S
Shiqian Wu
Researcher at Wuhan University of Science and Technology
Publications - 214
Citations - 5104
Shiqian Wu is an academic researcher from Wuhan University of Science and Technology. The author has contributed to research in topics: Pixel & Facial recognition system. The author has an hindex of 27, co-authored 176 publications receiving 4372 citations. Previous affiliations of Shiqian Wu include Information Technology University & Wuhan University.
Papers
More filters
Journal ArticleDOI
Face recognition with radial basis function (RBF) neural networks
TL;DR: A novel paradigm is proposed whereby data information is encapsulated in determining the structure and initial parameters of the RBF neural classifier before learning takes place, and the dimension of the search space is drastically reduced in the gradient paradigm.
Journal ArticleDOI
Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain
W. Chen,Meng Joo Er,Shiqian Wu +2 more
TL;DR: A novel illumination normalization approach for face recognition under varying lighting conditions using a discrete cosine transform to compensate for illumination variations in the logarithm domain that is easily implemented in a real-time face recognition system.
Journal ArticleDOI
Dynamic fuzzy neural networks-a novel approach to function approximation
Shiqian Wu,Meng Joo Er +1 more
TL;DR: Simulation studies and comprehensive comparisons with some other learning algorithms demonstrate that a more compact structure with higher performance can be achieved by the proposed approach.
Journal ArticleDOI
Weighted guided image filtering.
TL;DR: Experimental results show that the resultant algorithms produce images with better visual quality and at the same time halo artifacts can be reduced/avoided from appearing in the final images with negligible increment on running times.
Journal ArticleDOI
A fast approach for automatic generation of fuzzy rules by generalized dynamic fuzzy neural networks
Shiqian Wu,Meng Joo Er,Yang Gao +2 more
TL;DR: Comprehensive comparisons with other latest approaches show that the proposed approach is superior in terms of learning efficiency and performance.