Recognition of Camera-captured Characters in Blurred Image Using Motion-blur Parameters

We propose a recognition method of camera-captured characters using motion-blur parameters. One of the most challenging problems in recognizing characters with handheld cameras is motion-blur effect. In order to cope with this problem, a generationbased learning method is introduced in the training step to simulate blurred images. In the recognition step, motion-blur parameters are estimated and used for the matching to the artificial blurred images. We have experimentally proved that the effective use of the parameters improves the recognition accuracy of camera-captured characters.