检索结果-内蒙古大学图书馆

2012 9th Conference on Computer and Robot vision, CRV 2012

作者： Abdelrahman, Mostafa El-Melegy, Moumen Farag, Aly Computer Vision and Image Processing Laboratory University of Louisville Louisville KY 40292 United States Electrical Engineering Department Assiut University Assiut 71516 Egypt

ISBN: (纸本)9780769546834

One of the major goals of computer vision and machine intelligence is the development of flexible and efficient methods for shape representation. This paper presents an approach for shape retrieval based on sparse representation of scale-invariant heat kernel. We use the Lap lace-Beltrami eigen functions to detect a small number of critical points on the shape surface. Then a shape descriptor is formed based on the heat kernels at the detected critical points for different scales, combined with the normalized eigen values of the Lap lace-Beltrami operator. Sparse representation is used to reduce the dimensionality of the calculated descriptor. The proposed descriptor is used for classification via the collaborative representation-based classification with regularized least square algorithm. We compare our approach to two well-known approaches on two different data sets: the nonrigid world data set and the SHREC 2011. The results have indeed confirmed the improved performance of the proposed approach, yet reducing the time and space complicity of the shape retrieval problem. © 2012 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Regularized Gradient Kernel Anisotropic Diffusion for Better image Filtering

Regularized Gradient Kernel Anisotropic Diffusion for Better...

引用

Canadian Conference on Computer and Robot vision, CRV

作者： Amir H. Shabani John S. Zelek David A. Clausi Vision and Image Processing Laboratory Intelligent Systems Laboratory University of Waterloo ONT Canada Intelligent Systems Laboratory University of Waterloo ONT Canada Vision and Image Processing Laboratory University of Waterloo ONT Canada

This paper proposes an extension to anisotropic diffusion filtering for a better preservation of semantically meaningful structures such as edges in an image in its smoothing/denoising process. The problem of separation of the gradients due to edges and the gradients due to noise is formulated as a nonlinearly separable classification problem. More specifically, the spatially-regularized image gradient is mapped to a higher dimensional Reproducing Kernel Hilbert Space (RKHS) in which the gradients of the edges from those of noise can be readily separated. This proper discrimination of edges prevents the filter from blurring the edges, while smoothing the image. Compared to the existing anisotropic filters, the proposed method improves the denoising and smoothing of an image on both synthetic and real images.

关键词： image edge detection Anisotropic magnetoresistance Kernel Smoothing methods Noise Noise reduction Design automation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Local Spatio-temporal Salient Feature Detectors for Human Action Recognition

Evaluation of Local Spatio-temporal Salient Feature Detector...

引用

Canadian Conference on Computer and Robot vision, CRV

作者： Amir H. Shabani David A. Clausi John S. Zelek Vision and Image Processing Laboratory Intelligent Systems Laboratory University of Waterloo ONT Canada Vision and Image Processing Laboratory University of Waterloo ONT Canada Intelligent Systems Laboratory University of Waterloo ONT Canada

Local spatio-temporal salient features are used for a sparse and compact representation of video contents in many computer vision tasks such as human action recognition. To localize these features (i.e., key point detection), existing methods perform either symmetric or asymmetric multi-resolution temporal filtering and use a structural or a motion saliency criteria. In a common discriminative framework for action classification, different saliency criteria of the structured-based detectors and different temporal filters of the motion-based detectors are compared. We have two main observations. (1) The motion-based detectors localize features which are more effective than those of structured-based detectors. (2) The salient motion features detected using an asymmetric temporal filtering performbetter than all other sparse salient detectors and dense sampling. Based on these two observations, we recommend the use of asymmetric motion features for effective sparse video content representation and action recognition.

