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.
Abstract (translated)
本文提出了一种新的单通道图像低层解释模型。图像被分解成一个图表,它捕获一组完整的结构特征。该描述允许准确识别每个边缘位置及其正确的连接。该方法的主要特点是:边缘的矢量描述、亚像素精度和底层算法的并行性。在概念和实验层面上,该方法优于经典和最先进的边缘检测器。它还支持基于图形的高级特征提取算法。任何图像处理管道都可以从这些结果中获益:例如,受控去噪、边缘保持过滤、上采样、压缩、基于矢量和图形的模式匹配、神经网络培训。
URL
https://arxiv.org/abs/1904.09659