Tian-Hui Ma

Dr. Tian-Hui Ma


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
Xi-Le ZhaoXi-Le Zhao
Xi-Le Zhao
JYJinghua Yang
Jinghua Yang
TMTian-Hui Ma
Tian-Hui Ma
TJTai-Xiang Jiang
Tai-Xiang Jiang
MNMichael NG
Michael NG
THTing-Zhu Huang
Ting-Zhu Huang
Completing missing entries in multidimensional visual data is a typical ill-posed problem that requires appropriate exploitation of prior information of the underlying data. Commonly used priors can be roughly categorized into three classes: global tensor low-rankness, local properties, and nonlocal self-similarity (NSS); most existing works utilize one or two of them to implement completion. Naturally, there arises an interesting question: can one concurrently make use of multiple priors in a unified way, such that they can collaborate with each other to achieve better performance? This work gives a positive answer by formulating a novel tensor completion framework which can simultaneously take advantage of the global-local-nonlocal priors. In the proposed framework, the tensor train (TT) rank is adopted to characterize the global correlation; meanwhile, two Plug-and-Play (PnP) denoisers, including a convolutional neural network (CNN) denoiser and the color block-matching and 3 D filtering (CBM3D) denoiser, are incorporated to preserve local details and exploit NSS, respectively. Then, we design a proximal alternating minimization algorithm to efficiently solve this model under the PnP framework. Under mild conditions, we establish the convergence guarantee of the proposed algorithm. Extensive experiments show that these priors organically benefit from each other to achieve state-of-the-art performance both quantitatively and qualitatively.

5 January 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YLYun-Yang Liu
Yun-Yang Liu
Xi-Le ZhaoXi-Le Zhao
Xi-Le Zhao
Yu-Bang ZhengYu-Bang Zheng
Yu-Bang Zheng
TMTian-Hui Ma
Tian-Hui Ma
HZHongyan Zhang
Hongyan Zhang
Hyperspectral images (HSIs) are often contaminated by several types of noise, which significantly limits the accuracy of subsequent applications. Recently, low-rank modeling based on tensor singular value decomposition (T-SVD) has achieved great success in HSI restoration. Most of them use the convex and nonconvex surrogates of the tensor rank, which cannot well approximate the tensor singular values and obtain suboptimal restored results. We suggest a novel HSI restoration model by introducing a fibered rank constrained tensor restoration framework with an embedded plug-and-play (PnP)-based regularization (FRCTR-PnP). More precisely, instead of using the convex and nonconvex surrogates to approximate the fibered rank, the proposed model directly constrains the tensor fibered rank of the solution, leading to a better approximation to the original image. Since exploiting the low-fibered-rankness of HSI is mainly to capture the global structure, we further employ an implicit PnP-based regularization to preserve the image details. Particularly, the above two building blocks are complementary to each other, rather than isolated and uncorrelated. Based on the alternating direction multiplier method (ADMM), we propose an efficient algorithm to tackle the proposed model. For robustness, we develop a three-directional randomized T-SVD (3DRT-SVD), which preserves the intrinsic structure of the clean HSI and removes partial noise by projecting the HSI onto a low-dimensional essential subspace. Extensive experimental results including simulated and real data demonstrate that the proposed method achieves superior performance over compared methods in terms of quantitative evaluation and visual inspection.

2 October 2019 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Closed access
JWJian-Li Wang
Jian-Li Wang
THTing-Zhu Huang
Ting-Zhu Huang
Xi-Le ZhaoXi-Le Zhao
Xi-Le Zhao
JHJie Huang
Jie Huang
TMTian-Hui Ma
Tian-Hui Ma
Yu-Bang ZhengYu-Bang Zheng
Yu-Bang Zheng
Destriping has attracted a lot of interest in the field of remote sensing images processing. Recent research works consider the characteristics of stripes, among which low-rankness and group sparsity regularizations are widely used. However, for real scenarios, these regularizations sometimes fail to work when the underlying assumptions are violated. Motivated by this observation, we propose a novel and flexible regularization, named as the reweighted block sparsity (RBS), for complex stripes (e.g., the partial stripes). RBS divides the stripe layer into several blocks along the stripe-perpendicular direction and boosts the group sparsity of each block, where the sparsity level is adaptively controlled by updating weights. Based on RBS, we further propose a destriping model by integrating RBS and unidirectional total variation regularization, which can better detect and remove complex stripes. Moreover, we develop an alternating direction method of multipliers algorithm to solve the proposed model. Experimental results demonstrate that the proposed method outperforms the state-of-the-art competitors qualitatively and quantitatively.

1 January 2021 in Inverse Problems and Imaging
Verified
Journal Article
Closed access
PDF file
MDMeng Ding
Meng Ding
THTing-Zhu Huang
Ting-Zhu Huang
Xi-Le ZhaoXi-Le Zhao
Xi-Le Zhao
MNMichael NG
Michael NG
TMTian-Hui Ma
Tian-Hui Ma
The tensor train (TT) rank has received increasing attention in tensor completion due to its ability to capture the global correlation of high-order tensors ($ \rm{order} >3 $). For third order visual data, direct TT rank minimization has not exploited the potential of TT rank for high-order tensors. The TT rank minimization accompany with ket augmentation, which transforms a lower-order tensor (e.g., visual data) into a higher-order tensor, suffers from serious block-artifacts. To tackle this issue, we suggest the TT rank minimization with nonlocal self-similarity for tensor completion by simultaneously exploring the spatial, temporal/spectral, and nonlocal redundancy in visual data. More precisely, the TT rank minimization is performed on a formed higher-order tensor called group by stacking similar cubes, which naturally and fully takes advantage of the ability of TT rank for high-order tensors. Moreover, the perturbation analysis for the TT low-rankness of each group is established. We develop the alternating direction method of multipliers tailored for the specific structure to solve the proposed model. Extensive experiments demonstrate that the proposed method is superior to several existing state-of-the-art methods in terms of both qualitative and quantitative measures.

1 November 2019 in Applied Mathematics and Computation
Verified
Journal Article
Closed access
JWJian-Li Wang
Jian-Li Wang
THTing-Zhu Huang
Ting-Zhu Huang
TMTian-Hui Ma
Tian-Hui Ma
Xi-Le ZhaoXi-Le Zhao
Xi-Le Zhao
Yong ChenYong Chen
Yong Chen

1 January 2017 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
TJTai-Xiang Jiang
Tai-Xiang Jiang
THTing-Zhu Huang
Ting-Zhu Huang
XZXi-Le Zhao
Xi-Le Zhao
TMTian-Hui Ma
Tian-Hui Ma
We have proposed a patch-based principal component analysis (PCA) method to deal with face recognition. Many PCA-based methods for face recognition utilize the correlation between pixels, columns, or rows. But the local spatial information is not utilized or not fully utilized in these methods. We believe that patches are more meaningful basic units for face recognition than pixels, columns, or rows, since faces are discerned by patches containing eyes and noses. To calculate the correlation between patches, face images are divided into patches and then these patches are converted to column vectors which would be combined into a new “image matrix.” By replacing the images with the new “image matrix” in the two-dimensional PCA framework, we directly calculate the correlation of the divided patches by computing the total scatter. By optimizing the total scatter of the projected samples, we obtain the projection matrix for feature extraction. Finally, we use the nearest neighbor classifier. Extensive experiments on the ORL and FERET face database are reported to illustrate the performance of the patch-based PCA. Our method promotes the accuracy compared to one-dimensional PCA, two-dimensional PCA, and two-directional two-dimensional PCA.