Edge Approximation Text Detector

2025-04-05

AI Summary

Irregular scene text detection suffers from coarse contour representation and complex reconstruction pipelines. To address these issues, this paper proposes EdgeText, which models text contours as a continuous, smooth parametric edge curve fitting problem. EdgeText achieves compact and efficient reconstruction through three core components: center-point localization, edge function generation, and truncation point prediction. It is the first method to formalize text detection as an edge approximation task. We introduce a Bilateral Enhancement Perception (BEP) module to strengthen edge-aware feature representation, and propose a Proportional-Integral loss (PI-loss) to improve parameter convergence and multi-scale robustness of the fitted curves. Extensive experiments demonstrate that EdgeText achieves state-of-the-art performance on multiple benchmarks, significantly improving detection accuracy for irregular text while simplifying the reconstruction pipeline and reducing model complexity.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Computer Vision: Representation Learning for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Pursuing efficient text shape representations helps scene text detection models focus on compact foreground regions and optimize the contour reconstruction steps to simplify the whole detection pipeline. Current approaches either represent irregular shapes via box-to-polygon strategy or decomposing a contour into pieces for fitting gradually, the deficiency of coarse contours or complex pipelines always exists in these models. Considering the above issues, we introduce EdgeText to fit text contours compactly while alleviating excessive contour rebuilding processes. Concretely, it is observed that the two long edges of texts can be regarded as smooth curves. It allows us to build contours via continuous and smooth edges that cover text regions tightly instead of fitting piecewise, which helps avoid the two limitations in current models. Inspired by this observation, EdgeText formulates the text representation as the edge approximation problem via parameterized curve fitting functions. In the inference stage, our model starts with locating text centers, and then creating curve functions for approximating text edges relying on the points. Meanwhile, truncation points are determined based on the location features. In the end, extracting curve segments from curve functions by using the pixel coordinate information brought by truncation points to reconstruct text contours. Furthermore, considering the deep dependency of EdgeText on text edges, a bilateral enhanced perception (BEP) module is designed. It encourages our model to pay attention to the recognition of edge features. Additionally, to accelerate the learning of the curve function parameters, we introduce a proportional integral loss (PI-loss) to force the proposed model to focus on the curve distribution and avoid being disturbed by text scales.

Problem

• Efficient text shape representation for scene text detection
• Compact contour reconstruction to simplify detection pipeline
• Parameterized curve fitting for accurate text edge approximation

Innovation

• EdgeText fits text contours via smooth curves
• Bilateral enhanced perception module enhances edge recognition
• Proportional integral loss accelerates curve parameter learning