Open AccessCharacter Segmentation and Skew Correction for Handwritten Devanagari Scripts: A Friends Technique
Author(s) -
Ashok Kumar Bathla,
Sunil Kumar Gupta
Publication year - 2019
Publication title -
asian journal of engineering and applied technology
Language(s) - English
Resource type - Journals
ISSN - 2249-068X
DOI - 10.51983/ajeat-2019.8.1.1060
Subject(s) - devanagari , scripting language , computer science , optical character recognition , character (mathematics) , skew , segmentation , artificial intelligence , hindi , natural language processing , speech recognition , pattern recognition (psychology) , character recognition , image (mathematics) , mathematics , telecommunications , geometry , operating system
Optical Character Recognition (OCR) technology allows a computer to “read” text (both typed and handwritten) the way a human brain does.Significant research efforts have been put in the area of Optical Character Segmentation (OCR) of typewritten text in various languages, however very few efforts have been put on the segmentation and skew correction of handwritten text written in Devanagari which is a scripting language of Hindi. This paper aims a novel technique for segmentation and skew correction of hand written Devanagari text. It shows the accuracy of 91% and takes less than one second to segment a particular handwritten word.