检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Antonio Sze-To H. R. Tizhoosh Andrew K. C. Wong Systems Design Engineering University of Waterloo Ontario Canada N2L 3G1 KIMIA Lab University of Waterloo Ontario Canada N2L 3G1

ISBN: (纸本)9781509006212

A Content-Based Image Retrieval (CBIR) system which identifies similar medical images based on a query image can assist clinicians for more accurate diagnosis. The recent CBIR research trend favors the construction and use of binary codes to represent images. Deep architectures could learn the non-linear relationship among image pixels adaptively, allowing the automatic learning of high-level features from raw pixels. However, most of them require class labels, which are expensive to obtain, particularly for medical images. The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique. In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes. We conducted experiments on more than 14,000 x-ray images. By using class labels only for evaluating the retrieval results, we constructed a 16-bit DDA and a 512-bit DDA independently. Comparing to other unsupervised methods, we succeeded to obtain the lowest total error by using the 512-bit codes for retrieval via exhaustive search, and speed up 9.27 times with the use of the 16-bit codes while keeping a comparable total error. We found that our new training scheme could reduce the total retrieval error significantly by 21.9%. To further boost the image retrieval performance, we developed Radon Autoencoder Barcode (RABC) which are learned from the Radon projections of images using a de-noising autoencoder. Experimental results demonstrated its superior performance in retrieval when it was combined with DDA binary codes.

关键词： Binary codes Training Noise reduction X-ray imaging Image retrieval Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Twisting sliding mode control of an electrostatic MEMS micromirror for a laser scanning system 34

Twisting sliding mode control of an electrostatic MEMS micro...

引用

第三十四届中国控制会议

作者： Chen Hui Sun ZhenDong Sun WeiJie Yeow John T W School of Comp uter and Information Engineering HeNan University Key Lab of Systems & Control Academy of Mathematics and Systems Science Chinese Academy of Sciences College of Automation Science and Engineering South China University of Technology Systems Design Engineering University of Waterloo

ISBN: (纸本)9781467374439

This paper demonstrates the design and implementation of a second order twisting control algorithm with PID sliding surface for aMEM S micromirror.A laser scanning system with the closed-loop controlled MEM S micromirror is developed and obtains 2D *** response and pointing performance are essential for the optical communications applications,for instance,MEM S optical *** verify the effectiveness of theproposed scheme,the experiments of set-point regulation are *** with traditional sliding mode control,the proposed scheme is able to improve the pointing accuracy with less chattering phenomenon.A micromirror-based laser scanning system is developed,the experimental results confirm that the proposed scheme is able to reduce the distortion of the scan trajectory and improve the image quality.

关键词： Sliding Mode Control,Twisting algorithm,electrostatic micromirror

来源：评论

学校读者我要写书评

暂无评论

TIGER: A TEXTURE-ILLUMINATION GUIDED ENERGY RESPONSE MODEL FOR ILLUMINATION ROBUST LOCAL SALIENCY

TIGER: A TEXTURE-ILLUMINATION GUIDED ENERGY RESPONSE MODEL F...

引用

IEEE International Conference on Image Processing

作者： B. Chwyl A. G. Chung F. Y. Li A. Wong D. A. Clausi Vision & Image Processing Lab Systems Design Engineering Dept. University of Waterloo

ISBN: (纸本)9781479983407

Local saliency models are a cornerstone in image processing and computer vision, used in a wide variety of applications ranging from keypoint detection and feature extraction, to image matching and image representation. However, current models exhibit difficulties in achieving consistent results under varying, non-ideal illumination conditions. In this paper, a novel texture-illumination guided energy response (TIGER) model for illumination robust local saliency is proposed. In the TIGER model, local saliency is quantified by a modified Hessian energy response guided by a weighted aggregate of texture and illumination aspects from the image. A stochastic Bayesian disassociation approach via Monte Carlo sampling is employed to decompose the image into its texture and illumination aspects for the saliency computation. Experimental results demonstrate that higher correlation between local saliency maps constructed from the same scene under different illumination conditions can be achieved using the TIGER model when compared to common local saliency approach, i.e., Laplacian of Gaussian, Difference of Gaussians, and Hessian saliency models.

关键词： Local saliency model Illumination robust Local features Bayesian estimation Stochastic Texture Illumination illumination Lighting Stochastic Bayes methods textures local image feature texture images Gauss Energy responses image representation image matching

来源：评论

学校读者我要写书评

暂无评论

IMPROVED FINE STRUCTURE MODELING VIA GUIDED STOCHASTIC CLIQUE FORMATION IN FULLY CONNECTED CONDITIONAL RANDOM FIELDS

IMPROVED FINE STRUCTURE MODELING VIA GUIDED STOCHASTIC CLIQU...

