Cursive Character Recognition by Learning Vector Quantization
Camastra, Francesco; Vinciarelli, Alessandro
2000

Files

Abstract

This paper presents a cursive character recognizer embedded in an off-line cursive script recognition system. The recognizer is composed of two modules: the first one is a feature extractor, the second one an LVQ. The selected feature set was compared to Zernike polynomials using the same classifier. Experiments are reported on a database of about 49000 isolated characters.

Details

Title Cursive Character Recognition by Learning Vector Quantization
Author(s) Camastra, Francesco ; Vinciarelli, Alessandro
Date 2000
Publisher IDIAP
Keywords
Note Accepted for publication by Pattern Recognition Letters
Additional link URL
Laboratories LIDIAP
Record Appears in Scientific production and competences > STI - School of Engineering > IEM - Institut d'Electricité et de Microtechnique > LIDIAP - L'IDIAP Laboratory
Scientific production and competences > Euler Center for Signal Processing
Work produced at EPFL
Technical Reports
Published
Record creation date 2006-03-10

Actions

Preview