Deep learning techniques have proven effective in many applications, but these implementations mostly apply to data in one or two dimensions. Handling 3D data is more challenging due to its irregularity and complexity, and there is a growing interest in adapting deep learning techniques to the 3D domain. A recent successful approach called MeshCNN consists of a set of convolutional and pooling operators applied to the edges of triangular meshes. While this approach produced superb results in classification and segmentation of 3D shapes, it can only be applied to edges of a mesh, which can constitute a disadvantage for applications where the focuses are other primitives of the mesh. In this study, we propose face-based and vertex-based operators for mesh convolutional networks. We design two novel architectures based on the MeshCNN network that can operate on faces and vertices of a mesh, respectively. We demonstrate that the proposed face-based architecture outperforms the original MeshCNN implementation in mesh classification and mesh segmentation, setting the new state of the art on benchmark datasets. In addition, we extend the vertex-based operator to fit in the Point2Mesh model for mesh reconstruction from clean, noisy, and incomplete point clouds. While no statistically significant performance improvements are observed, the model training and inference time are reduced by the proposed approach by 91% and 20%, respectively, as compared with the original Point2Mesh model.

This paper describes a mobile application for tracking progress resulting from pectus excavatum treatment. The application was developed with the Unity cross platform game engine and an adaption of the Visualization Tool Kit (VTK) for Unity. It can be used on a Windows Surface tablet in addition to a Windows based personal computer. Challenges in developing the application involved integrating features of VTK into Unity, designing the friendly user interface, and selecting metrics of interest to medical professionals. In addition to providing comparisons of the overall chest shapes, a technique was developed for automatically measuring the maximum depth. This was accompanied by a method where the user can manually select areas of interest to rapidly explore depth measurement techniques. The application enables users to easily compare scans taken at different times and track changes in shape and maximum depth of the chest deformations. This provides an opportunity for medical professionals and patients to easily monitor progress resulting from the selected treatment and explore alternative measurement techniques.

Pectus Excavatum (PE) is congenital chest wall deformity of unknown etiology that become more pronounced during early adolescence. PE is often accompanied by other problems such as fatigue, breathing issues, and even scoliosis. Severity is evaluated by calculating radiographically derived indices on cross-sectional imaging utilizing computed tomography (CT). For surgical and non-surgical treatments, monitoring improvements in the patient’s chest shape is challenging. Tracking improvements with radiographically derived indices would be cost-prohibitive and unsafe. Therefore, we developed a non-invasive and objective method for measuring and visualizing the change in chest shape over time utilizing an inexpensive Microsoft Kinect camera. We have used this external surface scan Pectus Metric system for several months and recently posited alternative severity indices called the external Haller index (XHI) and external correction index (XCI) using these scans. We believe these new indexes will replace the gold standard, CT scan derived, Haller Index, without subjecting patients to ionizing radiation. This work outlines the non-invasive external indices calculation and discusses the clinical validity of the indices.

For modern parallel applications, modeling their general execution characteristics, such as power and time, is difficult due to a great many factors affecting software-hardware interactions, which is also exacerbated by the dearth of measuring and monitoring tools for novel architectures, such as Intel Xeon Phi processors. To address this modeling challenge, the present work proposes to employ the Empirical Mode Decomposition (EMD) method to describe an execution as a series of modes culminating in a single residual trend, for which, in its turn, a model equation is obtained as a non-linear fit. As outcome, an overall energy consumption may be predicted using this model. A real-world quantum-chemistry application GAMESS and a molecular-dynamics proxy application CoMD were considered in the experiments. The results demonstrate that the energy modeled ranges within 10-30% of the measured energy, depending on the length of execution.

Aerial images are used extensively in many trip and mapping software packages, such as Google Earth and Microsoft Virtual Earth. These software packages provide a wealth of geospatial information including transportation, terrain, places, etc. Among the issues in effective utilization of aerial images, color tone discrepancy is the inconsistency in brightness, saturation, or color balance between images representing adjacent areas, causing adjacent areas appear significantly different that would otherwise be similar. This paper proposes novel algorithms that can significantly eliminate or reduce color tone discrepancies of aerial images based on estimation of atmospheric effects. Two algorithms are proposed for estimating the parameters of the translucent layer modeling the atmosphere. Proposed algorithm I utilizes a cost function approach and is suitable for images that have overlapped areas, while proposed algorithm II is based on statistical estimation and is suitable for arbitrary images representing adjacent areas. Enhanced images are obtained by removing atmospheric effects in the target images. Presented results demonstrate the effectiveness of proposed algorithms.

In this paper, we analyze several previous optimization approaches for weighted vector median (WVM) filters and show their deficiencies. We then propose two fast adaptive WVM optimization algorithms. Proposed algorithm I computes the optimal weight changes at each iteration, and updates weights accordingly. Proposed algorithm II extends the results from weighted median optimization to the vector case by a generalization of an error metric. Both algorithms are fast and stable, and perform well under a wide variety of circumstances.

This paper proposes a novel approach for smoothing surfaces represented by triangular meshes. The proposed method is a two-step procedure: surface normal smoothing through fuzzy vector median (FVM) filtering followed by integration of surface normals for vertex position update based on the least square error (LSE) criteria. Median and Order Statistic-based filters are extensively used in signal processing, especially image processing, due to their ability to reject outliers and preserve features such as edges and monotonic regions. More recently, fuzzy ordering theory has been introduced to allow averaging among similarly valued samples. Fuzzy ordering theory leads naturally to the fuzzy median, which yields improved noise smoothing over traditional crisp median filters. This paper extends the fuzzy ordering concept to vector-based data and introduces the fuzzy vector median filter. The application of FVM filters to surface normal smoothing yields improved results over previously introduced normal smoothing algorithms. The improved filtering results, coupled with LSE vertex position update, produces surface smoothing that minimizes the effects of noise while simultaneously preserving detail features. The proposed method is simple to implement and relatively fast. Simulation results are presented showing the performance of the proposed method and its advantages over commonly used surface smoothing algorithms. Additionally, optimization procedures for FVM filters are derived and evaluated.

This paper proposes a novel approach for smoothing surfaces represented by triangular meshes. The proposed method is a two-step procedure: surface normal smoothing through fuzzy vector median (FVM) filtering followed by vertex position update based on the least square error criteria. This paper applies the fuzzy ordering theory to the vector based data and introduces the fuzzy vector median. The application of FVM filters to surface normal smoothing yields improved results over previously introduced normal smoothing algorithms. The improved filtering results, coupled with LSE vertex position update, produces surface smoothing that minimizes the effects of noise while simultaneously preserving detail features. Simulation results are presented showing the performance of the proposed method and its advantages over commonly used surface smoothing algorithms. Additionally, optimization procedures for FVM are derived and evaluated.