J
Jing Tian
Researcher at National University of Singapore
Publications - 180
Citations - 2714
Jing Tian is an academic researcher from National University of Singapore. The author has contributed to research in topics: Wavelet & Image restoration. The author has an hindex of 21, co-authored 175 publications receiving 2212 citations. Previous affiliations of Jing Tian include Institute for Infocomm Research Singapore & South China University of Technology.
Papers
More filters
Journal ArticleDOI
A survey on super-resolution imaging
Jing Tian,Kai-Kuang Ma +1 more
TL;DR: This paper provides a comprehensive review of SR image and video reconstruction methods developed in the literature and highlights the future research challenges.
Proceedings ArticleDOI
An ant colony optimization algorithm for image edge detection
Jing Tian,Weiyu Yu,Shengli Xie +2 more
TL;DR: The proposed ACO-based edge detection approach is able to establish a pheromone matrix that represents the edge information presented at each pixel position of the image, according to the movements of a number of ants which are dispatched to move on the image.
Journal ArticleDOI
Adaptive multi-focus image fusion using a wavelet-based statistical sharpness measure
Jing Tian,Li Chen +1 more
TL;DR: A new statistical sharpness measure is proposed by exploiting the spreading of the wavelet coefficients distribution to measure the degree of the image's blur and is exploited to perform adaptive image fusion in wavelet domain.
Journal ArticleDOI
Multi-focus image fusion using a bilateral gradient-based sharpness criterion
TL;DR: A new bilateral sharpness criterion is proposed to exploit both the strength and the phase coherence that are evaluated using the gradient information of the images to perform weighted aggregation of multi-focus images.
Journal ArticleDOI
An adaptive unsupervised approach toward pixel clustering and color image segmentation
TL;DR: Compared with classical segmentation algorithms such as mean shift and normalized cut, the proposed adaptive unsupervised scheme could generate reasonably good or better image partitioning, which illustrates the method's practical value.