Title

Recognition of handprinted numerals in VISA® card application forms

Keywords

Computer vision; Handwriting recognition; Neural networks; OCR; Self-organization

Abstract

An optical character recognition (OCR) frame-work is developed and applied to handprinted numeric fields recognition. The numeric fields were extracted from binary images of VISA® credit card application forms. The images include personal identity numbers and telephone numbers. The proposed OCR framework is a cascaded neural networks. The first stage is a self-organizing feature map algorithm. The second stage maps distance values into allograph membership values using a gradient descent learning algorithm. The third stage is a multi-layer feedforward net-work. In this paper, we present experimental results which demonstrate the ability to read handprinted numeric fields. Experiments were performed on a test data set from the CCL/ITRI database which consists of over 90,390 handwritten numeric digits.

Publication Date

1-1-1997

Publication Title

Machine Vision and Applications

Volume

10

Issue

3

Number of Pages

144-149

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1007/s001380050067

Socpus ID

0030654543 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0030654543

This document is currently not available here.

Share

COinS