Handwritten Word Recognition Based on Fourier Coefficients

Abstract

A machine which can read unconstrained words remains an unsolved problem. For example, automatic entry o handwritten documents into a computer is yet to be accomplished. Most systems attempt to segment letters o a word and read words one character at a time. Segmenting a handwritten word is very difficult and often, the confidence of the results is low. Another method which avoids segmentation altogether is to treat each word as a whole. This research investigates the use of Fourier Transform coefficients, computed from the whole word, for the recognition of handwritten words. To test this concept, the particular pattern recognition problem studied consisted of classifying four handwritten words. 'Buffalo', 'Vegas', 'Washington', 'City.' Several feature subsets of the Fourier coefficients are examined. The best recognition performance of 76.2% was achieved when the Karhunen-Loeve transform was computed on the Fourier coefficients. Pattern recognition, Recognition, Whole word recognition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1993
Accession Number
ADA274050

Entities

People

  • Gary Shartle

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Automated Speech Recognition
  • Classification
  • Computational Science
  • Computer Vision
  • Computers
  • Data Sets
  • Electrical Engineering
  • Feature Extraction
  • Hidden Markov Models
  • Markov Models
  • Pattern Recognition
  • Standards
  • Test Sets
  • Two Dimensional
  • Word Recognition

Readers

  • Approximation Theory.
  • Computer Programming and Software Development.
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation