Abstract | ||
---|---|---|
An end-to-end method for multi-language scene text localization, recognition and script identification is proposed. The approach is based on a set of convolutional neural nets. The method, called E2E-MLT, achieves state-of-the-art performance for both joint localization and script identification in natural images and in cropped word script identification. E2E-MLT is the first published multi-language OCR for scene text. The experiments show that obtaining accurate multi-language multi-script annotations is a challenging problem. |
Year | Venue | Field |
---|---|---|
2018 | ACCV Workshops | Pattern recognition,End-to-end principle,Computer science,Speech recognition,Artificial intelligence,Artificial neural network,Multi language |
DocType | Volume | Citations |
Journal | abs/1801.09919 | 1 |
PageRank | References | Authors |
0.35 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yash Patel | 1 | 9 | 4.28 |
Michal Busta | 2 | 19 | 1.30 |
Jiri Matas | 3 | 335 | 35.85 |