Detection and correction of deformed historical arabic manuscripts

Historical manuscripts are considered one of the most imperative human riches and a source of intellectual production. Unfortunately, due to aging effects, multiple noises and deviations are found in the document image. Moreover, challenges for several images of ancient documents show defects of inclinations and curvatures of text lines. These defects arise due to bad storage conditions, or during the digitization process. In order to improve the readability and the automatic recognition of historical Arabic manuscripts, preprocessing steps are imperative. This paper presents a novel method that consists of two major phases. The first refer to binarization and enhancement of the scanned document image. In the second phase, correction of skew angle in the text line passes by the detection of curvature/inclination of the baseline. Then, calculating the skewed angle of this line, and finally, correcting the line with a rotation relative to its centre. The proposed method was implemented on different scanned Arabic documents. The proposed methodology overcomes the defects of global binarization method, also, save the high computation effort of adaptive binarization techniques. Moreover, it works well with both Arabic handwritten words and printed text.