STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Electronic Design Technology

Text Line Segmentation for Kannada Language Using Enhanced Horizantol Projection Profile Method

  1. Shakunthala B S
  2. Ullas H.S.
  3. Pillai C.S. C.S.
  4. M Suresh

Abstract

Handwritten character image is taken as dataset for this method. Segmentation is crucial in the Human Character Recognition System for extracting text lines, words, and characters from handwritten Kannada documents. In the proposed system, segmenting text lines, word, characters are done based on enhanced horizantol projection profile approach. The algorithm will be used for finding the height and width of the entire handwritten word The horizontal projection profile approach is evaluated using photographs from a handwritten Kannada manuscript with 100 data set dimension. The system achieved an average segmentation rate of 96.38% on fully unconstrained handwritten Kannada documents.

Keywords

Support