An object detection method for single images based on objectness estimation theory is proposed.Original proposals are generated based on combinational geometry. The proposals are scored by segmentation-based structural feature and support vector machine. Proposals are sorted according to their score. Quantitative validation on PASCAL VOC 2007 dataset
when the number of the proposals is 1 000
the algorithm can achieve recall rate at96. 1 %. Its detection performnce outperforms four classic algorithms.
关键词
Keywords
references
Selective Search for Object Recognition [J] . J. R. R. Uijlings,K. E. A. Sande,T. Gevers,A. W. M. Smeulders. International Journal of Computer Vision . 2013 (2)
Efficient Graph-Based Image Segmentation [J] . Pedro F. Felzenszwalb,Daniel P. Huttenlocher. International Journal of Computer Vision . 2004 (2)
Robust Real-Time Face Detection [J] . Paul Viola,Michael J. Jones. International Journal of Computer Vision . 2004 (2)