检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： K.S. Pradeep A.N. Rajagopalan Image Processing and Computer Vision Laboratory Department of Electrical Engineering Indian Institute of Technology Madras India

ISBN: (纸本)0769525210

Shape from focus (SFF) method determines the degree of focus in a sequence of observations to estimate the shape of a 3-D object. Existing SFF algorithms use an ad hoc interpolation strategy to account for the error due to the finite step-size by which the translational table is moved while capturing the images. We propose an improved SFF method that uses relative defocus blur derived from actual image data to arrive at the final estimates of the shape of the object. A space-variant image restoration scheme is also proposed to obtain a focused image of the 3-D object. The shape estimates as well as the quality of the restored image using the proposed method are superior to that of traditional SFF

关键词： Shape Focusing Cameras Lenses image restoration Interpolation Pixel Polynomials image sensors image processing

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT REPRESENTATION OF DIGITAL CURVES WITH LINE SEGMENTS AND ELLIPTICAL ARCS

AN EFFICIENT REPRESENTATION OF DIGITAL CURVES WITH LINE SEGM...

引用

2006 IET International Conference on Visual Information Engineering

作者： C. Paramanand A.N. Rajagopalan Department of Electrical Engineering Image Processing and Computer Vision Laboratory Indian Institute of Technology Chennai India

来源：评论

学校读者我要写书评

暂无评论

ROBUST SPACE-VARIANT SUPER-RESOLUTION

ROBUST SPACE-VARIANT SUPER-RESOLUTION

引用

2006 IET International Conference on Visual Information Engineering

作者： K.V. Suresh A.N. Rajagopalan Image Processing and Computer Vision Laboratory Department of Electrical Engineering Indian Institute of Technology Madras Chennai India

来源：评论

学校读者我要写书评

暂无评论

Automatic Texture Synthesis for Face Recognition from Single Views

Automatic Texture Synthesis for Face Recognition from Single...

引用

International Conference on Pattern Recognition

作者： Xiaozheng Zhang Yongsheng Gao M.K.H. Leung Computer Vision & Image Processing Laboratory School of Engineering Griffith University Australia School of Computer Engineering Nanyang Technological University Singapore

ISBN: (纸本)0769525210

One possible solution for pose- and illumination-invariant face recognition is to employ appearance-based approaches, which rely greatly on correct facial textures. However, existing facial texture analysis algorithms are suboptimal, because they usually neglect specular reflections and require numerous training images for virtual view synthesis. This paper presents a novel texture synthesis approach from a single frontal view for face recognition. Using a generic 3D face shape, facial textures are analyzed with consideration of all of the ambient, diffuse, and specular reflections. Virtual views are synthesized under different poses and illuminations. The proposed approach was evaluated using the CMU-PIE face database. Encouraging results show that the proposed approach improves face recognition performances across pose and illumination variations

关键词： Face recognition Optical reflection Lighting computer vision image texture analysis Shape Surface texture Face detection Pattern recognition image databases

来源：评论

学校读者我要写书评

暂无评论

Recognizing Rotated Faces from Two Orthogonal Views in Mugshot Databases

Recognizing Rotated Faces from Two Orthogonal Views in Mugsh...

引用

International Conference on Pattern Recognition

作者： Xiaozheng Zhang Yongsheng Gao Bai-ling Zhang Computer Vision & Image Processing Laboratory School of Engineering Griffith University Australia School of Computer Science and Mathematics Victoria University Australia

ISBN: (纸本)0769525210

Tolerance to pose variations is one of the key remaining problems in face recognition. It is of great interest in airport surveillance systems using mugshot databases to screen travellers' faces. This paper presents a novel pose-invariant face recognition approach using two orthogonal face images from mugshot databases. Virtual views under different poses are generated in two steps: shape modeling and texture synthesis. In the shape modeling step, a feature-based multilevel quadratic variation minimization approach is applied to generate smooth 3D face shapes. In the texture synthesis step, a non-Lambertian reflectance model is explored to synthesize facial textures taking into account both diffuse and specular reflections. A view-based face recognizer is used to examine the feasibility and effectiveness of the proposed pose-invariant face recognition. The experimental results show that the proposed method provides a new solution to the problem of recognizing rotated faces

关键词： Face recognition Shape Face detection Humans image databases computer vision Surveillance Spatial databases Reflectivity Reflection

来源：评论

学校读者我要写书评

暂无评论

Effect of minicolumnar disturbance on dyslexic brains: an MRI study

Effect of minicolumnar disturbance on dyslexic brains: an MR...

