Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/72994
Title: 2D partially occluded object recognition using curve moments
Authors: Lim, K.B. 
Du, T.
Zheng, H.
Keywords: And segment
Computer vision
Curve moment
Pattern recognition
Issue Date: 2004
Source: Lim, K.B.,Du, T.,Zheng, H. (2004). 2D partially occluded object recognition using curve moments. Proceedings of the Seventh IASTED International Conference on Computer Graphics and Imaging : 303-308. ScholarBank@NUS Repository.
Abstract: This paper presents a new approach for recognition of 2D partially occluded objects using the curve moments as the features. In this approach, the boundary of object of interest is first extracted after image pre-processing. Then corner points were used to partition the boundary into curve segments consisted of 3 consecutive breakpoints. Subsequently, seven different order moment descriptors are computed as feature vectors for each segment. Finally, feature matching between the object of interest in scene and the model is performed hierarchically. From the experiment results, the proposed recognition algorithm was found to be robust to similarity transform, noise and partial occlusion, and computational efficient.
Source Title: Proceedings of the Seventh IASTED International Conference on Computer Graphics and Imaging
URI: http://scholarbank.nus.edu.sg/handle/10635/72994
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

70
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.