引用

IEEE International Conference on Image Processing

作者： M. J. Shafiee A. G. Chung A. Wong P. Fieguth Vision & Image Processing Lab Systems Design Engineering Dept. University of Waterloo

ISBN: (纸本)9781479983407

Markov random fields (MRFs) and conditional random fields (CRFs) are influential tools in image modeling, particularly for applications such as image segmentation. Local MRFs and CRFs utilize local nodal interactions when modeling, leading to excessive smoothness on boundaries (i.e., the short-boundary bias problem). Recently, the concept of fully connected conditional random fields with stochastic cliques (SFCRF) was proposed to enable long-range nodal interactions while addressing the computational complexity associated with fully connected random fields. While SFCRF was shown to provide significant improvements in segmentation accuracy, there were still limitations with the preservation of fine structure boundaries. To address these limitations, we propose a new approach to stochastic clique formation for fully connected random fields (G-SFCRF) that is guided by the structural characteristics of different nodes within the random field. In particular, fine structures surrounding a node are modeled statistically by probability distributions, and stochastic cliques are formed by considering the statistical similarities between nodes within the random fields. Experimental results show that G-SFCRF outperforms existing fully connected CRF frameworks, SFCRF, and the principled deep random field framework for image segmentation.

关键词： Stochastic Cliques SFCRF Guided Stochastic Cliques CRF Segmentation Fully connected Corticotropin-Releasing Hormone segmentation Segmentation image segmentation fine structure Modeling Random Markov random fields all-pass Ganglia Probability distribution Structural properties complexity classes

来源：评论

学校读者我要写书评

暂无评论

HIGH DYNAMIC RANGE MAP ESTIMATION VIA FULLY CONNECTED RANDOM FIELDS WITH STOCHASTIC CLIQUES

HIGH DYNAMIC RANGE MAP ESTIMATION VIA FULLY CONNECTED RANDOM...

引用

IEEE International Conference on Image Processing

作者： F. Y. Li M. J. Shafiee A. G. Chung B. Chwyl F. Kazemzadeh A. Wong J. Zelek Vision & Image Processing Lab Systems Design Engineering Dept. University of Waterloo

ISBN: (纸本)9781479983407

The reconstruction of high dynamic range (HDR) images via conventional camera systems and low dynamic range (LDR) images is a growing field of research in image acquisition. The radiance map associated with the HDR image of a scene is typically computed using multiple images of the same scene captured at different exposures (i.e., bracketed LDR imzages). This approach, though inexpensive, is sensitive to noise under high camera ISO. Each bracketed image is associated with a different level of noise due to the change in exposure time, and the noise is further amplified when tone-mapping the HDR image for display. A new framework is proposed to address the associated noise in the context of random fields. The estimation of the HDR image from a set of LDR images is formulated as a stochastically fully connected conditional random field where the spatial information is incorporated to compute the HDR value in combination with the LDR image values. Experimental results show that the proposed framework compensated the non-stationary ISO noise while preserving the boundaries in the estimated HDR images.

关键词： High Dynamic Range Imaging Conditional Random Fields Image Denoising HDR Reconstruction SFCRF image denoising hot dry rocks GATA3 gene LAND DISPOSAL RESTRICTIONS Noise images HIGH DYNAMIC RANGE Markov random fields field surveys Noise levels Brackets Cameras

来源：评论

学校读者我要写书评

暂无评论

EXTERNAL FORCES FOR ACTIVE CONTOURS USING THE UNDECIMATED WAVELET TRANSFORM

EXTERNAL FORCES FOR ACTIVE CONTOURS USING THE UNDECIMATED WA...

引用

IEEE International Conference on Image Processing

作者： Ahmed Gawish Paul Fieguth Vision and Image Processing (VIP) Lab Department of Systems Design Engineering University of Waterloo

ISBN: (纸本)9781479983407

A limitation of active contours models (both parametric and geometric) is their sensitivity to noise. Many solutions to noise sensitivity have been proposed in the literature, with the current state-of-the-art based on image blurring and multiresolution processing. However a significant drawback of both approaches is the side effect of edge delocalization. In this paper, gradient information extracted from all resolutions of the undecimated wavelet transform is used to build the external force map for the active contour. The new map accurately drives the active contour and improves edge localization. The proposed method builds on both Gradient Vector Flow and Vector Field Convolution active contours. Comparisons to classical and state-of-the-art methods show a dramatic improvement in active contour convergence for all levels of noise.

