Share Email Print

Proceedings Paper

Object detection based on 2D canonical correlation analysis
Author(s): Guofeng Zhang; Weida Zhou; Weihua Ren
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A novel approach combining 2DCCA, edge detector, and corner detector for object detection is proposed in this paper. The detection system consists of two stages. In the first stage, edge and corner information is obtained by edge detector and corner detector. By setting range for the number of edge pixel and corner in the scanning window, a large number of non-object windows are rejected. In the second stage, the classifier trained by 2DCCA is combined with slide window method so that further non-object windows are rejected. For the case that one object is simultaneously contained in several windows, the algorithm of determining the best position of object is designed. Compared with related approaches, our method has advantage of obtaining higher precision under the similar recall. The performance of the proposed approach is illustrated by experimental results.

Paper Details

Date Published: 15 November 2007
PDF: 8 pages
Proc. SPIE 6788, MIPPR 2007: Pattern Recognition and Computer Vision, 67882P (15 November 2007); doi: 10.1117/12.750452
Show Author Affiliations
Guofeng Zhang, Xidian Univ. (China)
Weida Zhou, Xidian Univ. (China)
Weihua Ren, Xidian Univ. (China)

Published in SPIE Proceedings Vol. 6788:
MIPPR 2007: Pattern Recognition and Computer Vision
S. J. Maybank; Mingyue Ding; F. Wahl; Yaoting Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top