Wee Kheng Leow

National University of Singapore, Singapore, Singapore

Are you Wee Kheng Leow?

Claim your profile

Publications (110)22.19 Total impact

  • Chen Zhu, Wee Kheng Leow
    [Show abstract] [Hide abstract]
    ABSTRACT: There are three main approaches for reconstructing 3D models of buildings. Laser scanning is accurate but expensive and limited by the laser’s range. Structure-from-motion (SfM) and multi-view stereo (MVS) recover 3D point clouds from multiple views of a building. MVS methods, especially patch-based MVS, can achieve higher density than do SfM methods. Sophisticated algorithms need to be applied to the point clouds to construct mesh surfaces. The recovered point clouds can be sparse in areas that lack features for accurate reconstruction, making recovery of complete surfaces difficult. Moreover, segmentation of the building’s surfaces from surrounding surfaces almost always requires some form of manual inputs, diminishing the ease of practical application of automatic 3D reconstruction algorithms. This paper presents an alternative approach for reconstructing textured mesh surfaces from point cloud recovered by patch-based MVS method. To a good first approximation, a building’s surfaces can be modeled by planes or curve surfaces which are fitted to the point cloud. 3D points are resampled on the fitted surfaces in an orderly pattern, whose colors are obtained from the input images. This approach is simple, inexpensive, and effective for reconstructing textured mesh surfaces of large buildings. Test results show that the reconstructed 3D models are sufficiently accurate and realistic for 3D visualization in various applications.
    The Visual Computer 06/2013; 29(6-8). DOI:10.1007/s00371-013-0827-z · 1.07 Impact Factor
  • Source
  • [Show abstract] [Hide abstract]
    ABSTRACT: Robust and efficient segmentation tools are important for the quantification of 3D liver and liver tumor volumes which can greatly help clinicians in clinical decision-making and treatment planning. A two-module image analysis procedure which integrates two novel semi-automatic algorithms has been developed to segment 3D liver and liver tumors from multi-detector computed tomography (MDCT) images. The first module is to segment the liver volume using a flippingfree mesh deformation model. In each iteration, before mesh deformation, the algorithm detects and avoids possible flippings which will cause the self-intersection of the mesh and then the undesired segmentation results. After flipping avoidance, Laplacian mesh deformation is performed with various constraints in geometry and shape smoothness. In the second module, the segmented liver volume is used as the ROI and liver tumors are segmented by using support vector machines (SVMs)-based voxel classification and propagational learning. First a SVM classifier was trained to extract tumor region from one single 2D slice in the intermediate part of a tumor by voxel classification. Then the extracted tumor contour, after some morphological operations, was projected to its neighboring slices for automated sampling, learning and further voxel classification in neighboring slices. This propagation procedure continued till all tumorcontaining slices were processed. The performance of the whole procedure was tested using 20 MDCT data sets and the results were promising: Nineteen liver volumes were successfully segmented out, with the mean relative absolute volume difference (RAVD), volume overlap error (VOE) and average symmetric surface distance (ASSD) to reference segmentation of 7.1%, 12.3% and 2.5 mm, respectively. For live tumors segmentation, the median RAVD, VOE and ASSD were 7.3%, 18.4%, 1.7 mm, respectively.
    Proceedings of SPIE - The International Society for Optical Engineering 03/2011; DOI:10.1117/12.877927 · 0.20 Impact Factor
  • Source
    H. Li, W. K. Leow, I.-S. Chiu
    [Show abstract] [Hide abstract]
    ABSTRACT: The Cosserat theory of elastic rods has been used in a wide range of application domains to model and simulate the elastic deformation of thin rods. It is physically accurate and its implementations are efficient for interactive simulation. However, one requirement of using Cosserat rod theory is that the tubular object must have rigid cross-sections that are small compared to its length. This requirement make it difficult for the approach to model elastic deformation of rods with large, non-rigid cross-sections that can change shape during rod deformation, in particular, hollow tubes. Our approach achieves this task using a hybrid model that binds a mesh elastically to a reference Cosserat rod. The mesh represents the surface of the hollow tube while the reference rod models bending, twisting, shearing and stretching of the tube. The cross-sections of the tube may take on any arbitrary shape. The binding is established by a mapping between mesh vertices and the rod's directors. Deformation of the elastic tube is accomplished in two phases. First, the reference rod is deformed according to Cosserat theory. Next, the mesh is deformed using Laplacian deformation according to its mapping to the rod and its surface elastic energy. This hybrid approach allows the tube to deform in a physically correct manner in relation to the bending, twisting, shearing, and stretching of the reference rod. It also allows the surface to deform realistically and efficiently according to surface elastic energy and the shape of the reference rod. In this way, the deformation of elastic hollow tubes with large, non-rigid cross-sections can be simulated accurately and efficiently.
