RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
| Autor: | Zhanghui Kuang, Xiaoyu Yue, Chenhao Lin, Wayne Zhang, Hongbin Sun |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Feature vector Pattern recognition 02 engineering and technology Text recognition 010501 environmental sciences 01 natural sciences Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Encoder Decoding methods 0105 earth and related environmental sciences |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585280 ECCV (19) |
| DOI: | 10.1007/978-3-030-58529-7_9 |
| Popis: | The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts (e.g., random character sequences) which is unacceptable in most of real application scenarios. In this paper, we first deeply investigate the decoding process of the decoder. We empirically find that a representative character-level sequence decoder utilizes not only context information but also positional information. Contextual information, which the existing approaches heavily rely on, causes the problem of attention drift. To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition. Specifically, it contains a position aware module to enable the encoder to output feature vectors encoding their own spatial positions, and an attention module to estimate glimpses using the positional clue (i.e., the current decoding time step) only. The dynamic fusion is conducted for more robust feature via an element-wise gate mechanism. Theoretically, our proposed method, dubbed RobustScanner, decodes individual characters with dynamic ratio between context and positional clues, and utilizes more positional ones when the decoding sequences with scarce context, and thus is robust and practical. Empirically, it has achieved new state-of-the-art results on popular regular and irregular text recognition benchmarks while without much performance drop on contextless benchmarks, validating its robustness in both contextual and contextless application scenarios. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|