引用

IEEE International Symposium on Biomedical Imaging

作者： N. El-Zehiry M. Casanova H. Hassan A. Farag Computer Vision and Image Processing Laboratory University of Louisville USA Department of Psychiatry and Behavioral Sciences University of Louisville USA

The minicolumn is generally considered the basic unit of the neocortex in all the mammalian brains. Enlargement of the cortical surface is believed to occur through the addition of minicolumns rather than a single neuron. This study aims at testing the hypothesis that brain developmental disorders can be diagnosed and analyzed in terms of the minicolumnar disturbance. To do this, we propose to correlate the pathological findings in terms of the minicolumnar structure to the MRI findings in terms of volumetric analysis

关键词： Magnetic resonance imaging Neurons Autism Pathology Aging computer vision image processing Psychiatry Testing Nerve fibers

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Approach for Non-Contact Measurements of Arterial Pulse using Thermal Imaging

Multiresolution Approach for Non-Contact Measurements of Art...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： S.Y. Chekmenev A.A. Farag E.A. Essock Computer Vision and Image Processing Laboratory University of Louisville Louisville KY USA Department of Psychological and Brain University of Louisville Louisville KY USA

This paper presents a novel, multiresolution (MR) approach for non-contact passive measurements of the arterial pulse along the arterial tree using thermal imaging of the most accessible regions of human face and neck. The method automatically detects Region/s Of Measurement (ROM) of the arterial pulse using the periodic nature of arterial thermal patterns. This ROM constitutes a skin area where the heat pulsation produced by an artery is most pronounced. The output of the algorithm is a descriptive arterial pulse waveform. To the best of our knowledge, our results are novel and have not been reported before. Some potential applications of this work are in the field of non-contact health state/ physiology monitoring, magnetic resonance imaging, smart rooms, polygraph testing, and intent identification.

关键词： Pulse measurements image resolution Read only memory Humans Face detection Neck Skin Arteries Physiology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Validating linear elastic and linear viscoelastic models of lamb liver tissue using cone-beam CT

引用

International Congress Series 2005年 1281卷 473-478页

作者： Shi, Hongjian Farag, Aly Computer Vision and Image Processing Laboratory University of Louisville Louisville KY United States

The purpose of this paper is to validate simple linear elastic model and linear viscoelastic models for lamb liver tissue deformation using high resolution cone-beam CT images. The resolution of the scanned images is 5 to 25 times higher than typical CT scans. The tissue deformation details in the contact region between the tissue and the indentor can be detected and rendered for smaller force loads. For these loads, it is difficult to accurately predict the volume and surface changes using typical low resolution CT scans. Surgical simulations rely on the accurate representation of the mechanical response of the soft tissues which are subject to surgical manipulations. If the simulation results using a model are quite different from reality, it can be concluded that such model is not applicable to the modelling of the targeted tissue. From simulation results we compare the deformed tissue with that obtained from experiments to verify the applicability of the model to soft tissue deformation. For our validation, fresh ex vivo lamb liver is chosen to validate the linear elastic model and the linear viscoelastic model. © 2005.

关键词： Cone-beam CT Finite element modeling Tissue deformation

来源：评论

学校读者我要写书评

暂无评论

Non-rigid registration techniques for automatic follow-up of lung nodules

引用

International Congress Series 2005年 1281卷 1115-1120页

作者： El-Baz, Ayman Yuksel, Seniha E. Elshazly, Salwa Farag, Aly A. Computer Vision and Image Processing Laboratory University of Louisville Louisville KY 40292 United States

Our long-term research goal is to develop an automatic approach for early detection of lung nodules that may lead to lung cancer. This paper focuses on the monitoring of the progress (growth or shrinking) of lung nodules in successive chest low dose CT (LDCT) scans of a person using non-rigid registration. The overall nodule detection approach consists of four main steps: (1) extraction of lung region by modeling the gray level distribution of LDCT slices using a linear combination of Gaussians, (2) classifying the lung region into homogenous tissues, arteries, veins and lung nodules, (3) applying rigid registration using a combination of segmentation information and mutual information as a similarity measure, and (4) compensating for the effects of heartbeats and respiration using non-rigid registration. Our earlier work addressed a number of steps in this protocol;this paper focuses on the registration step. We show that proper registration could lead to precise identification of the progress of the lung nodules. © 2005.

关键词： Lung nodules Motion compensation Mutual information Registration Segmentation

来源：评论

学校读者我要写书评

暂无评论

Virtual forces for camera planning in smart vision systems

Virtual forces for camera planning in smart vision systems

引用

7th IEEE Workshop on Applications of computer vision, WACV 2005

作者： Farag, Aly A. Abdel-Hakim, Alaa E. Computer Vision and Image Processing Laboratory University of Louisville Louisville KY 40292 United States

ISBN: (纸本)0769522718

In this paper, we present a novel and robust approach for camera planning in smart vision systems. The proposed approach uses virtual forces to adjust the camera parameters (pan, tilt, translation ... etc.) toward the most proper values with respect to the application. It employs the physical spring model to direct the motion of the camera toward its target. Our approach is a general framework and any vision system can be easily modeled to use it. This approach has several advantages over previous work in camera planning. It is portable, expandable, robust, and flexible. We present a case study of a two degree-of-freedom stereo vision system to test our approach. The results show the efficiency of our approach even with poor system initialization and its robustness against possible weakness in the auxiliary algorithms used.

关键词： Stereo vision

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：