In this paper, a novel binarization approach based on neutrosophic sets and sauvola’s approach is presented. This approach is used for historical Arabic manuscript images which have problems with types of noise. The input RGB image is changed into the NS domain, which is shown using three subsets, namely, the percentage of indeterminacy in a subset, the percentage of falsity in a subset and the percentage of truth in a subset. The entropy in NS is used for evaluating the indeterminacy with the most important operation ”λ mean” operation in order to minimize indeterminacy which can be used to reduce noise. Finally, the manuscript is binarized using an adaptive thresholding technique. The main advantage of the proposed approach is that it preserves weak connections and provides smooth and continuous strokes. The performance of the proposed approach is evaluated both objectively and subjectively against standard databases and manually collected data base. The proposed method gives high results compared with other famous binarization approaches.
Document image binarization, Historical manuscript image, Neutrosophic theory, Pixel classification.
Aboul Ella HASSANIEN, Mohamed ABDELFATTAH, Khaled M. AMIN, Sherihan MOHAMED, "A Novel Hybrid Binarization Technique for Images of Historical Arabic Manuscripts", Studies in Informatics and Control, ISSN 1220-1766, vol. 24(3), pp. 271-282, 2015. https://doi.org/10.24846/v24i3y201504
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).