Rethinking Irregular Scene Text Recognition
arXiv:1908.11834
Abstract
Reading text from natural images is challenging due to the great variety in text font, color, size, complex background and etc.. The perspective distortion and non-linear spatial arrangement of characters make it further difficult. While rectification based method is intuitively grounded and has pushed the envelope by far, its potential is far from being well exploited. In this paper, we present a bag of tricks that prove to significantly improve the performance of rectification based method. On curved text dataset, our method achieves an accuracy of 89.6% on CUTE-80 and 76.3% on Total-Text, an improvement over previous state-of-the-art by 6.3% and 14.7% respectively. Furthermore, our combination of tricks helps us win the ICDAR 2019 Arbitrary-Shaped Text Challenge (Latin script), achieving an accuracy of 74.3% on the held-out test set. We release our code as well as data samples for further exploration at https://github.com/Jyouhou/ICDAR2019-ArT-Recognition-Alchemy
arXiv commentTechnical report for participation in ICDAR2019-ArT recognition track
References in corpus (9)
- Sequence to Sequence Learning with Neural Networks
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- 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
- Scene Text Detection and Recognition: The Deep Learning Era
- Scene Text Recognition with Sliding Convolutional Character Models
- Reading Scene Text with Attention Convolutional Sequence Modeling
- SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds