Recognition of Unconstrained Handwritten Digits Using Feedforward MLP and Projection Profile

Autor/innen

  • Rohit Kumar Singh
  • Nidhi Gulati School of Information and Communication Technology, Gautam Buddha University, Greater Noida, India
  • Ravi Yadav School of Information and Communication Technology, Gautam Buddha University, Greater Noida, India

Schlagwörter:

Handwritten numeral recognition, Feedforward MLP, Projection profile

Abstract

This paper presents a new approach to off-line handwritten numeral recognition using feedforward MLP and projection profile. Different writers have variations in their handwriting since each writer possesses own writing speed, own styles, sizes or positions for numeral or text. Recognition of handwritten numerals poses serious problems because of high variability in numeral shapes written by individuals. The performance of character recognition system depends heavily on what kind of features extraction techniques are being used. Here a handwritten numeral is scanned and this image is fed into the computer in which it is recognized using projection profile, and converted into the same word in equivalent printed characters. This paper focusses on recognition and classification of various numeral recognition techniques.Keywords: Handwritten numeral recognition, feedforward MLP, projection profileCite this Article Singh RK, Gulati N, Yadav R. Recognition of Unconstrained Handwritten Digits Using Feedforward MLP and Projection Profile. Journal of Communication Engineering & Systems. 2015; 5(2): 15–20p.

Veröffentlicht

2015-06-25

Ausgabe

Rubrik

Research Articles