Binary tree-based accuracy-keeping clustering using CDA for very fast Japanese character recognition

Yohei Sobu, Hideaki Goto

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

2 Citations (Scopus)

Abstract

Real-time character recognition in video frames has been attracting great attention from developers since scene text recognition was recognized as a new field of Optical Character Recognition (OCR) applications. There are thousands of characters in some oriental languages such as Japanese and Chinese, and the character recognition takes much longer time in general compared with European languages. Speed-up of character recognition is crucial to develop software for mobile devices such as Smart Phones. This paper proposes a binary tree-based clustering technique with CDA (Canonical Discriminant Analysis) that can keep the accuracy as quite high as possible. The experimental results show that the character recognition using the proposed clustering technique is 10.2 times faster than the full linear matching at mere 0.04% accuracy drop. When the proposed method is combined with the Sequential Similarity Detection Algorithm (SSDA), we can achieve 12.3 times faster character matching at exactly the same accuracy drop.

Original languageEnglish
Title of host publicationProceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011
Pages299-302
Number of pages4
Publication statusPublished - 2011 Dec 1
Event12th IAPR Conference on Machine Vision Applications, MVA 2011 - Nara, Japan
Duration: 2011 Jun 132011 Jun 15

Publication series

NameProceedings of the 12th IAPR Conference on Machine Vision Applications, MVA 2011

Other

Other12th IAPR Conference on Machine Vision Applications, MVA 2011
CountryJapan
CityNara
Period11/6/1311/6/15

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Binary tree-based accuracy-keeping clustering using CDA for very fast Japanese character recognition'. Together they form a unique fingerprint.

Cite this