    Computer Graphics Forum 08/2010; 29(6):1770 - 1782. DOI:10.1111/j.1467-8659.2010.01647.x · 1.60 Impact Factor
  • Source
    Feng Ding, Hao Li, Yuan Cheng, W.K. Leow
    [Show abstract] [Hide abstract]
    ABSTRACT: Medical volume images are large in size. They cannot be efficiently transmitted and visualized as candidates for medical image retrieval and relevance feedback. On the other hand, 2D images that are small in size and rich in 3D details can be efficiently transmitted and visualized as candidates. This paper presents an algorithm that summarizes the 3D details in a volume image into a single 2D image. It applies soft segmentation to highlight the anatomy of interest in the volume, and automatically selects a salient view that contains the most amount of semantic information as the summarization of the volume image. Experimental results show that the proposed method can well summarize medical volume images of different anatomical structures. Compared to representation of volume images using 2D slices and conventional volume rendering, our summarized images are rich in 3D details, and they can be transmitted and visualized very efficiently.
    Applications of Computer Vision (WACV), 2009 Workshop on; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Studies of interactions between protein domains and ligands are important in many aspects such as cellular signaling and regulation. In this work, we applied a three-stage knowledge-guided approach of docking flexible peptide ligands to SH2 domains. The first stage of the approach search for binding pockets of SH2 domain proteins and binding motifs of peptide ligands based on known features. The knowledge of the binding sites are used in the second stage as binding constraints to align ligand's peptide backbone to the SH2 domain. The backbone-aligned ligands produced serve as good starting points to the third stage which uses a Monte Carlo method to perform the flexible docking. The experimental results show that the backbone alignment method at the second stage produces good backbone conformations which are close to the conformation in complex. The binding site information is well utilized to provide a better starting point to the next docking stage. The subsequent docking is successful or partially successful in 5 of 7 test cases. The performance is better than that of general docking methods. The presented approach can also be applied to other well characterized protein domains which bind ligands in two or more binding grooves.
    10th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2010, Philadelphia, Pennsylvania, USA, May 31-June 3 2010; 01/2010
  • Source
    Hao Li, Wee Kheng Leow, Ing-Sh Chiu
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a hybrid approach for modeling torsion of blood vessels that undergo deformation and joining. The proposed model takes 3D mesh of the blood vessel as input. It first fits a generalized cylinder to extract the blood vessel's medial axis. Then, it uses rotation minimizing frame as a reference to model and measure the torsion of blood vessel after deformation. In general, the proposed approach can incorporate any kind of deformation algorithms. In our experiments, differential geometry method is used as an example. The test results show that our algorithm can correctly and effectively evaluate the amount of torsion caused by blood vessel deformation. In addition, it can also determine the configuration of the blood vessel with minimum torsion.
    Studies in health technology and informatics 02/2009; 142:153-8. DOI:10.3233/978-1-58603-964-6-153
  • Source
    Hao Li, Wee Kheng Leow, Yingyi Qi, Ing-Sh Chiu
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a method for performing predictive simulation of complex cardiac surgery. It computes complex surgical results given a small amount of user inputs. In this way, the surgeon can easily explore various surgical options without having to go through all the detailed steps of the surgical procedure. Test results, using aorta reconstruction as an application example, show that the proposed method can generate realistic simulation results given different kinds of user inputs, thus demonstrating the feasibility of the approach.
    Studies in health technology and informatics 02/2009; 142:159-61. DOI:10.3233/978-1-58603-964-6-159
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Scoring the nuclear pleomorphism in histopathological images is a standard clinical practice for the diagnosis and prognosis of breast cancer. It relies highly on the experi- ence of the pathologists. In a large hospital, one pathol- ogist may have to evaluate more than a hundred cases per day, which is a very tedious and time-consuming task. Thus, it is necessary to develop an automatic system to support the pathologists.This paper proposes a method that auto- matically selects and segments critical cell nuclei within a high-resolution histopathological image for nuclear pleo- morphism scoring according to the Nottingham grading system. In contrast, most of the existing methods tend to detect all the cells in an image which is computationally expensive. Comprehensive experiments show that accurate scoring can be achieved by segmenting only critical cells, thus reducing the execution time of the method.
