关键词: 文档图像, 径向失真, 数学形态学, 闭运算

Abstract: Document image captured by hand-held camera suffers from lens distortion more or less, and a mathematic morphology based lens correction algorithm was proposed according to the text line of document images. First, it used adaptive thresholding algorithm to segment the document image, and clustered connected components into text lines with morphology closing algorithm. Then, it used second order polynomial to fit the central line of text line, and constructed the object function of lens distortion. It warped the curved text line to the straight text line, thus, to solve the distortion parameters of document image. The experimental results show this method can effectively correct lens distortion of document image with various degrees.

Key words: document image, radial distortion, mathematical morphology, closing algorithm