DocumentCode :
446020
Title :
Learning informative features for spatial histogram-based object detection
Author :
Zhang, Hongming ; Gao, Wen ; Chen, Xilin ; Zhao, Debin
Author_Institution :
Dept. of Comput. Sci., Harbin Inst. of Technol., China
Volume :
3
fYear :
2005
fDate :
31 July-4 Aug. 2005
Firstpage :
1806
Abstract :
Feature extraction for object representation plays an important role in automatic object detection system. As the spatial histograms consist of marginal distribution of image over local patches, object texture and shape are simultaneously preserved by the spatial histogram representation. In this paper, we propose methods of learning informative features for spatial histogram-based object detection. We employ Fisher criterion to measure the discriminability of each spatial histogram feature and calculate features correlation using mutual information. In order to construct compact feature sets for efficient classification, we propose informative selection algorithm to select uncorrelated and discriminative spatial histogram features. The proposed approaches are tested on two different kinds of objects: car and video text. The experimental results show that the proposed approaches are efficient in object detection.
Keywords :
feature extraction; image classification; image representation; object detection; Fisher criterion; feature extraction; features correlation; image marginal distribution; informative feature; informative selection algorithm; object representation; object texture; spatial histogram-based object detection; video text; Computer vision; Face detection; Histograms; Humans; Mutual information; Object detection; Object recognition; Shape; Support vector machine classification; Support vector machines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
Type :
conf
DOI :
10.1109/IJCNN.2005.1556154
Filename :
1556154
Link To Document :
بازگشت