Simple and Efficient Document Image Binarization Technique For Degraded Document Images

Abstract

Document Image binarization converts an acquired gray-scale document image to binary format, the ob- jective of binarization is to automatically choose a threshold that separates the foreground and background information. Document image binarization is a process that is usually carried out in the pre-processing stage of document image pro- cessing. Primary aim of this document image binarization is to extract the foreground text from the document background. In the case of degraded document images this text extraction or segmentation is a difficult task. In this paper, we propose a simple and efficient document image binarization technique it makes use of the adaptive image contrast and some of the noise reduction methods. In the proposed technique, first input degraded document image is normalized to improve the quality of output binarized document image. Second, an adaptive image contrast map is constructed for the normalized image .Third, adaptive image contrast map is binarized and combined with Canny's edge map to identify the text stroke edge pixels. Then the document text is segmented by a local threshold that is estimated based on the intensities of the detected text stroke edge pixels. Finally, the output document image is filtered to reduce noise. The proposed method requires only minimum number of parameters. This method shows superior performance over various datasets interms of various performance measures.