Abstract | ||
---|---|---|
•We train a Fully Convolutional Network (FCN) for text prediction in scene images and fuse it with a text proposal method.•Significantly higher recall rates than SoA text localization pipelines and better quality regions are obtained.•The resulting pipeline reduces the number of proposals resulting to a 4 × speed up compared with the baseline.•Our proposed method yields top performance when integrated in an end-to-end pipeline.•Analysis and results on standard datasets COCO-Text and ICDAR-Challenge 4 are reported. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.patrec.2017.08.030 | Pattern Recognition Letters |
Keywords | Field | DocType |
Text proposals,Fully convolutional networks,Scene text images | Signal processing,Noisy text analytics,Pattern recognition,Computer science,Software,Artificial intelligence,Recall,Text recognition,Machine learning,Speedup,Pruning | Journal |
Volume | ISSN | Citations |
119 | 0167-8655 | 2 |
PageRank | References | Authors |
0.36 | 32 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dena Bazazian | 1 | 8 | 2.89 |
Raul Gomez | 2 | 5 | 2.12 |
Anguelos Nicolaou | 3 | 104 | 10.14 |
Lluís Gómez | 4 | 93 | 8.74 |
Dimosthenis Karatzas | 5 | 406 | 38.13 |
Andrew D. Bagdanov | 6 | 861 | 52.78 |
Andrew D. Bagdanov | 7 | 861 | 52.78 |