Skip to main content

Research Repository

Advanced Search

Outputs (29)

ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation (2024)
Journal Article
Li, Z., Zheng, Y., Shan, D., Yang, S., Li, Q., Wang, B., …Shen, D. (in press). ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation. IEEE Transactions on Medical Imaging, https://doi.org/10.1109/tmi.2024.3363190

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional la... Read More about ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation.

Using outlier elimination to assess learning-based correspondence matching methods (2024)
Journal Article
Ding, X., Luo, Y., Jie, B., Li, Q., & Cheng, Y. (2024). Using outlier elimination to assess learning-based correspondence matching methods. Information Sciences, 659, Article 120056. https://doi.org/10.1016/j.ins.2023.120056

Recently, deep learning (DL) technology has been widely used in correspondence matching. The learning-based models are usually trained on benign image pairs with partial overlaps. Since DL model is usually data-dependent, non-overlapping images may b... Read More about Using outlier elimination to assess learning-based correspondence matching methods.

LViT: Language meets Vision Transformer in Medical Image Segmentation (2023)
Journal Article
Li, Z., Li, Y., Li, Q., Wang, P., Guo, D., Lu, L., …Hong, Q. (2024). LViT: Language meets Vision Transformer in Medical Image Segmentation. IEEE Transactions on Medical Imaging, 43(1), 96-107. https://doi.org/10.1109/TMI.2023.3291719

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data due to the... Read More about LViT: Language meets Vision Transformer in Medical Image Segmentation.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification (2023)
Journal Article
Hong, Q., Lin, L., Li, Z., Li, Q., Yao, J., Wu, Q., …Tian, J. (in press). A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification. IEEE Transactions on Neural Networks and Learning Systems, https://doi.org/10.1109/TNNLS.2023.3280646

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification... Read More about A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Consensus Adversarial Defense Method Based on Augmented Examples (2022)
Journal Article
Ding, X., Cheng, Y., Luo, Y., Li, Q., & Gope, P. (2022). Consensus Adversarial Defense Method Based on Augmented Examples. IEEE Transactions on Industrial Informatics, https://doi.org/10.1109/TII.2022.3169973

Deep learning has been used in many computer-vision-based industrial Internet of Things applications. However, deep neural networks are vulnerable to adversarial examples that have been crafted specifically to fool a system while being imperceptible... Read More about Consensus Adversarial Defense Method Based on Augmented Examples.

High-quality vascular modeling and modification with implicit extrusion surfaces for blood flow computations (2020)
Journal Article
Hong, Q., Li, Q., Wang, B., Tian, J., Xu, F., Liu, K., & Cheng, X. (2020). High-quality vascular modeling and modification with implicit extrusion surfaces for blood flow computations. Computer Methods and Programs in Biomedicine, 196, Article 105598. https://doi.org/10.1016/j.cmpb.2020.105598

High-quality vascular modeling is crucial for blood flow simulations, i.e., computational fluid dynamics (CFD). As without an accurate geometric representation of the smooth vascular surface, it is impossible to make meaningful blood flow simulations... Read More about High-quality vascular modeling and modification with implicit extrusion surfaces for blood flow computations.

Fingerprint enhancement using multi-scale classification dictionaries with reduced dimensionality (2020)
Journal Article
Bian, W., Xu, D., Cheng, Y., Li, Q., Luo, Y., & Yu, Q. (2020). Fingerprint enhancement using multi-scale classification dictionaries with reduced dimensionality. IET Biometrics, 9(5), 194-204. https://doi.org/10.1049/iet-bmt.2019.0121

In order to improve the quality of fingerprint with large noise, this paper proposes a fingerprint enhancement method by using a sparse representation of learned multi-scale classification dictionaries with reduced dimensionality. Mul... Read More about Fingerprint enhancement using multi-scale classification dictionaries with reduced dimensionality.

Local keypoint-based Faster R-CNN (2020)
Journal Article
Ding, X., Li, Q., Cheng, Y., Wang, J., Bian, W., & Jie, B. (in press). Local keypoint-based Faster R-CNN. Applied Intelligence, https://doi.org/10.1007/s10489-020-01665-9

Region-based Convolutional Neural Network (R-CNN) detectors have achieved state-of-the-art results on various challenging benchmarks. Although R-CNN has achieved high detection performance, the research of local information in producing candidates is... Read More about Local keypoint-based Faster R-CNN.

