An image structure model for exact edge detection
This provides a foundational improvement for image processing pipelines, benefiting tasks like denoising, filtering, and neural network training.
The paper tackles the problem of low-level image interpretation by introducing a new model that decomposes images into a graph to capture structural features, enabling exact edge detection with subpixel precision and outperforming classical and state-of-the-art methods.
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.