High-efficiency Handwriting Recognition Online Shopping Systemby Mobile Devices

DOI

10.2991/ictcs-14.2014.5How to use a DOI?

Keywords

component;recognition, BAM,associative memory, real-time)

Abstract

This paper proposed an innovational method and technology real-time to carry out remote recognition system by a mobile device. User draws a pattern in the local browser to transmit to remote server that will to do recognized task and database search immediately. The recognition system is bidirectional associative memory (BAM) employing artificial neural network technology. This study is based on the example of buying a dog house on the network. When users use the mouse to draw in the browser they want to buy a dog house outline map, the proposed system will instantly be recognized. The recognition result will display relevant dog house style on the web page and allows users to pick them. First, this study will be classified commercial dog house, and set the corresponding graphics stored in the system. These are specified graphics are also training sample patterns of the system. Currently in use on the network, people are almost always enter key words to search for relevant information. This paper presents an innovative approach that users can do hand-drawn graphics data recognition and search by mobile devices.Finally, this study for the accuracy of pattern recognition, and made some improvement analysis experiments.

Copyright

© 2014, 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  - CONF
AU  - Sung-Jung Hsiao
AU  - Kuang-Yow Lian
AU  - Wen-Tsai Sung
PY  - 2014/05
DA  - 2014/05
TI  - High-efficiency Handwriting Recognition Online Shopping Systemby Mobile Devices
BT  - Proceedings of the 2nd International Conference on Teaching and Computational Science
PB  - Atlantis Press
SP  - 18
EP  - 22
SN  - 1951-6851
UR  - https://doi.org/10.2991/ictcs-14.2014.5
DO  - 10.2991/ictcs-14.2014.5
ID  - Hsiao2014/05
ER  -