# An image structure model for exact edge detection

## TL;DR

This paper introduces a novel image structure model that accurately detects edges with subpixel precision, capturing complete structural features and enabling advanced image analysis and processing tasks.

## Contribution

The paper proposes a new graph-based model for edge detection that outperforms existing methods and facilitates higher-level image analysis.

## Key findings

- Outperforms classical and state-of-the-art edge detectors
- Provides vector description of edges with subpixel accuracy
- Enables graph-based higher-level feature extraction

## Abstract

The paper presents a new model for single channel images low-level interpretation. The image is decomposed into a graph which captures a complete set of structural features. The description allows to accurately identify every edge location and its correct connectivity. The key features of the method are: vector description of the edges, subpixel precision, and parallelism of the underlying algorithm. The methodology outperforms classical and state of the art edge detectors at both conceptual and experimental levels. It also enables graph based algorithms for higher-level feature extraction. Any image processing pipeline can benefit from such results: e.g., controlled denoising, edge preserving filtering, upsampling, compression, vector and graph based pattern matching, neural network training.