Bio-AKA: An efficient fingerprint based two factor user authentication and key agreement scheme (2020)
Journal Article
Bian, W., Gope, P., Cheng, Y., & Li, Q. (2020). Bio-AKA: An efficient fingerprint based two factor user authentication and key agreement scheme. Future generations computer systems : FGCS, 109, 45-55. https://doi.org/10.1016/j.future.2020.03.034

The fingerprint has long been used as one of the most important biological features in the field of biometrics. It is person-specific and remain identical though out one’s lifetime. Physically uncloneable functions (PUFs) have been used in authentica... Read More about Bio-AKA: An efficient fingerprint based two factor user authentication and key agreement scheme.

Developing a Semantic-Driven Hybrid Segmentation Method for Point Clouds of 3D Shapes (2020)
Journal Article
Yang, X., Han, X., Li, Q., He, L., Pang, M., & Jia, C. (2020). Developing a Semantic-Driven Hybrid Segmentation Method for Point Clouds of 3D Shapes. IEEE Access, 8, 40861-40880. https://doi.org/10.1109/access.2020.2976847

With the rapid development of point cloud processing technologies and the availability of a wide range of 3D capturing devices, a geometric object from the real world can be directly represented digitally as a dense and fine point cloud. Decomposing... Read More about Developing a Semantic-Driven Hybrid Segmentation Method for Point Clouds of 3D Shapes.

Skeleton Marching-based Parallel Vascular Geometry Reconstruction Using Implicit Functions (2019)
Journal Article
Qi, Q., Li, Q. D., Cheng, Y., & Hong, Q. Q. (2020). Skeleton Marching-based Parallel Vascular Geometry Reconstruction Using Implicit Functions. International Journal of Automation and Computing, 17(1), 30-43. https://doi.org/10.1007/s11633-019-1189-4

Fast high-precision patient-specific vascular tissue and geometric structure reconstruction is an essential task for vascular tissue engineering and computer-aided minimally invasive vascular disease diagnosis and surgery. In this paper, we present a... Read More about Skeleton Marching-based Parallel Vascular Geometry Reconstruction Using Implicit Functions.

High precision implicit modeling for patient-specific coronary arteries (2019)
Journal Article
Hong, Q., Li, Q., Wang, B., Liu, K., & Qi, Q. (2019). High precision implicit modeling for patient-specific coronary arteries. IEEE Access, 7, 72020-72029. https://doi.org/10.1109/ACCESS.2019.2920113

High precision geometric reconstruction of patient-specific coronary arteries plays a crucial role in visual diagnosis, treatment decision-making, and the evaluation of the therapeutic effect of interventions in coronary artery diseases. It is also a... Read More about High precision implicit modeling for patient-specific coronary arteries.

A Survey of the methods on fingerprint orientation field estimation (2019)
Journal Article
Bian, W., Xu, D., Li, Q., Cheng, Y., Jie, B., & Ding, X. (2019). A Survey of the methods on fingerprint orientation field estimation. IEEE Access, 7, 32644-32663. https://doi.org/10.1109/ACCESS.2019.2903601

Fingerprint orientation field (FOF) estimation plays a key role in enhancing the performance of the automated fingerprint identification system (AFIS): Accurate estimation of FOF can evidently improve the performance of AFIS. However, despite the eno... Read More about A Survey of the methods on fingerprint orientation field estimation.

Towards additive manufacturing oriented geometric modeling using implicit functions (2018)
Journal Article
Li, Q., Hong, Q., Qi, Q., Ma, X., Han, X., & Tian, J. (2018). Towards additive manufacturing oriented geometric modeling using implicit functions. Visual Computing for Industry, Biomedicine, and Art, 1(1), Article 9. https://doi.org/10.1186/s42492-018-0009-y

Surface-based geometric modeling has many advantages in terms of visualization and traditional subtractive manufacturing using computer-numerical-control cutting-machine tools. However, it is not an ideal solution for additive manufacturing because t... Read More about Towards additive manufacturing oriented geometric modeling using implicit functions.

