Abstract:
Historical handwritten palm leaf manuscripts are very informative documents from which we can learn precious and various experiences from them. This paper presents the character segmentations of historical handwriting from palm leaf manuscripts for handwriting character extraction. In this paper an experiment is carried out to choose color array of an image for binarization of palm leaf manuscripts. To extract images of each character from the leaf selected color intensity array is used for binarization by using famous Otsu thresholding algorithm. After that, image is segmented line by line searching optimal points among the lines using object frequency histogram along the line and Otsu algorithm again. These segmented images are the input elements and the character segmentation process as the final stage of this work. The end result is the images array which contains character images of palm leaf manuscripts. These images, the output of this work, can be applied to optical character recognition for text extraction.
