Finding region of interest and automatic cropping from Palm leaf manuscripts by using one-dimensional segmentation

Abstract

This paper offers finding the region of interest and automatic cropping from palm leaf manuscripts developed by using one-dimensional segmentation. This system can be used to provide for enhancing palm leaf manuscripts are taken by high quality resolution digital camera. The one-dimensional segmentation approach is that object location can be determined by clustering points of interest and hierarchically forming candidate of palm leaf manuscript regions according to similarity and spatial proximity predicates. This system can be used to optimize two factors: RGB background colors and number of vertical lines to choose candidate area. Moreover, one-dimensional edge segmentation performs better accuracy and less calculation time than other traditional filters. This system can be applied to segmentation of candidate area which includes text. The results of the research can be used as an input image to implement an OCR system to provide information of being existence for their related fields.