SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition
arXiv:2005.13117
Abstract
Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including perspective distortions, line curvature or other style variations. Therefore, methods based on spatial transformers are extensively studied. However, chromatic difficulties in complex scenes have not been paid much attention on. In this work, we introduce a new learnable geometric-unrelated module, the Structure-Preserving Inner Offset Network (SPIN), which allows the color manipulation of source data within the network. This differentiable module can be inserted before any recognition architecture to ease the downstream tasks, giving neural networks the ability to actively transform input intensity rather than the existing spatial rectification. It can also serve as a complementary module to known spatial transformations and work in both independent and collaborative ways with them. Extensive experiments show that the use of SPIN results in a significant improvement on multiple text recognition benchmarks compared to the state-of-the-arts.
Accepted to AAAI21. Code is available at https://davar-lab.github.io/publication.html or https://github.com/hikopensource/DAVAR-Lab-OCR
References in corpus (7)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- ADADELTA: An Adaptive Learning Rate Method
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Focusing Attention: Towards Accurate Text Recognition in Natural Images
- Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
- 2D Attentional Irregular Scene Text Recognizer
- 2D-CTC for Scene Text Recognition