    IEEE Workshop on Applications of Computer Vision (WACV 2009), 7-8 December, 2009, Snowbird, UT, USA; 01/2009
  • Source
    Hao Li, Wee Kheng Leow, Chao-Hui Huang, Tet Sen Howe
    [Show abstract] [Hide abstract]
    ABSTRACT: Scoliosis causes deformations such as twisting and lateral bending of the spine. To correct scoliotic deformation, the extents of 3D spinal deformation need to be measured. This paper studies the modeling and measurement of scoliotic spine based on 3D curve model. Through modeling the spine as a 3D Cosserat rod, the D structure of a scoli- otic spine can be recovered by obtaining the minimum potential energy registration of the rod to the scoliotic spine in the x-ray image. Test re- sults show that it is possible to obtain accurate D reconstruction using only the landmarks in a single view, provided that appropriate boundary conditions and elastic properties are included as constraints.
    Computer Analysis of Images and Patterns, 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings; 01/2009
  • Feng Ding, Wee Kheng Leow, Sudhakar K. Venkatesh
    [Show abstract] [Hide abstract]
    ABSTRACT: D visualization and segmentation of organs in abdominal volume images are important in medical image processing for applications such as diagnosis, treatment and surgical planning. However, the abdominal wall leads to difficulties in both visualization and segmentation. These difficulties can be eliminated by removing the abdominal wall. This paper presents an algorithm that removes abdominal wall by registering a 3D flipping-free deformable model to the inner boundary of the wall. To our best knowledge, it is the first work in removing the abdominal wall for the purpose of D visualization and segmentation of the organs.
    Proceedings of the International Conference on Image Processing, ICIP 2009, 7-10 November 2009, Cairo, Egypt; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Studies of interactions between protein domains and ligands are important in many aspects such as cellular signaling. We present a knowledge-guided approach for docking protein domains and exible ligands. The approach is applied to the WW domain, a small protein module mediating signaling complexes which have been implicated in diseases such as muscular dystrophy and Liddle's syndrome. The rst stage of the approach employs a substring search for two binding grooves of WW domains and possible binding motifs of peptide ligands based on known features. The second stage aligns the ligand's peptide backbone to the two binding grooves using a quasi-Newton constrained optimization algorithm. The backbone-aligned ligands produced serve as good start- ing points to the third stage which uses any exible docking algorithm to perform the docking. The experimental results demonstrate that the backbone alignment method in the second stage performs better than conventional rigid superposition given two binding constraints. It is also shown that using the backbone-aligned ligands as initial congurations improves the exible docking in the third stage. The presented approach can also be applied to other protein domains that involve binding of exible ligand to two or more binding sites.
    Pattern Recognition in Bioinformatics, 4th IAPR International Conference, PRIB 2009, Sheffield, UK, September 7-9, 2009. Proceedings; 01/2009
  • Source
    Hao Li, Wee Kheng Leow, Ing-Sh Chiu
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a method for performing predictive simulation of cardiac surgery. It applies a hybrid approach to model the deformation of blood vessels. The hybrid blood vessel model consists of a reference Cosserat rod and a surface mesh. The reference Cosserat rod models the blood vessel's global bending, stretching, twisting and shearing in a physically correct manner, and the surface mesh models the surface details of the blood vessel. In this way, the deformation of blood vessels can be computed efficiently and accurately. Our predictive simulation system can produce complex surgical results given a small amount of user inputs. It allows the surgeon to easily explore various surgical options and evaluate them. Tests of the system using bidirectional Glenn shunt (BDG) as an application example show that the results produc by the system are similar to real surgical results.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Segmentation of 3D soft organs from complex volume images is a very important and challenging task. The objects of interest may have inhomogeneous voxel intensities and some object boundaries may be indistinct. Existing algorithms are either sensitive to noise or computationally expensive. This paper presents a novel algorithm that overcomes these shortcomings. The algorithm adopts a novel flipping-free mesh deformation and registration method that can easily incorporate geometric constraints to reduce sensitivity to noise. It efficiently deforms the 3D model in large displacements reducing total computational costs. These properties are confirmed by comprehensive test results.
    IEEE Workshop on Applications of Computer Vision (WACV 2009), 7-8 December, 2009, Snowbird, UT, USA; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer grading of histopathological images is the standard clinical practice for the diagnosis and prognosis of breast cancer development. In a large hospital, a pathologist typically handles 100 grading cases per day, each consisting of about 2000 image frames. It is, therefore, a very tedious and time-consuming task. This paper proposes a method for automatic computer grading to assist pathologists by providing second opinions and reducing their workload. It combines the three criteria in the Nottingham scoring system using a multi-resolution approach. To our best knowledge, there is no existing work that provide complete grading according to the Nottingham criteria.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 02/2008; 2008:3052-5. DOI:10.1109/IEMBS.2008.4649847
  • Source
    Hao Li, Wee Kheng Leow, Ing-Sh Chiu, Shu-Chien Huang
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper focuses on an important aspect of cardiac surgi- cal simulation, which is the deformation of mesh models to form smooth joins between them. A novel algorithm based on the Laplacian deforma- tion method is developed. It extends the Laplacian method to handle deformation of 2-manifold mesh models with 1-D boundaries, and join- ing of 1-D boundaries to form smooth joins. Test results show that the algorithm can produce a variety of smooth joins common in cardiac surg- eries, and it is efficient for practical applications.
