Recognition with supplementary information how many bits are lacking for 100% recognition?

Masakazu Iwamura, Seiichi Uchida, Shinichiro Omachi, Koichi Kise

Research output: Contribution to conferencePaperpeer-review

4 Citations (Scopus)

Abstract

In this paper, we propose a new model in which the classifier receives not only a pattern itself but also supplementary information that assists recognition. This model enables us to achieve a 100% recognition rate with a 0% rejection rate with certain bits of supplementary information required. For printed characters, experiments show that 4 bits of supplementary information were required in the leave-one-out method and 1 bit was in the resubstitution method. In addition, we generalize the discussion into the relationship among a quantity of supplementary information, a recognition rate and a rejection rate. The theory presented in this paper is applied to the data embedding of a font set for camera-based character recognition [9].

Original languageEnglish
Pages68-75
Number of pages8
Publication statusPublished - Dec 1 2005
Event1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005 - Seoul, Korea, Republic of
Duration: Aug 29 2005Aug 29 2005

Other

Other1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005
Country/TerritoryKorea, Republic of
CitySeoul
Period8/29/058/29/05

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'Recognition with supplementary information how many bits are lacking for 100% recognition?'. Together they form a unique fingerprint.

Cite this