Q
Qing Liu
Researcher at Central South University
Publications - 32
Citations - 331
Qing Liu is an academic researcher from Central South University. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 7, co-authored 32 publications receiving 193 citations. Previous affiliations of Qing Liu include Chinese Ministry of Education & University of Oulu.
Papers
More filters
Journal ArticleDOI
A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images.
Qing Liu,Qing Liu,Qing Liu,Beiji Zou,Beiji Zou,Jie Chen,Wei Ke,Kejuan Yue,Zailiang Chen,Zailiang Chen,Guoying Zhao +10 more
TL;DR: The experimental results show that the proposed location-to-segmentation strategy achieves 76% in sensitivity and 75% in positive prediction value (PPV), which both outperform the state of the art methods significantly.
Journal ArticleDOI
A Spatial-aware Joint Optic Disc and Cup Segmentation Method
TL;DR: A spatial-aware joint segmentation method by explicitly considering the spatial locations of the pixels and learning the multi-scale spatially dense features is proposed, and high correlation between the cup-to-disk values and the risks of the glaucoma is validated on the dataset ORIGA.
Journal ArticleDOI
Hierarchical Contour Closure-Based Holistic Salient Object Detection
TL;DR: This work proposes a hierarchical contour closure-based holistic salient object detection method, in which two saliency cues, i.e., closure completeness and closure reliability, are thoroughly exploited, and proposes a framework to combine the twoSaliency maps, obtaining the final saliency map.
Journal ArticleDOI
Automatic microaneurysm detection in fundus image based on local cross-section transformation and multi-feature fusion
TL;DR: The proposed local cross-section transformation enhances the discrimination of descriptors by amplifying difference between MAs and confusing structures, which facilitates the classification and improves the detection performances.
Journal ArticleDOI
Improved multi-scale line detection method for retinal blood vessel segmentation
TL;DR: An improved multi-scale line detector to segment retinal vessels is proposed that computes the line responses of vessels in multi- scale windows and takes the maximum as the response value, which can enhance the responses of pale vessel pixels near strong vessels or dark background pixels.