Designing a Handwriting Reader

  title={Designing a Handwriting Reader},
  author={David J. Burr},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • D. Burr
  • Published 1 May 1983
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer recognition of cursive handwriting is complisated by the lack of letter separation. In an attempt to gain insight on the cursive problem, the simpler problem of recognizing separated hand-written letters is addressed here. A warp-based character matching technique is employed with dictionary lookup, using a 16 000 word vocabulary. Cooperative users achieve high recognition accuracy with this on-line system, which is easily tailored to the individual. Possible extensions to cursive… 

Figures from this paper

On-line cursive handwriting recognition: a survey of methods and performances

A detailed review of prior techniques and applications for on-line cursive handwriting recognition, since most have been used in cursive script recognition as well.

A New Approach in Persian Handwriting Recognition Using Writing Path

A novel method to recognize online Persian handwritten letters by using the letters’ writing path by comparing the curves of those two functions from input letter with stored samples, which suggests some possible letters in a sorted list.

Online handwriting recognition-a survey

It is found that online recognizers, except for bar-code readers and other specialized equipment, are not applicable to machine-printed characters.

A model for variability effects in handprinting with implications for the design of handwriting character recognition systems

The work is a synthesis of theoretical aspects and observations of handprinting styles in a large collection gathered during the development of a commercial online character recognition system, in which the variability effects are treated separately from the recognition process.

On-line recognition of connected handwriting

The ORCHiD system described in this thesis recognises connected handwriting collected on-line, in real time, via a digitising pad, and allows ambiguous matching, since cursive script is an ambiguous communications medium when taken out of context.

Handprinted text reader that learns by experience


A system for recognizing cursive English text, guided in part by global characteristics of the handwriting, and it is found that using a Hidden Markov Model of English is signiicantly less successful than assuming independence among the letters of a word.

Handwriting recognition or reading? What is the situation at the dawn of the 3rd millenium?

  • G. Lorette
  • Computer Science
    International Journal on Document Analysis and Recognition
  • 1999
The use of handwriting invariants, a physical model for a first segmentation, a logical model for segmentation and recognition, a fundamental equation of handwriting, and to integrate several sources of perception and of knowledge are proposed in order to design Handwriting Reading Systems (HRS), which would be more universal systems than is currently the case.



Automatic recognition of print and script

The evolution and present state of the art of machine recognition of print and script is examined and major problems of cost and effectiveness still exist.

Computer Recognition of Handwritten Numerals by Polygonal Approximations

The outlines of handwritten numerals are approximated by polygons using a method previously developed by Pavlidis and Horowitz [10]. This enables a simple evaluation of many intuitively descriptive

Experiments in the Contextual Recognition of Cursive Script

A structure for a contextual cursive script recognition system that makes use of letter context to determine word length, letter segmentation, and character identity to achieve contextual recognition at the word level is presented.

Contextual Postprocessing System for Cooperation with a Multiple-Choice Character-Recognition System

  • W. Doster
  • Computer Science
    IEEE Transactions on Computers
  • 1977
The paper describes the design and the optimization of a contextual postprocessing system (CPPS) operating in combination with a multiple-choice single-character recognition system (SCRS). The CPPS

Reading machines for the blind:The technical problems and the methods adopted for their solution

Direct assessment of speech synthesized by rule has shown that even currently available techniques can yield speech acceptable to blind users.

Experiments intheContextual Recognition ofCursive Script

In this paper astructure foracontextual cursive script recognition system is presented and the design ofacharacter recognizer that isbasically acorrelator basedonthestatistic, x2, is described.

A Dynamic Programming Algorithm for the Distance Between Two Finite Areas

  • Roger K. Moore
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1979
An algorithm for finding the distance between two finite areas is presented for speech recognition and orthographic word correction and applications of the algorithm are suggested.

A minimum-distance search technique and its application to automatic directory assistance

A new search procedure is described and its application to the problem of obtaining telephone directory information from spoken spelled input using the concept of equivalence classes, with names classified according to their letter-by-letter acoustic similarity.

Dynamic programming algorithm optimization for spoken word recognition

This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition, in which the warping function slope is restricted so as to improve discrimination between words in different categories.