Morphological Operations and Projection Profiles based Segmentation of Handwritten Kannada Document

Abstract

Segmentation is an important task of any Optical Character Recognition (OCR) system. It separates the image text documents into lines, words and characters. The accuracy of OCR system mainly depends on the segmentation algorithm being used. Segmentation of handwritten text of some Indian languages like Kannada, Telugu, Assamese is difficult when compared with Latin based languages because of its structural complexity and increased character set. It contains vowels, consonants and compound characters. Some of the characters may overlap together. Despite several successful works in OCR all over the world, development of OCR tools in Indian languages is still an ongoing process. Character segmentation plays an important role in character recognition because incorrectly segmented characters are unlikely to be recognized correctly. In this paper, a segmentation scheme for segmenting handwritten Kannada scripts into lines, words and characters using morphological operations and projection profiles is proposed. The method was tested on totally unconstrained handwritten Kannada scripts, which pays more challenge and difficulty due to the complexity involved in the script. Usage of the morphology made extracting text lines efficient by an average extraction rate of 94.5% .Because of the varying inter and intra word gaps an average segmentation rate of 82.35% and 73.08% for words and characters respectively is obtained.

Handwritten Kannada Numerals Recognition by Using Zone Features and CNN Classifier

“…The segmentation plays a significant role in character recognition because inaccurately segmentedcharactersareunlikelytobedocumentedaccurately.Inthispaper,asegmentation methodforsegmentingthehandwrittenKannadanumeralsintolines,wordsandcharacters withthehelpofmorphologicaloperationsandprojectionprofilesisproposed (Mamatha& Srikantamurthy, 2012). The method was tested on completely unconstrained handwritten Kannadanumerals,whichpaysmorechallengeandcomplexityduetothecomplicationincluded inthecharacters.…”

Computationally efficient handwritten Telugu text recognition

“…For the segmentation of text in the images into words and characters is difficult for Indic languages. Mamatha and Srikantamurthy [11] worked on Kannada character segmentation using morphological operations, which efficiently extracts the lines in the text. Later applied projection profiles for detecting characters form words that are in text lines.…”