STRUCTURAL CLASSIFICATION AND RELAXATION MATCHING OF TOTALLY UNCONSTRAINED HANDWRITTEN ZIP-CODE NUMBERS

被引：76

作者：

LAM, L ^{[1
]}

SUEN, CY ^{[1
]}

机构：

[1] CONCORDIA UNIV,DEPT COMP SCI,1455 MAISONNEUVE BLVD W,MONTREAL H3G 1M8,QUEBEC,CANADA

来源：

PATTERN RECOGNITION | 1988年 / 21卷 / 01期

基金：

加拿大自然科学与工程研究理事会;

关键词：

CLASSIFICATION ALGORITHM - FEATURE EXTRACTOR - HANDWRITTEN NUMERALS - RELAXATION MATCHING - ZIP-CODE NUMBERS;

D O I：

10.1016/0031-3203(88)90068-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A system for recognizing totally unconstrained handwritten numerals is described. It comprises a feature extractor and two classification algorithms. The feature extractor decomposes the skeleton of a character into geometric primitives containing topological information of the character. These primitives consist of convex polygons and line segments, and features are generated from each primitive. The recognition process contains a fast structural classifier that identifies the majority of the samples, and a robust relaxation algorithmn which classifies the rest of the data. The system was trained and tested on real-life handwritten ZIP codes.

引用

页码：19 / 31

页数：13

共 4 条

[1] ZIP-Code Classification using Spatial and Crowdsourced Data
Khan, Tunaggina Subrina
2018 IEEE 34TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE), 2018, : 1694 - 1698
[2] EFFICIENT CLASSIFICATION OF TOTALLY UNCONSTRAINED HANDWRITTEN NUMERALS WITH A TRAINABLE MULTILAYER NETWORK
STRINGA, L
PATTERN RECOGNITION LETTERS, 1989, 10 (04) : 273 - 280
[3] Handwritten ZIP code Classification Using Artificial Neural Networks
Kumar, K. Siva
Devi, D. Uma
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2013, 13 (08): : 77 - 81
[4] Automatic allograph selection and multiple expert classification for totally unconstrained handwritten character recognition.
Prevost, L
Milgram, M
FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 381 - 383

← 1 →