Efficient image compression with detecting text regions

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Various image and video compression methods have been developed so far for data reduction. However, necessary information of an original image or video may be degraded if the image is highly compressed without considering the importance of each region in the image. In this paper, we propose a method to detect regions that are important for humans in an image and compress the image efficiently by changing the compression rate according to the importance. We assume that text in an image is important and propose a method for detecting important text regions with the edge information and saliency map.

Original languageEnglish
Title of host publicationICSP 2012 - 2012 11th International Conference on Signal Processing, Proceedings
Pages650-653
Number of pages4
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 11th International Conference on Signal Processing, ICSP 2012 - Beijing, China
Duration: 2012 Oct 212012 Oct 25

Publication series

NameInternational Conference on Signal Processing Proceedings, ICSP
Volume1

Other

Other2012 11th International Conference on Signal Processing, ICSP 2012
CountryChina
CityBeijing
Period12/10/2112/10/25

Keywords

  • Edge
  • Image compression
  • JPEG
  • Saliency map
  • Text detection

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Efficient image compression with detecting text regions'. Together they form a unique fingerprint.

  • Cite this

    Kaneko, S., Sugaya, Y., & Omachi, S. (2012). Efficient image compression with detecting text regions. In ICSP 2012 - 2012 11th International Conference on Signal Processing, Proceedings (pp. 650-653). [6491571] (International Conference on Signal Processing Proceedings, ICSP; Vol. 1). https://doi.org/10.1109/ICoSP.2012.6491571