Color and Shape based Method for Detecting and Classifying Card Images

DOI

10.2991/jrnal.2018.4.4.6How to use a DOI?

Keywords

color segmentation, shape classification, interactive e-learning.

Abstract

This paper proposes an effective method for detecting and classifying card images by using color and shape features. We extract the card color area using color information and remove low possibility regions based on shape feature. Then, we classify the image by taking classroom size and camera distance. In order to confirm the proposed method, we conduct the experiments with our own videos. According to experimental results the proposed method achieves the overall accuracy of 93.93% in various classroom type (small and large).

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Cho Nilar Phyo
AU  - Thi Thi Zin
AU  - Hiroshi Kamada
AU  - Takashi Toriu
PY  - 2018
DA  - 2018/03/31
TI  - Color and Shape based Method for Detecting and Classifying Card Images
JO  - Journal of Robotics, Networking and Artificial Life
SP  - 287
EP  - 290
VL  - 4
IS  - 4
SN  - 2352-6386
UR  - https://doi.org/10.2991/jrnal.2018.4.4.6
DO  - 10.2991/jrnal.2018.4.4.6
ID  - Phyo2018
ER  -