Hierarchical word image representation for parts-based object recognition

Authors:
Xiangang Cheng;Yiqun Hu;Liang-Tien Chia
Affiliations:
Center for Multimedia and Network Technology, School of Computer Engineering, Nanyang Technological University, Singapore;Center for Multimedia and Network Technology, School of Computer Engineering, Nanyang Technological University, Singapore;Center for Multimedia and Network Technology, School of Computer Engineering, Nanyang Technological University, Singapore
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 5
Cited 0

Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Pictorial Structures for Object Recognition

International Journal of Computer Vision
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
The Representation and Matching of Pictorial Structures

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many multimedia applications can benefit from recognizing image content. It requires a robust and discriminative representation of objects, especially in the situation of only a few training samples available. In this paper, we present a new approach to integrate the advantages of bag-of-words model and part-based model for image recognition. Each image is encoded as a Hierarchical Word Image (HWI), which contains not only visual appearance but also spatial information. The object parts are then located and represented in HWI. Finally, the part-based Star Model (SM) is used to learn the object model and recognize the test images. It is shown that our proposed approach can detect more accurate part candidates and significantly improve the performance of original part-based model for object recognition.