Abstract | ||
---|---|---|
An efficient method for text localization and recognition in real-world images is proposed. Thanks to effective pruning, it is able to exhaustively search the space of all character sequences in real time (200ms on a 640 × 480 image). The method exploits higher-order properties of text such as word text lines. We demonstrate that the grouping stage plays a key role in the text localization performance and that a robust and precise grouping stage is able to compensate errors of the character detector. The method includes a novel selector of Maximally Stable Extremal Regions (MSER) which exploits region topology. Experimental validation shows that 95.7% characters in the ICDAR dataset are detected using the novel selector of MSERs with a low sensitivity threshold. The proposed method was evaluated on the standard ICDAR 2003 dataset where it achieved state-of-the-art results in both text localization and recognition. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICDAR.2011.144 | Document Analysis and Recognition |
Keywords | Field | DocType |
object recognition,text analysis,ICDAR dataset,character detector,error compensation,grouping stage,maximally stable extremal regions,pruned exhaustive search,real-world images,region topology,text localization,text recognition,word text lines,real-world images,text localization,text-in-the-wild | Computer vision,Text mining,Brute-force search,Character recognition,Pattern recognition,Computer science,Robustness (computer science),Maximally stable extremal regions,Artificial intelligence,Detector,Text recognition,Cognitive neuroscience of visual object recognition | Conference |
ISSN | ISBN | Citations |
1520-5363 E-ISBN : 978-0-7695-4520-2 | 978-0-7695-4520-2 | 78 |
PageRank | References | Authors |
2.86 | 11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lukas Neumann | 1 | 555 | 18.65 |
Jiri Matas | 2 | 283 | 14.03 |