Efficient estimation of character normal direction for Camera-based OCR

Kanta Kuramoto, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

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

Abstract

Handling characters the appearances of which are affected by three-dimensional (3D) rotation is a major challenge in Camera-Based Optical Character Recognition. Proper handling of these 3D rotated characters is expected to improve the performance of both detection and recognition of camera-captured characters. In this paper, we propose an efficient implementation of 3D rotation estimation for camera-captured characters. The proposed implementation requires small memory load and short computational time. We employ Linear Discriminant Function (LDF) instead of Modified Quadratic Discriminant Function (MQDF) for further memory reduction. The results of experimental evaluation using a large-scale alphanumeric character dataset showed that small number of dimensionality of original feature vector is sufficient for keeping accuracy of 3D rotation estimation and total amount of memory required for 3D rotation estimation is reduced from 141.0 MB to 6.6 MB. Moreover, we propose probabilistic rotation angle estimation and achieved improvement of estimation accuracy without increase of memory size.

Original languageEnglish
Title of host publication13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
PublisherIEEE Computer Society
Pages371-375
Number of pages5
ISBN (Electronic)9781479918058
DOIs
Publication statusPublished - Nov 20 2015
Event13th International Conference on Document Analysis and Recognition, ICDAR 2015 - Nancy, France
Duration: Aug 23 2015Aug 26 2015

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume2015-November
ISSN (Print)1520-5363

Other

Other13th International Conference on Document Analysis and Recognition, ICDAR 2015
Country/TerritoryFrance
CityNancy
Period8/23/158/26/15

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Efficient estimation of character normal direction for Camera-based OCR'. Together they form a unique fingerprint.

Cite this