Method for Character Domain Extraction from Image Using Wavelet Transform

Authors
Taiki Taniguchi, Yasunari Yoshitomi
Corresponding Author
Taiki Taniguchi
Available Online 1 September 2015.
DOI
https://doi.org/10.2991/jrnal.2015.2.2.8
Keywords
Character domain extraction, Image processing, Internet, Private information, URL of illegal Web site, and Wavelet transform
Abstract
There has been an increase in the number of images on the Internet that contain private information and/or the URL of an illegal Web site. This information could result in a violation of human rights and/or a crime. We present a method for extracting from an image the region(s) that contain characters. Our method uses the discrete wavelet transform and the empirical knowledge that characters have strong vertical and/or horizontal elements. The experimental results show the usefulness of our method.

Copyright
© 2013, the Authors. Published by ALife Robotics Corp. Ltd.
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)