Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICDAR.2013.186
Title: Scene text recognition using co-occurrence of histogram of oriented gradients
Authors: Tian, S.
Lu, S.
Su, B.
Tan, C.L. 
Issue Date: 2013
Citation: Tian, S., Lu, S., Su, B., Tan, C.L. (2013). Scene text recognition using co-occurrence of histogram of oriented gradients. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR : 912-916. ScholarBank@NUS Repository. https://doi.org/10.1109/ICDAR.2013.186
Abstract: Scene text recognition is a fundamental step in End-to-End applications where traditional optical character recognition (OCR) systems often fail to produce satisfactory results. This paper proposes a technique that uses co-occurrence histogram of oriented gradients (Co-HOG) to recognize the text in scenes. Compared with histogram of oriented gradients (HOG), Co-HOG is a more powerful tool that captures spatial distribution of neighboring orientation pairs instead of just a single gradient orientation. At the same time, it is more efficient compared with HOG and therefore more suitable for real-time applications. The proposed scene text recognition technique is evaluated on ICDAR2003 character dataset and Street View Text (SVT) dataset. Experiments show that the Co-HOG based technique clearly outperforms state-of-the-art techniques that use HOG, Scale Invariant Feature Transform (SIFT), and Maximally Stable Extremal Regions (MSER). © 2013 IEEE.
Source Title: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
URI: http://scholarbank.nus.edu.sg/handle/10635/78336
ISSN: 15205363
DOI: 10.1109/ICDAR.2013.186
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

31
checked on Dec 3, 2018

WEB OF SCIENCETM
Citations

14
checked on Dec 3, 2018

Page view(s)

38
checked on Sep 28, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.