Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion

by   Minghui Liao, et al.

Recently, segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field, because of their superiority in detecting the text instances of arbitrary shapes and extreme aspect ratios, profiting from the pixel-level descriptions. However, the vast majority of the existing segmentation-based approaches are limited to their complex post-processing algorithms and the scale robustness of their segmentation models, where the post-processing algorithms are not only isolated to the model optimization but also time-consuming and the scale robustness is usually strengthened by fusing multi-scale feature maps directly. In this paper, we propose a Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network. Optimized along with the proposed DB module, the segmentation network can produce more accurate results, which enhances the accuracy of text detection with a simple pipeline. Furthermore, an efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively. By incorporating the proposed DB and ASF with the segmentation network, our proposed scene text detector consistently achieves state-of-the-art results, in terms of both detection accuracy and speed, on five standard benchmarks.


page 4

page 6

page 8

page 9

page 14

page 15


Real-time Scene Text Detection with Differentiable Binarization

Recently, segmentation-based methods are quite popular in scene text det...

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Scene text detection, an important step of scene text reading systems, h...

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

The prosperity of deep learning contributes to the rapid progress in sce...

Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection

Recently, transformer-based methods have achieved promising progresses i...

It's All About The Scale -- Efficient Text Detection Using Adaptive Scaling

"Text can appear anywhere". This property requires us to carefully proce...

On Exploring and Improving Robustness of Scene Text Detection Models

It is crucial to understand the robustness of text detection models with...

An Effective Pipeline for a Real-world Clothes Retrieval System

In this paper, we propose an effective pipeline for clothes retrieval sy...