Edge detection technology aims to identify and extract the boundary information of image pixel mutation, which is a research hotspot in the field of computer vision. This technology has been widely used in image segmentation, target detection, and other high-level image processing technologies. In recent years, considering the problems of thick image edge contour, inaccurate positioning, and poor detection accuracy, researchers have proposed a variety of edge detection algorithms based on deep learning, such as multi-scale feature fusion, codec, network reconstruction, and so on. This paper dedicates to making a comprehensive analysis and special research on the edge detection algorithms. Firstly, by classifying the multi-level structure of traditional edge detection algorithms, the theory and method of each algorithm are introduced. Secondly, through focusing on the edge detection algorithm based on deep learning, the technical difficulties, advantages of methods, and backbone network selection of each algorithm are analysed. Then, through the experiments on the BSDS500 and NYUD dataset, the performance of each algorithm is further evaluated. It can be seen that the performance of the current edge detection algorithms is close to or even beyond the human visual level. At present, there are a few comprehensive review articles on image edge detection. This paper dedicates to making a comprehensive analysis of edge detection technology and aims to offer reference and guidance for the relevant personnel to follow up easily the current developments of edge detection and to make further improvements and innovations.

No abstract

Ultrafine-grained die-upset Nd-Fe-B magnets are of importance because they provide a wide researching space to redesign the textured structures. Here is presented a route to obtain a new die-upset magnet with substantially improved magnetic properties. After experiencing the optimized heat treatment, both the coercivity and remanent magnetization of the Dy-Cu press injected magnets increased substantially in comparison with those of the annealed reference magnets, which is distinct from the reported experimental results on heavy rare-earth diffusion. To study the mechanism, we analyzed the texture evolution in high-temperature annealed die-upset magnets, which had significant impact on the improvement of remanent magnetization. On basis of the results, we find that the new structures are strongly interlinked with the initial structures. With injecting Dy-Cu eutectic alloy, an optimized initial microstructure was achieved in the near-surface diffused regions, which made preparations for the subsequent texture improvement. Besides, the Dy gradient distribution of near-surface regions of the Dy-Cu press injected magnets was also investigated. By controlling the initial microstructure and subsequent diffusion process, a higher performance magnet is expected to be obtained.

No abstract

No abstract