Please use this identifier to cite or link to this item: https://doi.org/10.1016/0031-3203(96)00024-6
Title: Fuzzy pyramid scheme for distorted object recognition
Authors: Liu, X.
Tan, S. 
Ong, S.H. 
Keywords: Character recognition
Distorted object recognition
Fuzzy entropy
Fuzzy pyramid scheme
Map recognition
Issue Date: Oct-1996
Source: Liu, X., Tan, S., Ong, S.H. (1996-10). Fuzzy pyramid scheme for distorted object recognition. Pattern Recognition 29 (10) : 1631-1646. ScholarBank@NUS Repository. https://doi.org/10.1016/0031-3203(96)00024-6
Abstract: This paper considers the problem of distorted object recognition using the fuzzy pyramid approach developed by the authors. [Liu, Tan, Srinivasan, Ong and Xie, Pattern Recognition 27(5), 741-756 (1994)]. A distorted object is one that has undergone some kind of deformation in shape. Due to its nature, this recognition problem is considerably more difficult compared with that of conventional invariant object recognition. We first characterize the distortion of an object in terms of linear and nonlinear transformations along the two coordinate axes and provide a classification scheme for typical distortions. The fuzzy pyramid recognition system described earlier is then modified and applied to different classes of distorted objects. The key concepts are fuzzy entropy, which results in a significant reduction in feature dimension, and supervised learning, which is used to form object templates efficiently. To evaluate its performance, the system is applied to the practical problems of map recognition and character recognition. The effectiveness of the method is clearly demonstrated by the high recognition rate in these applications. Copyright © 1996 Pattern Recognition Society. Published by Elsevier Science Ltd.
Source Title: Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/62237
ISSN: 00313203
DOI: 10.1016/0031-3203(96)00024-6
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

3
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

1
checked on Nov 16, 2017

Page view(s)

28
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


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