexander ; Gritti, Tommaso ; Jeanne, Vincent
Author_Institution
Tech. Univ. of Eindhoven, Eindhoven, Netherlands
fYear
2009
fDate
10-12 Sept. 2009
Firstpage
1
Lastpage
8
Abstract
In this paper we describe algorithms and image features that can be used to construct a real-time hand detector. We present our findings using the histogram of oriented gradients (HOG) features in combination with two variations of the AdaBoost algorithm. First, we compare stump and tree weak classifier. Next, we investigate the influence of a large training database. Furthermore, we compare the performance of HOG against the Haar-like features.
Keywords
gesture recognition; gradient methods; image classification; learning (artificial intelligence); object detection; AdaBoost algorithm; histogram of oriented gradients; image features; real-time hand detection; stump weak classifier; tree weak classifier; Classification tree analysis; Detectors; Face detection; Face recognition; Histograms; Image databases; Laboratories; Lighting; Machine learning algorithms; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Affective Computing and Intelligent Interaction and Workshops, 2009. ACII 2009. 3rd International Conference on
Conference_Location
Amsterdam
Print_ISBN
978-1-4244-4800-5
Electronic_ISBN
978-1-4244-4799-2
Type
conf
DOI
10.1109/ACII.2009.5349503
Filename
5349503
Link To Document