Abstract | ||
---|---|---|
•We describe SnooperText, a new text detector specialized for photos of urban scenes.•Candidate characters are found by toggle segmentation and winnowed by shape descriptors.•Candidate characters are validated by a HOG-based descriptor.•SnooperText is better or at least as accurate and robust as other state-of-the-art detectors on standard benchmarks.•SnooperText was used in iTowns, a prototype system for virtual street-level urban navigation. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.cviu.2013.10.004 | Computer Vision and Image Understanding |
Keywords | DocType | Volume |
Text detection,Text region classification,Histogram of oriented gradients for text,Text descriptor,Textual indexing in urban scene images | Journal | 122 |
Issue | ISSN | Citations |
1 | 1077-3142 | 24 |
PageRank | References | Authors |
0.70 | 30 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rodrigo Minetto | 1 | 178 | 15.01 |
Nicolas Thome | 2 | 464 | 30.22 |
Matthieu Cord | 3 | 1038 | 79.86 |
Neucimar J. Leite | 4 | 104 | 7.89 |
Jorge Stolfi | 5 | 1559 | 296.06 |