Japanese / English

Detail of Publication

Text Language Japanese
Authors Megumi Sakai, Seiichi Uchida, Masakazu Iwamura, Shinichiro Omachi, and Koichi Kise
Title FSA-Based Optimal Segmentation for Camera-Based CharacterRecognition
Journal Proceedings of MIRU 2006
Presentation number IS3-2
Pages pp.1024-1029
Reviewed or not Not reviewed
Month & Year July 2006
Abstract For accurate camera-based character recognition, a method where category information is embedded onto every character image as a striped pattern has been investigated. The cross ratio calculated from the widths of stripes represents the category of the character. In this paper, an algorithm to detect the boundaries of the stripes for measuring the widths is proposed. The algorithm is realized by a combination of a dynamic programming-based optimal segmentation framework and a finite state automaton (FSA) which represents the characteristics of the striped pattern. Experimental results showed the ability of the proposed method on not only accurate boundary detection but also accurate recovery of the embedded cross ratio.
Back to list