Real-time Scene Text Detection with Differentiable Binarization

By Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai. AAAI Conference on Artificial Intelligence, 2019

850 citations recorded by the source corpus.

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text. In this paper, we propose a module named Differentiable Binarization (DB), which can perform the binarization process in a segmentation network. Optimized along with a DB module, a segmentation network can adaptively set the thresholds for binarization, which not only simplifies the post-processing but also enhances the performance of text detection. Based on a simple segmentation network, we validate the performance improvements of DB on five benchmark datasets, which consistently achieves state-of-the-art results, in terms of both detection accuracy and speed. In particular, with a light-weight backbone, the performance improvements by DB are significant so that we can look for an ideal tradeoff between detection accuracy and efficiency. Specifically, with a backbone of ResNet-18, our detector achieves an F-measure of 82.8, running at 62 FPS, on the MSRA-TD500 dataset. Code is available at: https://github.com/MhLiao/DB.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/70d3f037dd66f0126b6acda066276f66e204f76b

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. Xiang Bai
2. Cong Yao
3. Minghui Liao
4. Junchi Yan
5. Kai Chen
6. Pengyuan Lyu
7. Xue Yang
8. Chunhua Shen

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Minghui Liao
4. Zhaoyi Wan
5. Pengyuan Lyu
6. Xue Yang
7. Kai Chen
8. Chengquan Zhang

Citations in the corpus

• MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining (2022, methodology): “7 million cropped images are collected from Book32 with the predicted bounding boxes yielded by DB4 [28].”
• TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models (2021, methodology): “The text detection task is usually considered as an object detection problem where conventional object detection models such as YoLOv5 and DBNet (Liao et al., 2019) can be applied.”
• Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion (2022, background): “This paper is an extension of its conference version DBNet [26].”
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection (2020, background): “Designed for general rotation detection, DAL does not specifically consider this situation, therefore, the naive model still cannot outperform current state-of-the-art approaches for scene text detection, such as DB (Liao et al. 2020).”
• MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, background): “Recent research focus has shifted to challenging arbitrary-shaped text detection [7, 12, 14, 19, 20].”