关键词： Active contours Undecimated wavelet transform Active contours contour image blur Noise sensitivity Side Effect wavelet transforms Gradient vector Noise Parametric

来源：评论

学校读者我要写书评

暂无评论

Cross modality label fusion in multi-atlas segmentation

Cross modality label fusion in multi-atlas segmentation

引用

作者： Kasiri, Keyvan Fieguth, Paul Clausi, David A. Lab Department of Systems Design Engineering University of Waterloo Waterloo Canada

ISBN: (纸本)9781479957514

Multi-atlas label fusion is a widely used approach in medical image analysis that has improved the accuracy of segmentation. Majority voting, as the most common combination strategy, weighs each candidate in the atlas database equally. More sophisticated methods rely on the intensity similarity of each atlas to the target volume. However, these methods cannot handle those cases in which the atlases and the target image are in different modalities. A new method for label fusion is proposed, based on a structural similarity measure, relying on the structural relationships of features extracted from an undecimated wavelet transform instead of explicit image intensities. The new label fusion method has been tested on simulated and real MR images;segmentation results are promising, and open the door to a wider range of multi-modal approaches. © 2014 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Undecimated hierarchical active contours for oct image segmentation

Undecimated hierarchical active contours for oct image segme...

引用

作者： Gawish, Ahmed Fieguth, Paul Marschall, Sebastian Bizheva, Kostadinka Lab Dept. of Systems Design Engineering University of Waterloo Waterloo Canada Dept. of Physics and Astronomy University of Waterloo Waterloo Canada

ISBN: (纸本)9781479957514

A limitation of Optical Coherence Tomography (OCT) image segmentation is the poor signal-to-noise ratio of the imaging process, particularly because images are sampled quickly, at high resolutions, and in-vivo. Furthermore, speckle noise is generated by the reflections of the OCT LASER. Because OCT is widely used in imaging the cornea, retina, and skin, OCT layer segmentation is of key interest in all applications. In this paper, a multi-resolution parametric active contour is used for OCT segmentation. The proposed method uses an undecimated wavelet transform to obtain scale-dependent noise reduction, while the active contour is initialized with a generalized Hough transform. Experimental results show that the proposed method outperforms classical as well as state-of-the-art methods and segments OCT images with high level of accuracy. © 2014 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

User Perception of Data and Medical Record Personalities

引用

Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care 2014年第1期3卷 15 - 22页

作者： Justin St-Maurice Catherine M. Burns Advanced Interface Design Lab Systems Design Engineering University of Waterloo Ontario CanadaSchool of Health & Life Sciences and Community Service Conestoga College Ontario Canada Advanced Interface Design Lab Systems Design Engineering University of Waterloo Ontario Canada

Data quality is an important and costly topic in modern society, and data quality and contextual data quality are important components of the human-computer relationship. As a long-term design imperative, the user interface needs to be improved to support better data quality. To design for better data quality, this exploratory study characterizes physicians’ opinions on their own data and the data produced by their colleagues. Through a regional survey and semi-structured interviews, the issue of data style and medical record personality was a dominant theme. A record’s personality impacts an individual user’s willingness to accept the data it contains. Future work will incorporate these results into modeling the data quality problem with cognitive work analysis, and will explore design elements to support the design for better data quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Surface ghosts: Promoting awareness of transferred objects during pick-and-drop transfer in multi-surface environments 14

Surface ghosts: Promoting awareness of transferred objects d...

引用

9th ACM International Conference on Interactive Tabletops and Surfaces, ITS 2014

作者： Scott, Stacey D. Besacier, Guillaume Tournet, Julie Goyal, Nippun Haller, Michael Systems Design Engineering University of Waterloo WaterlooON Canada Games Institute University of Waterloo WaterlooON Canada Université Paris 8 Saint-Denis France Télécom Bretagne Brest France Media Interaction Lab University of Applied Sciences Upper Austria Hagenberg Austria

ISBN: (纸本)9781450325875

Rekimoto's Pick-and-Drop (P&D) transfer technique is commonly used to support multi-surface object transfer (e.g., between a shared tabletop and tablet) due to its easily understood metaphor of emulating object movement in the physical world. Current multi-surface implementations of P&D provide little to no feedback during transfer, causing confusion for the person performing the action as well as others in the environment. To address this issue, we investigated the use of virtual embodiments to improve awareness of transferred objects, in the context of a real-world group task that relied heavily on cross-device transfer. An iterative design process led to the design of Surface Ghosts virtual embodiments, which take the form of semitransparent "ghosts" of the transferred objects displayed under the "owner's" hand on the tabletop during transfer. A user study that compared two Surface Ghosts designs- varied by how explicitly the "owner" was indicated- showed that both designs improved awareness of transferred objects when compared to a no-feedback control condition, especially for tabletop-to-tablet transfers. Copyright © 2014 ACM.

关键词： Drops

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：