Y
Yonghuai Liu
Researcher at Edge Hill University
Publications - 200
Citations - 3700
Yonghuai Liu is an academic researcher from Edge Hill University. The author has contributed to research in topics: Real image & Image registration. The author has an hindex of 23, co-authored 189 publications receiving 2770 citations. Previous affiliations of Yonghuai Liu include Sainsbury Laboratory & University of Sheffield.
Papers
More filters
Journal ArticleDOI
Structure and Illumination Constrained GAN for Medical Image Enhancement.
Yuhui Ma,Jiang Liu,Yonghuai Liu,Huazhu Fu,Yan Hu,Jun Cheng,Hong Qi,Yufei Wu,Jiong Zhang,Yitian Zhao +9 more
TL;DR: Inspired by CycleGAN based on the global constraints of the adversarial loss and cycle consistency, the proposed CSI-GAN treats low and high quality images as those in two domains and computes local structure and illumination constraints for learning both overall characteristics and local details.
Journal ArticleDOI
Saliency driven vasculature segmentation with infinite perimeter active contour model
Yitian Zhao,Jingliang Zhao,Jian Yang,Yonghuai Liu,Yifan Zhao,Yalin Zheng,Likun Xia,Yongtian Wang +7 more
TL;DR: A new framework for precisely segmenting retinal vasculatures is proposed, adapted to the Retinex theory, and shows that the model outperforms its competitors.
Book ChapterDOI
Retinal Artery and Vein Classification via Dominant Sets Clustering-Based Vascular Topology Estimation
TL;DR: A novel framework that is capable of making the artery/vein (A/V) distinction in retinal color fundus images is proposed and the concept of dominant sets clustering is adapted and formalize the retinal vessel topology estimation and the A/V classification problem as a pairwise clustering problem.
Journal ArticleDOI
Automatic 3d free form shape matching using the graduated assignment algorithm
TL;DR: The experimental results based on both synthetic data and real images without any pre-processing show the effectiveness and efficiency of the proposed algorithm for the automatic matching of overlapping 3D free form shapes with either sparse or dense points.
Journal ArticleDOI
Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views
TL;DR: A new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial) was introduced outperforming several state-of-the-art competing methods.