Japanese / English

Detail of Publication

Text Language English
Authors Takuya Kobayashi, Masakazu Iwamura, Takahiro Matsuda and Koichi Kise
Title An Anytime Algorithm for Camera-Based Character Recognition
Journal Proc. 12th International Conference on Document Analysis and Recognition (ICDAR 2013)
Pages pp.1172-1176
Location Washington, DC, USA
Reviewed or not Reviewed
Presentation type Poster
Month & Year August 2013
Abstract In a scene image, some characters are difficult to recognize and some others are recognized easily. Such difficult characters usually make the processing time long while easy characters are recognized in a short time. In this paper, we propose a system which recognizes each character with a proper cost for the difficulty. Through the process, easy characters are recognized early and difficult ones are recognized late. This is a desired property of an anytime algorithm that the recognition accuracy does not decrease as the time increases. In order to realize it, we propose a method which splits the recognition process into several times and accumulates the recognition results and extracted features. We also discuss what is required to realize the anytime algorithm for the scene character recognition task. Experiments reveal that the proposed method obtains recognition results of easy characters earlier than the conventional method.
DOI 10.1109/ICDAR.2013.231
Back to list