    Advances in Geometric Modeling and Processing, 5th International Conference, GMP 2008, Hangzhou, China, April 23-25, 2008. Proceedings; 01/2008
  • Source
    Ruixuan Wang, Wee Kheng Leow, Hon Wai Leong
    [Show abstract] [Hide abstract]
    ABSTRACT: Computer systems are increasingly being used for sports training. Existing sports training systems either require ex- pensive 3D motion capture systems or do not provide intel- ligent analysis of user's sports motion. This paper presents a framework for affordable and intelligent sports training systems for general users that require only single camera to record the user's motion. Sports motion analysis is formu- lated as a 3D-2D spatiotemporal motion registration prob- lem. A novel algorithm is developed to perform spatiotem- poral registration of the expert's 3D reference motion and a performer's 2D input video, thereby computing the devi- ation of the performer's motion from the expert's motion. The algorithm can effectively handle ambiguous situations in a single video such as depth ambiguity of body parts and partial occlusion. Test results show that, despite using only single video, the algorithm can compute 3D posture errors that reflect the performer's actual motion error.
    2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 24-26 June 2008, Anchorage, Alaska, USA; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years more and more computer aided diagnosis (CAD) systems are being used routinely in hospitals. Image-based knowledge discovery plays important roles in many CAD applications, which have great potential to be integrated into the next-generation picture archiving and communication systems (PACS). Robust medical image segmentation tools are essentials for such discovery in many CAD applications. In this paper we present a platform with necessary tools for performance benchmarking for algorithms of liver segmentation and volume estimation used for liver transplantation planning. It includes an abdominal computer tomography (CT) image database (DB), annotation tools, a ground truth DB, and performance measure protocols. The proposed architecture is generic and can be used for other organs and imaging modalities. In the current study, approximately 70 sets of abdominal CT images with normal livers have been collected and a user-friendly annotation tool is developed to generate ground truth data for a variety of organs, including 2D contours of liver, two kidneys, spleen, aorta and spinal canal. Abdominal organ segmentation algorithms using 2D atlases and 3D probabilistic atlases can be evaluated on the platform. Preliminary benchmark results from the liver segmentation algorithms which make use of statistical knowledge extracted from the abdominal CT image DB are also reported. We target to increase the CT scans to about 300 sets in the near future and plan to make the DBs built available to medical imaging research community for performance benchmarking of liver segmentation algorithms.
    Proceedings of SPIE - The International Society for Optical Engineering 01/2008; DOI:10.1117/12.770858 · 0.20 Impact Factor
  • Source
    Huanhuan Lu, Bingjun Zhang, Ye Wang, Wee Kheng Leow
    [Show abstract] [Hide abstract]
    ABSTRACT: iDVT (interactive Digital Violin Tutor) is a violin learning system exploiting physical and virtual resources and interac- tivity. It aims at providing the user with new effective learn- ing experience. This demonstration paper briefly describes the structure of the system and the underlying audio-visual processing techniques employed in the system.
    Proceedings of the 16th International Conference on Multimedia 2008, Vancouver, British Columbia, Canada, October 26-31, 2008; 01/2008
  • Source
    Wee Kheng Leow, Cheng-Chieh Chiang, Yi-Ping Hung
    [Show abstract] [Hide abstract]
    ABSTRACT: Many large cities have installed surveillance cameras to mon- itor human activities for security purposes. An important surveillance application is to track the motion of an object of interest, e.g., a car or a human, using one or more cameras, and plot the motion path in a city map. To achieve this goal, it is necessary to localize the cameras in the city map and to determine the correspondence mappings between the positions in the city map and the camera views. Since the view of the city map is roughly orthogonal to the camera views, there are very few common features between the two views for a computer vision algorithm to correctly identify corresponding points automatically. This paper proposes a method for camera localization and position mapping that requires minimum user inputs. Given approximate corre- sponding points between the city map and a camera view identified by a user, the method computes the orientation and position of the camera in the city map, and determines the mapping between the positions in the city map and the camera view. The performance of the method is assessed in both quantitative tests and practical application. Quantita- tive test results show that the method is accurate and robust in camera localization and position mapping. Application test results are very encouraging, showing the usefulness of the method in real applications.
    Proceedings of the 16th International Conference on Multimedia 2008, Vancouver, British Columbia, Canada, October 26-31, 2008; 01/2008