Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling

TL;DR

This paper introduces IATS, an end-to-end framework for scene text spotting that effectively handles inverse-like texts with complex layouts by estimating reading order and dynamically sampling features, improving accuracy on challenging datasets.

Contribution

The paper proposes a novel reading-order estimation module and a dynamic sampling module within an end-to-end trainable framework for inverse-like scene text spotting, addressing complex text layouts.

Findings

Achieves superior performance on inverse-like and irregular scene text datasets.

Effectively handles mirrored, symmetrical, and retro-flexed texts.

Outperforms existing methods in challenging text spotting scenarios.

Abstract

Scene text spotting is a challenging task, especially for inverse-like scene text, which has complex layouts, e.g., mirrored, symmetrical, or retro-flexed. In this paper, we propose a unified end-to-end trainable inverse-like antagonistic text spotting framework dubbed IATS, which can effectively spot inverse-like scene texts without sacrificing general ones. Specifically, we propose an innovative reading-order estimation module (REM) that extracts reading-order information from the initial text boundary generated by an initial boundary module (IBM). To optimize and train REM, we propose a joint reading-order estimation loss consisting of a classification loss, an orthogonality loss, and a distribution loss. With the help of IBM, we can divide the initial text boundary into two symmetric control points and iteratively refine the new text boundary using a lightweight boundary refinement module (BRM) for adapting to various shapes and scales. To alleviate the incompatibility between text detection and recognition, we propose a dynamic sampling module (DSM) with a thin-plate spline that can dynamically sample appropriate features for recognition in the detected text region. Without extra supervision, the DSM can proactively learn to sample appropriate features for text recognition through the gradient returned by the recognition module. Extensive experiments on both challenging scene text and inverse-like scene text datasets demonstrate that our method achieves superior performance both on irregular and inverse-like text spotting.