Automatic segmentation & recognition of zip codes on handwritten real mail

J. V. Moreau, E. Lecolinet

Research output: Contribution to journalConference articlepeer-review

Abstract

The problem of the automatic recognition of unconstrained handwritten mail is discussed. Our approach combines statistical and structural techniques. The statistical stage is the first and main stage of our recognition system. It uses concavity measurements to characterize the characters and a linear discrimination technique is implemented to affect one character to one cluster. The second stage, called structural supervisor, was developed in order to control and improve the results of the first stage.

Original languageEnglish
Pages (from-to)217-221
Number of pages5
JournalIEE Conference Publication
Issue number307
Publication statusPublished - 1 Dec 1989
Externally publishedYes
EventThird International Conference on Image Processing and its Applications - Coventry, Engl
Duration: 18 Jul 198920 Jul 1989

Fingerprint

Dive into the research topics of 'Automatic segmentation & recognition of zip codes on handwritten real mail'. Together they form a unique fingerprint.

Cite this