L
Leida Li
Researcher at Xidian University
Publications - 190
Citations - 3941
Leida Li is an academic researcher from Xidian University. The author has contributed to research in topics: Image quality & Computer science. The author has an hindex of 28, co-authored 150 publications receiving 2664 citations. Previous affiliations of Leida Li include Beijing Electronic Science and Technology Institute & China University of Mining and Technology.
Papers
More filters
Journal ArticleDOI
No-Reference Image Blur Assessment Based on Discrete Orthogonal Moments
TL;DR: The experimental results demonstrate that the proposed blind image blur evaluation algorithm can produce blur scores highly consistent with subjective evaluations and outperforms the state-of-the-art image blur metrics and several general-purpose no-reference quality metrics.
Journal ArticleDOI
A Fast Reliable Image Quality Predictor by Fusing Micro- and Macro-Structures
TL;DR: A new perceptual image quality assessment (IQA) metric based on the human visual system (HVS) is proposed that performs efficiently with convolution operations at multiscales, gradient magnitude, and color information similarity, and a perceptual-based pooling.
Proceedings ArticleDOI
MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment
TL;DR: Zhang et al. as mentioned in this paper proposed a no-reference IQA metric based on deep meta-learning, which learns the meta-knowledge shared by human when evaluating the quality of images with various distortions, which can then be adapted to unknown distortions easily.
Journal ArticleDOI
Enhanced Just Noticeable Difference Model for Images With Pattern Complexity
TL;DR: Considering both pattern complexity and luminance contrast, a novel spatial masking estimation function is deduced, and an improved JND estimation model is built, which performs highly consistent with the human perception.
Journal ArticleDOI
No-Reference and Robust Image Sharpness Evaluation Based on Multiscale Spatial and Spectral Features
TL;DR: The experimental results demonstrate that the proposed RISE metric is superior to the relevant state-of-the-art methods for evaluating both synthetic and real blurring and the proposed metric is robust, which means that it has very good generalization ability.