Explicit Relational Reasoning Network for Scene Text Detection

2024-12-19

AI Summary

Existing connected-component (CC)-based scene text detection methods rely on time-consuming post-processing, hindering end-to-end efficiency. This work reformulates text detection as an end-to-end tracking problem over ordered text components—eliminating post-processing entirely. To this end, we propose the Explicit Relation Reasoning Network (ERRNet), establishing the first tracking-based paradigm for CC-based detection. We further introduce Polygon Monte-Carlo localization quality assessment and position-supervised classification loss to tightly align detection outputs with tracking objectives. Our method integrates component sequence modeling, a differentiable tracking decoder, and geometry-aware localization supervision. Evaluated on standard benchmarks—including ICDAR2015, CTW1500, and Total-Text—our approach achieves state-of-the-art accuracy while significantly outperforming mainstream CC-based methods in inference speed.

Technology Category

• Computer Vision: Motion & Tracking
• Reasoning under Uncertainty: Relational Probabilistic Models
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmental bottleneck that their time-consuming post-processing is difficult to eliminate. To address this issue, we introduce an explicit relational reasoning network (ERRNet) to elegantly model the component relationships without post-processing. Concretely, we first represent each text instance as multiple ordered text components, and then treat these components as objects in sequential movement. In this way, scene text detection can be innovatively viewed as a tracking problem. From this perspective, we design an end-to-end tracking decoder to achieve a CC-based method dispensing with post-processing entirely. Additionally, we observe that there is an inconsistency between classification confidence and localization quality, so we propose a Polygon Monte-Carlo method to quickly and accurately evaluate the localization quality. Based on this, we introduce a position-supervised classification loss to guide the task-aligned learning of ERRNet. Experiments on challenging benchmarks demonstrate the effectiveness of our ERRNet. It consistently achieves state-of-the-art accuracy while holding highly competitive inference speed.

Problem

• Scene Text Recognition
• Connected Component Analysis
• Efficiency Optimization

Innovation

• ERRNet
• mobile components decoding
• fast accurate position judgment