Prior knowledge-based deep learning method for indoor object recognition and application (2018)
Journal Article
Ding, X., Luo, Y., Li, Q., Cheng, Y., Cai, G., Munnoch, R., …Wang, B. (2018). Prior knowledge-based deep learning method for indoor object recognition and application. Systems Science and Control Engineering, 6(1), 249-257. https://doi.org/10.1080/21642583.2018.1482477

Indoor object recognition is a key task for indoor navigation by mobile robots. Although previous work has produced impressive results in recognizing known and familiar objects, the research of indoor object recognition for robot is still insufficien... Read More about Prior knowledge-based deep learning method for indoor object recognition and application.

Accurate geometry modeling of vasculatures using implicit fitting with 2D radial basis functions (2018)
Journal Article
Hong, Q., Li, Q., Wang, B., Liu, K., Lin, F., Lin, J., …Zeng, M. (2018). Accurate geometry modeling of vasculatures using implicit fitting with 2D radial basis functions. Computer aided geometric design, 62, 206-216. https://doi.org/10.1016/j.cagd.2018.03.006

Accurate vascular geometry modeling is an essential task in computer assisted vascular surgery and therapy. This paper presents a vessel cross-section based implicit vascular modeling technique, which represents a vascular surface as a set of locally... Read More about Accurate geometry modeling of vasculatures using implicit fitting with 2D radial basis functions.

Multilevel refinable triangular PSP-splines (Tri-PSPS) (2015)
Journal Article
Li, Q., & Tian, J. (2015). Multilevel refinable triangular PSP-splines (Tri-PSPS). Computers & mathematics with applications, 70(8), 1781-1798. https://doi.org/10.1016/j.camwa.2015.07.017

A multi-level spline technique known as partial shape preserving splines (PSPS) (Li and Tian, 2011) has recently been developed for the design of piecewise polynomial freeform geometric surfaces, where the basis functions of the PSPS can be directly... Read More about Multilevel refinable triangular PSP-splines (Tri-PSPS).

3D vasculature segmentation using localized hybrid level-set method (2014)
Journal Article
Hong, Q., Li, Q., Wang, B., Li, Y., Yao, J., Liu, K., & Wu, Q. (2014). 3D vasculature segmentation using localized hybrid level-set method. BioMedical Engineering OnLine, 13(1), 169. https://doi.org/10.1186/1475-925X-13-169

Background: Intensity inhomogeneity occurs in many medical images, especially in vessel images. Overcoming the difficulty due to image inhomogeneity is crucial for the segmentation of vessel image. Methods: This paper proposes a localized hybrid leve... Read More about 3D vasculature segmentation using localized hybrid level-set method.

GPU accelerating technique for rendering implicitly represented vasculatures (2014)
Journal Article
Hong, Q., Wang, B., Li, Q., Li, Y., & Wu, Q. (2014). GPU accelerating technique for rendering implicitly represented vasculatures. Bio-medical materials and engineering, 24(1), 1351-1357. https://doi.org/10.3233/BME-130938

With the flooding datasets of medical Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), implicit modeling techniques are increasingly applied to reconstruct the human organs, especially the vasculature. However, displaying implicitly rep... Read More about GPU accelerating technique for rendering implicitly represented vasculatures.

A versatile optical model for hybrid rendering of volume data (2012)
Journal Article
Xiang, D., Yang, F., Tian, J., Cao, Y., & Li, Q. (2012). A versatile optical model for hybrid rendering of volume data. IEEE Transactions on Visualization and Computer Graphics, 18(6), 925 - 937. https://doi.org/10.1109/TVCG.2011.113

In volume rendering, most optical models currently in use are based on the assumptions that a volumetric object is acollection of particles and that the macro behavior of particles, when they interact with light rays, can be predicted based on thebeh... Read More about A versatile optical model for hybrid rendering of volume data.

Virtual angioscopy based on implicit vasculatures (2011)
Journal Article
Hong, Q., Li, Q., & Tian, J. (2011). Virtual angioscopy based on implicit vasculatures. Lecture notes in computer science, 6785 LNCS(PART 4), 592-603. https://doi.org/10.1007/978-3-642-21898-9_49

Virtual endoscopy is among the most active areas in medical data visualization, which focuses on the simulated visualizations of specific hollow organs for the purposes of training and diagnosis. In this paper, we present a virtual angioscopy techniq... Read More about Virtual angioscopy based on implicit vasculatures.

