Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks

机译：从多脚本邮政地址块中识别数字邮政编码

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

The objective of the current work is to recognize postal codes written in Roman, Devanagari, Bangla and Arabic scripts. In the first stage 25 unique digit patterns are identified from the handwritten numeral patterns of the said four scripts. A script independent unified pattern classifier is then designed to classify any digit pattern of these scripts into one of the 25 classes. In the next stage a rule-based script inference engine infers about the script of the numeric string, that invokes one of the four script specific classifiers. The average script-inference accuracy over a six digit numeric string is observed as 95.1% and the best recognition rates for the four script specific digit classifiers are obtained as 96.10%, 94.40%, 96.45 % and 95.60% respectively.

机译：当前工作的目的是识别以罗马，梵文，孟加拉和阿拉伯语书写的邮政编码。在第一阶段中，从所述四个脚本的手写数字图案中识别出25个唯一数字图案。然后设计独立于脚本的统一模式分类器，以将这些脚本的任何数字模式分类为25个类之一。在下一阶段，基于规则的脚本推断引擎将推断数字字符串的脚本，该引擎将调用四个特定于脚本的分类器之一。观察到六位数字字符串的平均脚本推断准确度为95.1％，四个特定于脚本的数字分类器的最佳识别率分别为96.10％，94.40％，96.45％和95.60％。

著录项

来源
《Pattern recognition and machine intelligence》|2009年|P.381-386|共6页
会议地点 New Delhi(IN);New Delhi(IN)
作者
Subhadip Basil; Nibaran Das; Ram Sarkar; Mahantapas Kundu; Mita Nasipuri; Dipak Kumar Basu;
展开▼
作者单位

Computer Science Engineering Department, Jadavpur University, Kolkata-700032, India;

rnComputer Science Engineering Department, Jadavpur University, Kolkata-700032, India;

rnComputer Science Engineering Department, Jadavpur University, Kolkata-700032, India;

rnComputer Science Engineering Department, Jadavpur University, Kolkata-700032, India;

rnComputer Science Engineering Department, Jadavpur University, Kolkata-700032, India;

rnComputer Science Engineering Department, Jadavpur University, Kolkata-700032, India A.I.C.T.E. Emeritus Fellow;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类人工智能理论;
关键词
OCR; script-identification; classification; postal automation;

机译：OCR；脚本标识；分类;邮政自动化;

相似文献

外文文献
中文文献
专利

1. A novel framework for automatic sorting of postal documents with multi-script address blocks [J] . Basu S., Das N., Sarkar R., Pattern Recognition: The Journal of the Pattern Recognition Society . 2010,第10期

机译：具有多脚本地址块的自动分类邮政文档的新颖框架
2. Alphabetical handwritten address recognition method allowing for no postal code and omission of several address elements [J] . Tatsuo Akiyama, Daisuke Nishiwaki, Eiki Ishidera, 電子情報通信学会技術研究報告. パターン認識·メディア理解. Pattern Recognition and Media Understanding . 2002,第708期

机译：按字母顺序排列的手写地址识别方法，无需邮政编码，并且可以省略多个地址元素
3. Alphabetical handwritten address recognition method allowing for no postal code and omission of several address elements [J] . Tatsuo Akiyama, Daisuke Nishiwaki, Eiki Ishidera, 電子情報通信学会技術研究報告. パターン認識·メディア理解. Pattern Recognition and Media Understanding . 2002,第708期

机译：字母表的手写地址识别方法允许无邮政编码和省略几个地址元素
4. Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks [C] . Subhadip Basu, Nibaran Das, Ram Sarkar, International Conference on Pattern Recognition and Machine Intelligence . 2009

机译：从多脚本邮政地址块识别数字邮政编码
5. A multimodal fusion approach for automatic postal address recognition system using Optical Character Recognition (OCR) and Automatic Speech Recognition (ASR) techniques. [D] . Singh, Amriteshwar. 2011

机译：一种使用光学字符识别（OCR）和自动语音识别（ASR）技术的自动邮政地址识别系统的多模式融合方法。
6. What is the importance of postal codes for health research? Re: (Fuller and Shareck) Canada Post community mailboxes: Implications for health research [O] . Yan Kestens, Alexandre Naud, Madeleine Steinmetz-Wood, 2014

机译：邮政编码对健康研究的重要性是什么？回复：（Fuller和Shareck）加拿大邮政社区邮箱：对健康研究的启示
7. Segmentation and recognition of handwritten postal codes [O] . César Michel 1988

机译：手写邮政编码的细分和识别

Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks

摘要

著录项

相似文献

相关主题

期刊订阅