Distortion corrections for better character recognition of camera-based document images
Yun-Koo Chung, Dae-Geun Jang, Wonpil Yu, Soo-Young Chi, Kyekyung Kim, Jung Soh · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2004
The usage of cellular camera phones and digital cameras is rapidly increasing. but camera imaging application is not so expanded due to the lack of practical camera imaging technology. Especially the acquisition environments of camera images are very different from those of scanner images. The status of light condition, viewing distance and viewing angles constantly varies in case of cameras. The variations of light condition and viewing distance make it difficult to extract character areas from images through binarization and the variation of camera viewing angles makes the images distorted geometrically. Therefore, the extraction of character areas for camera document images is far more complex and difficult than for scanner images. In this paper, these problems are totally discussed and the resolving methods are suggested for better image recognition. The solutions such as adaptive binarization, color conversion, correction of lens distortion and geometrical distortion correction are discussed and the correction methods are suggested for accurate document image recognition. In experiment, we use the various types of document images captured by mobile phone cameras and digital cameras. The results of distortion correction show that our image processing methods are efficient to increase the accuracy of character recognition for camera based document image.