摘要
Because of the spine, a book cannot be set flat on a flat bed scanner. As a result, the image suffers from shape distortion, variable brightness, and blurred characters. This paper describes a method based on book shape analysis to address these problems. The algorithm utilizes the relation between the distance from a line segment on the book to the flat bed and its projected length. The correction process uses edge extraction, iterative boundary point computations, linear image transformation, and histogram modification. Experimental results show that the shape distortion and brightness variance problems are perfectly resolved by the method.
Because of the spine, a book cannot be set flat on a flat bed scanner. As a result, the image suffers from shape distortion, variable brightness, and blurred characters. This paper describes a method based on book shape analysis to address these problems. The algorithm utilizes the relation between the distance from a line segment on the book to the flat bed and its projected length. The correction process uses edge extraction, iterative boundary point computations, linear image transformation, and histogram modification. Experimental results show that the shape distortion and brightness variance problems are perfectly resolved by the method.