Implicit reconstruction of vasculatures using bivariate piecewise algebraic splines (2011)
Journal Article
Hong, Q., Li, Q., & Tian, J. (2012). Implicit reconstruction of vasculatures using bivariate piecewise algebraic splines. IEEE Transactions on Medical Imaging, 31(3), 543-553. https://doi.org/10.1109/TMI.2011.2172455

Vasculature geometry reconstruction from volumetric medical data is a crucial task in the development of computer guided minimally invasive vascular surgery systems. In this paper, a technique for reconstructing the geometry of vasculatures using biv... Read More about Implicit reconstruction of vasculatures using bivariate piecewise algebraic splines.

Partial shape-preserving splines (2011)
Journal Article
Li, Q., & Tian, J. (2011). Partial shape-preserving splines. Computer aided design, 43(4), 394-409. https://doi.org/10.1016/j.cad.2011.01.007

A complex geometric shape is often a composition of a set of simple ones, which may differ from each other in terms of their mathematical representations and the ways in which they are constructed. One of the necessary requirements in combining these... Read More about Partial shape-preserving splines.

Skeleton cuts-An efficient segmentation method for volume rendering (2010)
Journal Article
Xiang, D., Tian, J., Yang, F., Yang, Q., Zhang, X., Li, Q., & Liu, X. (2011). Skeleton cuts-An efficient segmentation method for volume rendering. IEEE Transactions on Visualization and Computer Graphics, 17(9), 1295-1306. https://doi.org/10.1109/tvcg.2010.239

Volume rendering has long been used as a key technique for volume data visualization, which works by using a transfer function to map color and opacity to each voxel. Many volume rendering approaches proposed so far for voxels classification have bee... Read More about Skeleton cuts-An efficient segmentation method for volume rendering.

2D piecewise algebraic splines for implicit modeling (2009)
Journal Article
Li, Q., & Tian, J. (2009). 2D piecewise algebraic splines for implicit modeling. ACM Transactions on Graphics, 28(2), Article ARTN 13. https://doi.org/10.1145/1516522.1516524

2D splines are a powerful tool for shape modeling, either parametrically or implicitly. However, compared with regular grid-based tensor-product splines, most of the high-dimensional spline techniques based on nonregular 2D polygons, such as box spli... Read More about 2D piecewise algebraic splines for implicit modeling.

Smooth piecewise polynomial blending operations for implicit shapes (2007)
Journal Article
Li, Q. (2007). Smooth piecewise polynomial blending operations for implicit shapes. Computer graphics forum : journal of the European Association for Computer Graphics, 26(2), 157-171. https://doi.org/10.1111/j.1467-8659.2007.01011.x

In this paper, we present a new set of blending operations for implicitly defined geometric shapes. The proposed shape operators are piecewise polynomial and blending range controllable, and can be constructed to any required degree of smoothness. Th... Read More about Smooth piecewise polynomial blending operations for implicit shapes.

Constructive implicit fitting (2005)
Journal Article
Li, Q., Griffiths, J. G., & Ward, J. (2006). Constructive implicit fitting. Computer aided geometric design, 23(1), 17-44. https://doi.org/10.1016/j.cagd.2005.04.011

In this paper, we present a constructive method for fitting both an explicit and an implicit curve or surface to a set of scattered points by using gate functions. With this technique, the data are first partitioned with geometric primitives into sma... Read More about Constructive implicit fitting.

Implicit fitting using radial basis functions with ellipsoid constraint (2004)
Journal Article
Li, Q., Wills, D., Phillips, R., Viant, W. J., Griffiths, J. G., & Ward, J. (2004). Implicit fitting using radial basis functions with ellipsoid constraint. Computer graphics forum : journal of the European Association for Computer Graphics, 23(1), 55-69. https://doi.org/10.1111/j.1467-8659.2004.00005.x

Implicit planar curve and surface fitting to a set of scattered points plays an important role in solving a wide variety of problems occurring in computer graphics modelling, computer graphics animation, and computer assisted surgery. The fitted impl... Read More about Implicit fitting using radial basis functions with ellipsoid constraint.

Iterative closest geometric objects registration (2000)
Journal Article
Li, Q., & Griffiths, J. G. (2000). Iterative closest geometric objects registration. Computers & mathematics with applications, 40(10-11), 1171-1188. https://doi.org/10.1016/s0898-1221%2800%2900230-3

In this paper, closed-form solutions are obtained for registering two sets of line segments, triangle patches, or even general simple geometric objects that are defined by a set of ordered points. Based on these new registration approaches, the itera... Read More about Iterative closest geometric objects registration.