Scene character detection and recognition based on multiple hypotheses framework

Rong Huang, Shinpei Oba, Shivakumara Palaiahnakote, Seiichi Uchida

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

9 Citations (Scopus)

Abstract

To handle the diversity of scene characters, we propose a multiple hypotheses framework which consists of an image operator set module, an optical character recognition (OCR) module, and an integration module. Image operators detect multiple suspicious character areas. The OCR engine is then applied to each detected area and returns multiple candidates with weight values for future integration. Without the aid of heuristic constraints on area, aspect ratio or color etc., the integration module prunes the redundant detection and pads the missing detection based on the outputs of OCR. The experimental results demonstrate that the whole multiple hypotheses outperforms each operator's hypotheses and be comparable with existing methods in terms of recall, precision, F-measure and recognition rate.

Original languageEnglish
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages717-720
Number of pages4
Publication statusPublished - 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1211/15/12

Fingerprint

Optical character recognition
Mathematical operators
Aspect ratio
Engines
Color

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Huang, R., Oba, S., Palaiahnakote, S., & Uchida, S. (2012). Scene character detection and recognition based on multiple hypotheses framework. In ICPR 2012 - 21st International Conference on Pattern Recognition (pp. 717-720). [6460235]

Scene character detection and recognition based on multiple hypotheses framework. / Huang, Rong; Oba, Shinpei; Palaiahnakote, Shivakumara; Uchida, Seiichi.

ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 717-720 6460235.

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

Huang, R, Oba, S, Palaiahnakote, S & Uchida, S 2012, Scene character detection and recognition based on multiple hypotheses framework. in ICPR 2012 - 21st International Conference on Pattern Recognition., 6460235, pp. 717-720, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.
Huang R, Oba S, Palaiahnakote S, Uchida S. Scene character detection and recognition based on multiple hypotheses framework. In ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 717-720. 6460235
Huang, Rong ; Oba, Shinpei ; Palaiahnakote, Shivakumara ; Uchida, Seiichi. / Scene character detection and recognition based on multiple hypotheses framework. ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. pp. 717-720
@inproceedings{0d7a3399bc60492594916a1b45e3def5,
title = "Scene character detection and recognition based on multiple hypotheses framework",
abstract = "To handle the diversity of scene characters, we propose a multiple hypotheses framework which consists of an image operator set module, an optical character recognition (OCR) module, and an integration module. Image operators detect multiple suspicious character areas. The OCR engine is then applied to each detected area and returns multiple candidates with weight values for future integration. Without the aid of heuristic constraints on area, aspect ratio or color etc., the integration module prunes the redundant detection and pads the missing detection based on the outputs of OCR. The experimental results demonstrate that the whole multiple hypotheses outperforms each operator's hypotheses and be comparable with existing methods in terms of recall, precision, F-measure and recognition rate.",
author = "Rong Huang and Shinpei Oba and Shivakumara Palaiahnakote and Seiichi Uchida",
year = "2012",
language = "English",
isbn = "9784990644109",
pages = "717--720",
booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

}

TY - GEN

T1 - Scene character detection and recognition based on multiple hypotheses framework

AU - Huang, Rong

AU - Oba, Shinpei

AU - Palaiahnakote, Shivakumara

AU - Uchida, Seiichi

PY - 2012

Y1 - 2012

N2 - To handle the diversity of scene characters, we propose a multiple hypotheses framework which consists of an image operator set module, an optical character recognition (OCR) module, and an integration module. Image operators detect multiple suspicious character areas. The OCR engine is then applied to each detected area and returns multiple candidates with weight values for future integration. Without the aid of heuristic constraints on area, aspect ratio or color etc., the integration module prunes the redundant detection and pads the missing detection based on the outputs of OCR. The experimental results demonstrate that the whole multiple hypotheses outperforms each operator's hypotheses and be comparable with existing methods in terms of recall, precision, F-measure and recognition rate.

AB - To handle the diversity of scene characters, we propose a multiple hypotheses framework which consists of an image operator set module, an optical character recognition (OCR) module, and an integration module. Image operators detect multiple suspicious character areas. The OCR engine is then applied to each detected area and returns multiple candidates with weight values for future integration. Without the aid of heuristic constraints on area, aspect ratio or color etc., the integration module prunes the redundant detection and pads the missing detection based on the outputs of OCR. The experimental results demonstrate that the whole multiple hypotheses outperforms each operator's hypotheses and be comparable with existing methods in terms of recall, precision, F-measure and recognition rate.

UR - http://www.scopus.com/inward/record.url?scp=84874573471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874573471&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874573471

SN - 9784990644109

SP - 717

EP - 720

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

ER -