Ultra-low resolution character recognition system with pruning mutual subspace method

Shuhei Toba, Hirotaka Kudo, Tomo Miyazaki, Yoshihiro Sugaya, Shinichiro Omachi

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

2 Citations (Scopus)

Abstract

Improvement of character recognition technology brings us various character recognition applications for mobile camera. However, many low-resolution and poor-quality character images exist due to the performance of the camera or the influence of environment, and existing methods are not good at recognizing those low-resolution characters. Therefore, we develop a character recognition system for ultra-low resolution character images less than 20∗20 pixels. The proposed system consists of three phases: increased training data with a generative learning method, creating a deblurred high-resolution image with Wiener filter and image alignment, and recognition by pruning Mutual Subspace Method.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages284-285
Number of pages2
ISBN (Electronic)9781479987443
DOIs
Publication statusPublished - 2015 Aug 20
Event2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015 - Taipei, Taiwan, Province of China
Duration: 2015 Jun 62015 Jun 8

Publication series

Name2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

Conference

Conference2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
Country/TerritoryTaiwan, Province of China
CityTaipei
Period15/6/615/6/8

Keywords

  • Accuracy
  • Cameras
  • Character recognition
  • Image recognition
  • Image resolution
  • Training data
  • Wiener filters

Fingerprint

Dive into the research topics of 'Ultra-low resolution character recognition system with pruning mutual subspace method'. Together they form a unique fingerprint.

Cite this