Japanese Scene Character Recognition using Random Image Feature and Ensemble Scheme

Fuma Horie, Hideaki Goto

Abstract

Scene character recognition is challenging and difficult owing to various environmental factors at image capturing and complex design of characters. Japanese character recognition requires a large number of scene character images for training since thousands of character classes exist in the language. In order to enhance the Japanese scene character recognition, we utilized a data augmentation method and an ensemble scheme in our previous work. In this paper, Random Image Feature (RI-Feature) method is newly proposed for improving the ensemble learning. Experimental results show that the accuracy has been improved from 65.57% to 78.50% by adding the RI-Feature method to the ensemble learning. It is also shown that HOG feature outperforms CNN in the Japanese scene character recognition.

Download


Paper Citation


in Harvard Style

Horie F. and Goto H. (2019). Japanese Scene Character Recognition using Random Image Feature and Ensemble Scheme.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 414-420. DOI: 10.5220/0007341904140420


in Bibtex Style

@conference{icpram19,
author={Fuma Horie and Hideaki Goto},
title={Japanese Scene Character Recognition using Random Image Feature and Ensemble Scheme},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={414-420},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007341904140420},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Japanese Scene Character Recognition using Random Image Feature and Ensemble Scheme
SN - 978-989-758-351-3
AU - Horie F.
AU - Goto H.
PY - 2019
SP - 414
EP - 420
DO - 10.5220/0007341904140420