This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Performance evaluation of classifiers on handwritten character recognition
Authors
  Binu P Chacko
Abstract
Research on HCR including online (stroke trajectory based) and offline (image based) recognition have received intensive attention since 1960s. In online handwriting recognition, data are captured during the writing process on an electronics surfacing with a special pen. Offline HCR is a process of automatic computer recognition of characters in the optically scanned and digitized pages of text. This study concentrates on the offline recognition of handwritten Malayalam characters. It goes through major components of character recognition system such as preprocessing, feature extraction and classification. The character images are normalized and binarized during the preprocessing stage. Then, division point features are extracted from processed images and classified using SVM, ELM, and OS-ELM. Among the classifiers, SVM performed well on KUMCD database.
Keywords- Division point feature, ELM, OS-ELM, SVM
Publication Details
Unique Identification Number - IJEDR2102034Page Number(s) - 207-213Pubished in - Volume 9 | Issue 2 | June 2021DOI (Digital Object Identifier) -    http://doi.one/10.1729/Journal.27238Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Binu P Chacko,   "Performance evaluation of classifiers on handwritten character recognition", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.9, Issue 2, pp.207-213, June 2021, Available at :http://www.ijedr.org/papers/IJEDR2102034.pdf
Article Preview
|
|
||||||
|