Real-time Scene Text Detection with Differentiable Binarization

20 Nov 2019  ·  Minghui Liao, Zhaoyi Wan, Cong Yao, Kai Chen, Xiang Bai ·

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:

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Scene Text Detection ICDAR 2015 DB-ResNet-50 (1152) F-Measure 87.3 # 13
Precision 91.8 # 5
Recall 83.2 # 21
Scene Text Detection MSRA-TD500 DB-ResNet-50 (736) Recall 79.2 # 7
Precision 91.5 # 1
F-Measure 84.9 # 6
Scene Text Detection SCUT-CTW1500 DB-ResNet50 (1024) F-Measure 83.4 # 5
Scene Text Detection Total-Text DB-ResNet-50 (800) F-Measure 84.7% # 11