关键词： Feature extraction Detectors Humans Training Cameras Standards Accuracy

来源：评论

学校读者我要写书评

暂无评论

Illumination correction in dermatological photographs using multi-stage illumination modeling for skin lesion analysis

Illumination correction in dermatological photographs using ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Jeffrey Glaister Alexander Wong David A. Clausi Vision and Image Processing Laboratory with the Department of Systems Design Engineering University of Waterloo ONT Canada

A novel algorithm for correcting illumination variation in dermatological photographs via a multi-stage modeling of the underlying illumination is proposed for the purpose of skin lesion analysis. First, an initial illumination estimate is obtained via a non-parametric modeling strategy based on Monte Carlo sampling. Next, a subset of pixels from the non-parametric estimate is used to determine a parametric estimate of the illumination based on a quadratic surface model. Using the parametric illumination estimate, the reflectance map is obtained and used to correct the photograph. The photographs corrected using the proposed algorithm are compared to uncorrected photographs and to a state-of-the-art correction algorithm. Qualitatively, a visual comparison is performed, while quantitatively, the coefficient of variation of skin pixel intensities is calculated and the precision-recall curve for segmentation of skin lesions is graphed. Results show that the proposed algorithm has a lower coefficient of variation and an improved precision-recall curve.

关键词： Lighting Skin Lesions Algorithm design and analysis Monte Carlo methods Malignant tumors image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale saliency-guided compressive sensing approach to efficient robotic laser range measurements

Multi-scale saliency-guided compressive sensing approach to ...

引用

2012 9th Conference on Computer and Robot vision, CRV 2012

作者： Schwartz, Shimon Wong, Alexander Clausi, David A. Department of Systems Design Engineering University of Waterloo Vision and Image Processing Lab. Research Group Waterloo ON N2L 3G1 Canada

ISBN: (纸本)9780769546834

Improving laser range data acquisition speed is important for many robotic applications such as mapping and localization. One approach to reducing acquisition time is to acquire laser range data through a dynamically small subset of measurement locations. The reconstruction can then be performed based on the concept of compressed sensing (CS), where a sparse signal representation allows for signal reconstruction at sub-Nyquist measurements. Motivated by this, a novel multi-scale saliency-guided CS-based algorithm is proposed for an efficient robotic laser range data acquisition for robotic vision. The proposed system samples the objects of interest through an optimized probability density function derived based on multi-scale saliency rather than the uniform random distribution used in traditional CS systems. Experimental results with laser range data from indoor and outdoor environments show that the proposed approach requires less than half the samples needed by existing CS-based approaches while maintaining the same reconstruction performance. In addition, the proposed method offers significant improvement in reconstruction SNR compared to current CS-based approaches. © 2012 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Saliency-Guided Compressive Sensing Approach to Efficient Robotic Laser Range Measurements

Multi-Scale Saliency-Guided Compressive Sensing Approach to ...

引用

Canadian Conference on Computer and Robot vision, CRV

作者： Shimon Schwartz Alexander Wong David A. Clausi Department of Systems Design Engineering Vision and Image Processing Laboratory research group University of Waterloo Waterloo ONT Canada

关键词： Measurement by laser beam image reconstruction image coding Robot sensing systems Noise measurement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Haptic rendering of dense 3D point cloud data

Haptic rendering of dense 3D point cloud data

引用

International Symposium on Haptic Interfaces for Virtual Environment and Teleoperator systems (HAPTICS)

作者： K. G. Sreeni Subhasis Chaudhuri Vision and Image Processing Laboratory Department of Electrical Engineering Indian Institute of Technology Bombay Powai Mumbai Vision and Image Processing Laboratory Department of Electrical Engineering Indian Institute of Technology Bombay Mumbai India

This work is aimed at rendering an object described by a dense point cloud data without a pre-computed polygonal mesh and surface normal information. We use a proxy based rendering technique with proxy collocated with the HIP in free space. To avoid sinking of proxy into the object during collision a sphere of sufficiently large radius is selected as the proxy so as to avoid it going through the point cloud. Once collision is detected, we minimize a cost function depending on the current HIP and proxy positions and find a new goal position for the proxy corresponding to the local minimum of the cost function. Our rendering algorithm continuously evaluates a tangential vector for the proxy to move over the object surface during collision. The penetration depth is calculated from the proxy to the HIP and is used to calculate the reaction force for the haptic device. We used our technique to render several dense point cloud based models. We also use the surface normal evaluated at the point of contact to shade the object surface when shown visually.

关键词： Indexes Vectors Bismuth Hip

来源：评论

学校读者我要写书评

暂无评论

2D PCA-based shape prior for level sets segmentation framework of the vertebral body

2D PCA-based shape prior for level sets segmentation framewo...

