Skip to main navigation Skip to search Skip to main content

Chinese character image retrieval based on moment invariants and shape context

  • Beihang University

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

Abstract

This paper presents a retrieval method for the image of Chinese characters calligraphy. The precision and recall rate are main indicators to measure the quality of image retrieval algorithm. Starting from the two aspects, there are two parts in the process of image retrieve which is proposed in this paper. In this paper, carry out the retrieve with the Hu invariant moment matching algorithm, which is fast and efficient, but little of the accuracy. Then, execute trice retrieval with shape context algorithm taking the advantages of high level of accuracy and good robustness based on the result set of the first retrieval. Experiments show that the method referred in this paper is accurate and efficient.

Original languageEnglish
Title of host publicationProceedings of 2015 IEEE International Conference on Computer and Communications, ICCC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages146-150
Number of pages5
ISBN (Electronic)9781467381253
DOIs
StatePublished - 19 Jan 2016
EventIEEE International Conference on Computer and Communications, ICCC 2015 - Chengdu, China
Duration: 10 Oct 201511 Oct 2015

Publication series

NameProceedings of 2015 IEEE International Conference on Computer and Communications, ICCC 2015

Conference

ConferenceIEEE International Conference on Computer and Communications, ICCC 2015
Country/TerritoryChina
CityChengdu
Period10/10/1511/10/15

Keywords

  • calligraphy image
  • matching
  • moment invariants
  • retrieval
  • shape context

Fingerprint

Dive into the research topics of 'Chinese character image retrieval based on moment invariants and shape context'. Together they form a unique fingerprint.

Cite this