Shuyou Zhang
Zhejiang University
137 Papers
195 Citations
Shuyou Zhang is an academic researcher from Zhejiang University. The author has contributed to research in topics: Computer science & Product design. The author has an hindex of 9, co-authored 101 publications.
Chat about Author
Papers
Non-rigid registration of biomedical image for radiotherapy based on adaptive feature density flow
TL;DR: In this paper, a non-rigid biomedical image registration method based on Adaptive Feature Density Flow (AFDF) is proposed for MRI image registration, where the deformation information and local shape information are homogeneous, so a flexible dimension of Fast Local Self-Similarity (FLSS) feature descriptor can be constructed to obtain adaptive FLSS feature descriptor with adaptive angle and radial intervals.
5
Blowhole Detection Based on Bidirectional Enhancement and Omnidirectional Analysis for X-Ray Inspection of Castings
TL;DR: Wang et al. as discussed by the authors proposed a blowhole detection method based on bidirectional enhancement and omnidirectional analysis for X-ray inspection of castings, which can detect small blurred blowholes.
Interruption performance design of variable freedom mechanism triggered by electro-mechanical-magnetic coupling
Jinghua Xu,Shuyou Zhang,Jianrong Tan,Sheng Hongsheng +3 more
- 01 Sep 2017
TL;DR: In this article, an interruption performance design method of variable freedom mechanism triggered by electro-magneto-thermo coupling is put forward, where the Euler-Lagrange partial differential equations are built using generalized coordinates.
5
Decompose image into meaningful regions based on contour detector and watershed algorithm
TL;DR: This work combines two methods to decompose images into meaningful regions, and proposes an index S-measure to measure the segmentation consistency between images, and shows that the decomposing is fast, effectively, meaningful, robustly, and coherently.
5
A Layered KNN-SVM Approach to Predict Missing Values of Functional Requirements in Product Customization
TL;DR: KNN-SVM outperforms other five single and five composite methods, with average reduction in root mean squared error (RMSE) of 39% and 21% against KNN and KNN-Tree, respectively.
5