Handwritten Devanagari Word Recognition: A Curvelet Transform Based Approach

Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 4

Abstract

This paper presents a new offline handwritten Devanagari word recognition system. Though Devanagari is the script for Hindi, which is the official language of India, its character and word recognition pose great challenges due to large variety of symbols and their proximity in appearance. In order to extract features which can distinguish similar appearing words, we employ Curvelet Transform. The resultant large dimensional feature space is handled by careful application of Principal Component Analysis (PCA). The Support Vector Machine (SVM) and k-NN classifiers were used with one-against-rest class model. Results of Curvelet feature extractor and classifiers have shown that Curvelet with k-NN gave overall better results than the SVM classifier and shown highest results (93.21%) accuracy on a Devanagari handwritten words set.

Authors and Affiliations

Brijmohan Singh , Ankush Mittal , M. A. Ansari , Debashis Ghosh

Keywords

Related Articles

Comparative study on Relational data sets and XML data sets in J2EE system

In the real world extracting information entirely depends up on the type of the information, type of the structures used to maintain the information and type of the application programs used to extract the information. M...

Effect of Quality Parameters on Energy Efficient Routing Protocols in MANETs

This paper presents a survey on energy efficient routing protocols for wireless Ad-Hoc networks. Survey focus on recent development and modifications in this widely used field. In this paper I present a number of ways of...

BEYOND SIMULATED ANNEALING IN GRID SCHEDULING

In Grid Environment the number of resources and tasks to be scheduled is usually variable and dynamic in nature. This characteristic emphasizes the scheduling approach as a complex optimization problem. Scheduling is a k...

Performance Evaluation of Reactive, Proactive and Hybrid Routing Protocols in MANET

This Mobile Ad hoc Networks (MANET) is a set of wireless mobile nodes dynamically form spontaneous network which works without centralized administration. Due to this characteristic, there are some challenges that protoc...

Cloud Computing: A solution to Geographical Information Systems (GIS) Cloud Computing and GIS

Geographical Information Systems or Geospatial Information Systems (GIS) is a collection of tools that captures, stores, analyzes, manages, and presents data that are linked to geographical locations. GIS plays an essent...

Download PDF file
  • EP ID EP108135
  • DOI -
  • Views 121
  • Downloads 0

How To Cite

Brijmohan Singh, Ankush Mittal, M. A. Ansari, Debashis Ghosh (2011). Handwritten Devanagari Word Recognition: A Curvelet Transform Based Approach. International Journal on Computer Science and Engineering, 3(4), 1658-1665. https://europub.co.uk/articles/-A-108135