Hybrid Algorithm, to segment Character in Gurmukhi Handwritten Text, with a Comparative Study

Immense research has been done on optical character recognition in the last few decades. The desire to make scanned text document as an editable document, forces the investigators to think about the optical character recognition (OCR). The process of recognizing a segmented part of the scanned image as a character is OCR. This process consists of three major sub processes pre processing, segmentation (the most crucial process) and then recognition. The incorrect segmentation can not lead to correct results; it is just like garbage in and garbage out. In case of handwritten document the situation is more difficult, because in that case, only few points are there which can be used to make segmentation. In this paper, we formulate an algorithm to segment the scanned document image as a character. As per the proposed algorithm, one part is extracted from the word present in the line. This extracted part is checked whether it has some meaningful symbol (as per Gurmukhi script). If it has then the extracted part is marked and written in the file, otherwise the extracted part is readjusted to find the symbol. This concept was implemented. These results were compared with other algorithms and got good reasonable results.