Efficient binarization technique for severely degraded document images

Abstract

Degradations in document images appear due to shadows, non-uniform illumination, ink bleed-through and blur caused by humidity. Thresholding of such document images either result in broken characters or detection of false texts. Numerous algorithms exist that can separate text and background efficiently in the textual regions of the document; but portions of background are mistaken as text in areas that hardly contain any text. This paper presents a way to overcome these problems by a robust binarization technique that recovers the text from a severely degraded document images and thereby increases the accuracy of optical character recognition systems. The proposed document recovery algorithm efficiently removes degradations from document images. Proposed work is based on the fusion of two well known binarization methods: Gatos et al. and Niblack, using dilation and logical AND operations. The results of our proposed binarization approach are seen to be better when compared to five existing well known approaches proposed by Otsu, Gatos et al., Niblack, Souvola et al., and Bernsen using four evaluations measures: Execution time, F-measure, PSNR, and NRM.