ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network

TL;DR

ABCNet introduces an adaptive Bezier-curve approach for real-time scene text detection and recognition, achieving high accuracy and efficiency on arbitrary-shaped text datasets, suitable for practical applications.

Contribution

The paper presents the first adaptive Bezier-curve fitting for arbitrarily-shaped text, a novel BezierAlign layer for feature extraction, and demonstrates real-time performance with state-of-the-art accuracy.

Findings

Achieves state-of-the-art accuracy on Total-Text and CTW1500 datasets.

Real-time version is over 10 times faster than recent methods.

Maintains high recognition accuracy with negligible computational overhead.

Abstract

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 (ABCNet). Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped 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 arbitrarily-shaped benchmark datasets, namely Total-Text and CTW1500, demonstrate that ABCNet achieves state-of-the-art accuracy, meanwhile significantly improving the speed. In particular, on Total-Text, our realtime version is over 10 times faster than recent state-of-the-art methods with a competitive recognition accuracy. Code is available at https://tinyurl.com/AdelaiDet