Recognition of camera-captured low-quality characters using motion blur information |
| |
| Authors: | Hiroyuki Ishida Tomokazu Takahashi Ichiro Ide Yoshito Mekada Hiroshi Murase |
| |
| Affiliation: | 1. Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8601, Japan;2. Japan Society for the Promotion of Science, Japan;3. School of Life System Science & Technology, Chukyo University, 101, Tokodachi, Kaizu-cho, Toyota, Aichi 470-0393, Japan;1. Chemical Engineering Department, Parahyangan Catholic University, Bandung, Indonesia;2. Chemical Engineering Department, Groningen University, The Netherlands;1. College of Textiles and Fashion, Qingdao University, Qingdao 266071, China;2. Sunvim Grp. Co. Ltd., Gaomi 261500, China;3. Fiber and Polymer Science Program, Department of Textile Engineering, Chemistry and Science, North Carolina State University, Raleigh, USA;3. Hubei Collaborative Innovation Center for Green Transformation of Bioresources, Hubei Key Laboratory of Industrial Biotechnology, Hubei University, Wuhan 430062, China;4. Key Laboratory of Systems Microbial Biotechnology, Tianjin Institute of Industrial Biotechnology, Chinese Academy of Sciences, Tianjin 300308, China;5. Department of Chemistry, University of Texas, Austin, Texas 78712 |
| |
| Abstract: | Camera-based character recognition has gained attention with the growing use of camera-equipped portable devices. One of the most challenging problems in recognizing characters with hand-held cameras is that captured images undergo motion blur due to the vibration of the hand. Since it is difficult to remove the motion blur from small characters via image restoration, we propose a recognition method without de-blurring. The proposed method includes a generative learning method in the training step to simulate blurred images by controlling blur parameters. The method consists of two steps. The first step recognizes the blurred characters based on the subspace method, and the second one reclassifies structurally similar characters using blur parameters estimated from the camera motion. We have experimentally proved that the effective use of motion blur improves the recognition accuracy of camera-captured characters. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
