On-line Handwritten Devanagari Character Recognition using Fuzzy Directional Features

TL;DR

This paper introduces Fuzzy Directional Features (FDF), a novel feature set for recognizing handwritten Devanagari script, demonstrating effective stroke-level recognition in writer-independent scenarios.

Contribution

The paper presents a new Fuzzy Directional Features (FDF) set and experimentally validates its effectiveness for on-line handwritten Devanagari character recognition.

Findings

FDF performs well on writer-independent data

FDF improves stroke-level recognition accuracy

Effective for isolated handwritten character primitives

Abstract

This paper describes a new feature set for use in the recognition of on-line handwritten Devanagari script based on Fuzzy Directional Features. Experiments are conducted for the automatic recognition of isolated handwritten character primitives (sub-character units). Initially we describe the proposed feature set, called the Fuzzy Directional Features (FDF) and then show how these features can be effectively utilized for writer independent character recognition. Experimental results show that FDF set perform well for writer independent data set at stroke level recognition. The main contribution of this paper is the introduction of a novel feature set and establish experimentally its ability in recognition of handwritten Devanagari script.