Object recognition in complex backgrounds

Author

Wu, Lifang ; Liu, Xun ; Yin, Lu

Author_Institution

Dept. of Electron. Eng., Beijing Univ. of Technol., China

Volume

2

fYear

2004

fDate

31 Aug.-4 Sept. 2004

Firstpage

1601

Abstract

Semantic object recognition is key issue in CBIR (content based image retrieval), video analysis and so on. In this paper, we discuss how to recognize the semantic object - basketball. First, the color feature is extracted to determine the possible regions of basketball, then the steerable filters are used to extract the MGE and MGD, then edge probability and the direction of edge normal are obtained from MGE and MGD. Next the modified Hough transform is designed to extract the circle contour. Finally, using template matching, the texture image is extracted for object confirmation. Experimental results confirm the efficiency of algorithm.

Keywords

Hough transforms; content-based retrieval; edge detection; feature extraction; image colour analysis; image retrieval; image segmentation; image texture; object detection; object recognition; probability; sport; video signal processing; CBIR; circle contour extraction; color segmentation; content based image retrieval; edge normal direction; edge probability; feature extraction; image texture; modified Hough transform; semantic object recognition; steerable filter; template matching; video analysis; Color; Computer vision; Image analysis; Image retrieval; Image segmentation; Lighting; Matched filters; Object detection; Object recognition; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on

Print_ISBN

0-7803-8406-7

Type

conf

DOI

10.1109/ICOSP.2004.1441637

Filename

1441637