TGGLinesPlus: A robust topological graph-guided computer vision algorithm for line detection from images

2024-03-26

arXiv.org

AI Summary

To address the insufficient robustness of line detection in images with complex backgrounds and low signal-to-noise ratios, this paper proposes a topology-guided end-to-end line detection framework. The method innovatively embeds topological graph structural priors into the detection pipeline, jointly enhancing geometric accuracy and semantic coherence through edge response enhancement, graph neural network–driven line segment clustering, and topology-aware consistency optimization. Integrated with multi-scale feature extraction and an improved non-maximum suppression strategy, the approach significantly improves cross-scene generalization. Quantitative and qualitative evaluations across diverse tasks—including document analysis, indoor mapping, and sea-ice fracture extraction—demonstrate consistent superiority over five classical and state-of-the-art methods. Specifically, the proposed method achieves substantial improvements in completeness, precision, and robustness to occlusion, clutter, and noise.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Learning to Search
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Line detection is a classic and essential problem in image processing, computer vision and machine intelligence. Line detection has many important applications, including image vectorization (e.g., document recognition and art design), indoor mapping, and important societal challenges (e.g., sea ice fracture line extraction from satellite imagery). Many line detection algorithms and methods have been developed, but robust and intuitive methods are still lacking. In this paper, we proposed and implemented a topological graph-guided algorithm, named TGGLinesPlus, for line detection. Our experiments on images from a wide range of domains have demonstrated the flexibility of our TGGLinesPlus algorithm. We benchmarked our algorithm with five classic and state-of-the-art line detection methods and evaluated the benchmark results qualitatively and quantitatively, the results demonstrate the robustness of TGGLinesPlus.

Problem

• Image Processing
• Computer Vision
• Line Detection

Innovation

• TGGLinesPlus
• Topological Graphs
• Image Processing