ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network

By Yuliang Liu, Hao Chen, Chunhua Shen, Tong He, Lianwen Jin, Liangwei Wang. Computer Vision and Pattern Recognition, 2020

402 citations recorded by the source corpus.

Scene text detection and recognition has received increasing research attention. Existing methods can be roughly categorized into two groups: character-based and segmentation-based. These methods either are costly for character annotation or need to maintain a complex pipeline, which is often not suitable for real-time applications. Here we address the problem by proposing the Adaptive Bezier-Curve Network (\BeCan). Our contributions are three-fold: 1) For the first time, we adaptively fit oriented or curved text by a parameterized Bezier curve. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods. 3) Compared with standard bounding box detection, our Bezier curve detection introduces negligible computation overhead, resulting in superiority of our method in both efficiency and accuracy. Experiments on oriented or curved benchmark datasets, namely Total-Text and CTW1500, demonstrate that \BeCan achieves state-of-the-art accuracy, meanwhile significantly improving the speed. In particular, on Total-Text, our real-time version is over 10 times faster than recent state-of-the-art methods with a competitive recognition accuracy. Code is available at \url{https://git.io/AdelaiDet}.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3da15c04db020c629aeb71b856cfdc7127b677ff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Mingkui Tan
2. Qi Wu
3. Sangdoo Yun
4. Shuaicheng Niu
5. Dongyoon Han
6. Qing Du
7. Guanghui Xu
8. JeongYeon Nam

Citations in the corpus

• OCR-Free Document Understanding Transformer (2021, methodology): “If we train an OCR model, it also requires extensive training costs and large-scale datasets [4,3,39,46].”
• MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression (2023, methodology): “In order to solve the problem of arbitrary shape scene text detection and recognition, ABCNet [28] and its improved version ABCNet v2 [29] use the BezierAlign to transform the arbitrary-shape texts into regular ones.”
• FCOS: A Simple and Strong Anchor-Free Object Detector (2020, neutral): “More importantly, due to its simple design, FCOS can be easily extended to solve other instance-level recognition tasks with minimal modification, as already evidenced by instance segmentation [2], [20], [47], [51], keypoint detection [39], text spotting [26], and tracking [13], [44].”
• Towards Accurate Text-based Image Captioning with Content Diversity Exploration (2021, background): “Recently, M4CCaptioner [40] tries to use additional OCR tools [4, 6, 31] to recognise texts in images.”
• Confidence-aware Non-repetitive Multimodal Transformers for TextCaps (2020, neutral): “2019b) and ABCNet (Liu et al. 2020) for text detection, and four-stage STR (Baek et al.”