Abstract | ||
---|---|---|
Text detection in natural images has been a high demand for a lot real-life applications such as image retrieval and self-navigation. This work deals with the problem of robust text detection especially for multi-script in natural scene images. Unlike the existing works that consider multi-script characters as groups of text fragments, we consider them as non-connected components. Specifically, we firstly propose a novel representation named Linked Extremal Regions (LER) to extract full characters instead of fragments of scene characters. Secondly, we propose a two-stage convolution neural networks for discriminating multi-script texts in clutter background images for more robust text detection. Experimental results on three well-known datasets, namely, ICDAR 2011, 2013 and MSRA-TD500, demonstrate that the proposed method outperforms the state-of-the-art methods, and is also language independent. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-51811-4_27 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Linked extremal regions,Scene text detection,Multi-script | Pattern recognition,Convolution,Clutter,Computer science,Image retrieval,Speech recognition,Artificial intelligence,Deep learning,Artificial neural network,Text detection,Scripting language | Conference |
Volume | ISSN | Citations |
10132 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 13 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruo-Ze Liu | 1 | 1 | 1.03 |
Xin Sun | 2 | 1 | 3.08 |
Hailiang Xu | 3 | 8 | 2.22 |
Palaiahnakote Shivakumara | 4 | 774 | 64.90 |
Feng Su | 5 | 170 | 18.63 |
tong lu | 6 | 372 | 67.17 |
Ruoyu Yang | 7 | 0 | 2.03 |