ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

TL;DR

ABCNet v2 introduces an adaptive Bezier curve approach for real-time, end-to-end text spotting of arbitrarily-shaped text, improving accuracy and simplicity over previous segmentation-based methods.

Contribution

The paper presents a novel Bezier curve fitting method, a BezierAlign layer, and a coordinate convolution technique, enabling structured, accurate, and efficient text detection and recognition.

Findings

Achieves state-of-the-art performance on bilingual datasets.

Maintains high efficiency with a simple pipeline.

Significantly improves recognition precision over previous methods.

Abstract

End-to-end text-spotting, which aims to integrate detection and recognition in a unified framework, has attracted increasing attention due to its simplicity of the two complimentary tasks. It remains an open problem especially when processing arbitrarily-shaped text instances. Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output. Here, we tackle end-to-end text spotting by presenting Adaptive Bezier Curve Network v2 (ABCNet v2). Our main contributions are four-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve, which, compared with segmentation-based methods, can not only provide structured output but also controllable representation. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance of arbitrary shapes, significantly improving the precision of recognition over previous methods. 3) Different from previous methods, which often suffer from complex post-processing and sensitive hyper-parameters, our ABCNet v2 maintains a simple pipeline with the only post-processing non-maximum suppression (NMS). 4) As the performance of text recognition closely depends on feature alignment, ABCNet v2 further adopts a simple yet effective coordinate convolution to encode the position of the convolutional filters, which leads to a considerable improvement with negligible computation overhead. Comprehensive experiments conducted on various bilingual (English and Chinese) benchmark datasets demonstrate that ABCNet v2 can achieve state-of-the-art performance while maintaining very high efficiency.