On-line Character Recognition of Devanagari

From TC11
Jump to: navigation, search

Datasets -> Datasets List -> Current Page

Created: 2010-11-18
Last updated: 2011-001-28

Current Version



The aim of this task is to recognise on-line Devangari handwritten characters. The topic has received an a lot of attention lately due to the increasing number of Devangari speakers throughout the world.

Evaluation Protocol

A 5-fold cross validation is proposed as an evaluation protocol. See also [2] for details.


  1. Santosh K.C., Cholwich Nattee, Bart Lamiroy, 'Spatial Similarity based Stroke Number and Order Free Clustering', IAPR, 12th International Conference on Frontiers in Handwriting Recognition (ICFHR), Kolkata, India, 2010, to appear
  2. Santosh K.C., Cholwich Nattee, 'Template-based Nepali Handwritten Alphanumeric Character Recognition', Thammasat International Journal of Science and Technology (TIJSAT), Thailand, Vol. 12, No. 1, pp. 20 - 30, 2007
  3. Santosh K.C., Cholwich Nattee, 'Stroke Number and Order Free Handwriting Recognition for Nepali', 9th Pacific Rim International Conference on Artificial Intelligence (PRICAI), Springer - Lecture Notes in Computer Science (LNCS), Subseries: Lecture Notes in Artifical Intelligence (LNAI), Guilin, China, Vol. 4099, pp. 990-994, August 7 - 11, 2006
  4. Santosh K.C., Cholwich Nattee, 'Structural Approach on Writer Independent Nepalese Natural Handwriting Recognition', IEEE, International Conference on Cybernetics & Intelligent Systems (CIS), Bangkok, Thailand, pp. 711-716, June 7 - 9, 2006
  5. Santosh K.C., Cholwich Nattee, 'Effect of Pre-processing and Feature Selection in Recognition for Nepali', International Conference on Knowledge, Information, Creativity, and Support Systems (KICSS), Ayuthya, Thailand, pp. 139-146, August 1 - 4, 2006

Related Dataset

This page is editable only by TC11 Officers .