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.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
