Recognition of Hand written and Printed Text of Cursive Writing Utilizing Optical Character Recognition

Optical character recognition is one of the capabilities of computers to perceive text from external sources, for example, e-structures, e-archives, etc. OCR is a technique to recognize handwritten or printed text by a PC. It converts handwritten, printed, or photo of any documents into digitized format. OCR is mainly applied in the research fields of pattern recognition, machine learning, and computer vision. Here in this paper, we use OCR and k-nearest neighbor algorithm and classifier for text recognition. The project is equipped to recognize both handwritten and printed for cursive writing of the following styles; San-Serif, Tahoma, Comic Sans, and Calibri. The technique will recognize both the upper case and lower case text of the above mentioned style. The steps involved in the proposed methodology are pre-processing, segmentation, feature extraction, and recognition. The project recognizes the style of the text with an accuracy of 95.60%.