引用

Cairo International Biomedical Engineering Conference, CIBEC

作者： Ahmed Shalaby Melih Aslan Hossam Abdelmunim Aly A. Farag Computer Vision and Image Processing Laboratory University of Louisville KY USA Computer & Systems Engineering Department Ain Shams University Cairo Egypt

In this paper, a novel statistical shape modeling method is developed for the vertebral body (VB) segmentation framework. Two-dimensional principle component analysis (2D-PCA) technique is exploited to extract the shape prior. The obtained shape prior is then embedded into the image domain to develop a new shape-based segmentation approach. Our framework consists of four main steps: i) shape model construction using 2D-PCA, ii) Detection of the VB region using the Matched filter, iii) Initial segmentation using the graph cuts which integrates the intensity and spatial interaction models, and iv) Registration of the shape prior and initially segmented region to obtain the final segmentation. The proposed method is validated on a Phantom as well as clinical CT images with various Gaussian noise levels. The experimental results show that the noise immunity and the segmentation accuracy of 2D-PCA based approach are much higher than conventional PCA approach.

关键词： Shape image segmentation Training Principal component analysis Accuracy Computed tomography Vectors

来源：评论

学校读者我要写书评

暂无评论

5th International Symposium on Focused Ultrasound Abstracts

引用

JOURNAL OF THERAPEUTIC ULTRASOUND 2016年第SUPPL 1期4卷 1-1页

作者： [Anonymous] Rambam Health Care Campus Haifa Israel Stanford University Stanford CA USA University of Pennsylvania Philadelphia PA USA The Ohio State University Columbus OH USA University of Virginia Charlottesville VA USA Center for Nanomedicine/Wilmer Eye Institute Johns Hopkins University Baltimore MD USA Columbia University New York NY USA Sunnybrook Health Sciences Centre Toronto ON Canada Sunnybrook Research Institute Toronto ON Canada Clem Jones Centre for Ageing Dementia Research Queensland Brain Institute The University of Queensland St Lucia QLD Australia The University of Queensland Brisbane (St Lucia Campus) QLD Australia University of Leuven Leuven Belgium University of Maryland School of Medicine/Baltimore VAMC Baltimore MD USA Research & Development Service VA Maryland Healthcare System and University of Maryland School of Medicine Baltimore MD USA University of Maryland School of Medicine Baltimore MD USA Brigham and Women’s Hospital Boston MA USA Harvard Medical School Boston MA USA Boston University Boston MA USA National Institutes of Health Bethesda MD USA National Institutes of Health Clinical Center Bethesda MD USA University of Utah Salt Lake City UT USA Focused Ultrasound Foundation Charlottesville VA USA Vanderbilt University Nashville TN USA Georgia Institute of Technology Atlanta GA USA Cleveland Clinic Cleveland OH USA Institut Langevin Ondes et Images ESPCI ParisTech CNRS UMR 7587 INSERM U979 Paris France CENIR ICM CNRS U7225 INSERM U975 Paris France University Children’s Hospital Zurich Zurich Switzerland Jeju National University Jeju Republic of Korea Hospital for Sick Children Toronto ON Canada Centre for Image Guided Innovation and Therapeutic Intervention Toronto ON Canada Philips Healthcare Canada Toronto ON Canada Toronto Western Hospital Toronto ON Canada Thunder Bay Regional Research Institute Thunder Bay ON Canada Incheon St. Mary’s Hospital The Catholic University of Korea Incheon Republic of Korea Departme

来源：评论

学校读者我要写书评

暂无评论

Perceptual Structure Distortion Ratio: An image Quality Metric Based on Robust Measures of Complex Phase Order

Perceptual Structure Distortion Ratio: An Image Quality Metr...

引用

Canadian Conference on Computer and Robot vision, CRV

作者： Alexander Wong Vision and Image Processing (VIP) Research Group Department of Systems Design Engineering University of Waterloo Waterloo Canada

This paper investigates a novel perceptual driven approach to image quality assessment using complex wavelets called PSDR (Perceptual Structure Distortion Ratio). The measure is grounded in the modeling of the human vision system as a frequency-based processing system and that perceptual structural significance can be derived based on the concept of complex phase order. Built upon a robust complex phase order framework for measuring structural significance, preliminary results using test images under different types of distortions show that PSDR can be a promising direction for evaluating the quality of visual media.

关键词： image quality PSNR Phase measurement Humans Wavelet transforms Transform coding

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：