Paper Info
Title
T-HOG: An effective gradient-based descriptor for single line text regions
Abstract
We discuss the use of histogram of oriented gradients (HOG) descriptors as an effective tool for text description and recognition. Specifically, we propose a HOG-based texture descriptor (T-HOG) that uses a partition of the image into overlapping horizontal cells with gradual boundaries, to characterize single-line texts in outdoor scenes. The input of our algorithm is a rectangular image presumed to contain a single line of text in Roman-like characters. The output is a relatively short descriptor that provides an effective input to an SVM classifier. Extensive experiments show that the T-HOG is more accurate than Dalal and Triggs's original HOG-based classifier, for any descriptor size. In addition, we show that the T-HOG is an effective tool for text/non-text discrimination and can be used in various text detection applications. In particular, combining T-HOG with a permissive bottom-up text detector is shown to outperform state-of-the-art text detection systems in two major publicly available databases.
Year
DOI
Venue
2013
10.1016/j.patcog.2012.10.009
Pattern Recognition
Keywords
Field
DocType
single line text region,effective gradient-based descriptor,various text detection application,effective input,descriptor size,single-line text,effective tool,hog-based texture descriptor,text description,state-of-the-art text detection system,permissive bottom-up text detector,short descriptor
Texture Descriptor,Pattern recognition,Computer science,Local binary patterns,Histogram of oriented gradients,Artificial intelligence,Svm classifier,Classifier (linguistics),Partition (number theory),Detector,Text detection
Journal
Volume
Issue
ISSN
46
3
0031-3203
Citations 
PageRank 
References 
41
1.09
26
Authors
5
Name
Order
Citations
PageRank
Rodrigo Minetto117815.01
Nicolas Thome246430.22
Matthieu Cord3103879.86
Neucimar J. Leite41047.89
Jorge Stolfi51559296.06