Image feature based method for mail retrieval

  • Yuxiao Du*
  • , Yue Lu
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A mail retrieval method based on image feature is an innovative approach by which the postal department can realize the query of mail information. The paper chooses envelope images with handwritten address characters as retrieval object. Through a series of researches on a large number of image features, we select partition-block image feature, projection histogram feature and SIFT feature to construct feature vector. In order to accelerate processing speed, we optimize the retrieval procedure by matching feature component in multiple levels. The experimental results and comparative analysis have demonstrated that the precision of the proposed retrieval system reaches at least 99%, which proves the practicability and robustness of the method.

Original languageEnglish
Title of host publication2010 Chinese Conference on Pattern Recognition, CCPR 2010 - Proceedings
Pages374-378
Number of pages5
DOIs
StatePublished - 2010
Event2010 Chinese Conference on Pattern Recognition, CCPR 2010 - Chongqing, China
Duration: 21 Oct 201023 Oct 2010

Publication series

Name2010 Chinese Conference on Pattern Recognition, CCPR 2010 - Proceedings

Conference

Conference2010 Chinese Conference on Pattern Recognition, CCPR 2010
Country/TerritoryChina
CityChongqing
Period21/10/1023/10/10

Keywords

  • Mail retrieval
  • Mail sorting
  • Partition-block feature
  • Projection histogram feature
  • SIFT feature

Fingerprint

Dive into the research topics of 'Image feature based method for mail retrieval'. Together they form a unique fingerprint.

Cite this