PROCEEDINGS OF THE ITE ANNUAL CONVENTION
Online ISSN : 2424-2292
Print ISSN : 1343-1846
ISSN-L : 1343-1846
2016
Conference information

A Robust Method of Detecting Multi-oriented Scene Text Candidate
*Rei ENDOYoshihiko KAWAIHideki SUMIYOSHIMasanori SANO
Author information
CONFERENCE PROCEEDINGS OPEN ACCESS

Pages 22B-4-

Details
Abstract
An image retrieval system based on name of person/place which reflected in news video images is required to utilize archived videos. One of the techniques to realize the system is a scene text recognition technique which can recognize a text written on signs and name tags. We propose a robust method of detecting multi-oriented scene text candidate by using a rotated-aspect ratio feature. Moreover, we define a rotated bounding box descriptor to fast find the rotated-aspect ratio.
Content from these authors
© 2016 The Institute of Image Information and Television Engineers
Previous article Next article
feedback
Top