检索结果-内蒙古大学图书馆

Optics, Illumination, and Image Sensing for Machine vision III 1988

作者： Kimball, Steven F. Messner, Richard A. University of New Hampshire Synthetic Vision and Pattern Analysis Laboratory Department of Electrical and Computer Engineering DurhamNH03824 United States

The method of using log-polar mapping with spectral band separation to form feature vectors for an associative memory is investigated. Log-polar mapping is used to provide the scale and rotation invariant properties. This reduces the teaching time and total capacity requirement for the associative memory because all orientations and sizes of the target object need not be learned. The images are also broken down into spatial frequency bands. The use of this technique is motivated by evidence that similar processes occur in the human visual system. Suspected benefits include enhanced recognition in the presence of noise and improved network robustness. Simulation results are presented for the case of character recognition. © 1989 SPIE. All rights reserved.

关键词： Associative processing

来源：评论

学校读者我要写书评

暂无评论

Image segmentation using human visual system properties with applications in image compression

Image segmentation using human visual system properties with...

引用

Human vision, Visual Processing, and Digital Display 1989

作者： Peterson, Heidi A. Rajala, Sarah A. Delp, Edward J. Computer Vision and Image Processing Laboratory School of Electrical Engineering Purdue University West LafayetteIN47907 United States Department of Electrical and Computer Engineering North Carolina State University RaleighNC27695 United States

Many image compression techniques involve segmentation of a gray level image. With such techniques, information is extracted that describes the regions in the segmented image, and this information is then used to form a coded version of the image. In this paper we present a region-growing-based segmentation technique that incorporates human visual system properties, and describe the use of this technique in image compression. We also discuss the effect of requantizing a segmented image. Requantization of a segmented image is useful because it can lead to a reduction in the number of bits required to code the description of the regions in the segmented image. This results in a lower data rate. We show that the number of gray levels in a segmented image can be reduced by a factor of at least twelve, without noticeable degradation in the quality of the segmented image. This result is attributable to human visual system properties having to do with contrast sensitivity, and to the fact that requantization of a segmented image does not usually reduce significantly the number of distinct segments in the image. In addition, in this paper we explore the relationship between the number of segments in an image, and the extent of requantization possible before noticeable degradation occurs in the image. Finally, we discuss the impact of the above results on image compression algorithms, and present some experimental results. © 1989 SPIE. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

A medical axis transform algorithm for compression and vectorization of document images

A medical axis transform algorithm for compression and vecto...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： J.W. Brandt A.K. Jain Computer Vision Research Laboratory Department of Electrical Engineering and Computer Science University of California Davis CA USA

It is proposed that the medial axis transformation (MAT), being an invertible transformation, has value in lossless data compression, and, since the MAT conveys the line structure of an image, that it is also useful for vector conversion. To this end, some properties of the MAT are established and then exploited to devise a specialized chain-code representation. This MAT-based chain-code language captures any binary image but is particularly suited to line drawings. An extension of the language that can express chain-code sequences as linear and quadratic line segments under tunable error tolerance is described. The representation has achieved acceptable lossless data compression and significant additional compression for line drawings when vectorization is employed. As the error tolerance is increased, the amount of compression increases together with distortion. Thus, the method can be used to obtain a rate/distortion curve for binary images.< >

关键词： Biomedical imaging Image coding Image segmentation computer vision Skeleton Rate distortion theory Data compression computer science Vectors Image converters

来源：评论

学校读者我要写书评

暂无评论

Mean field theory and MT neurons

Mean field theory and MT neurons

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： A. Dobbins S.W. Zucker Computer Vision and Robotics Laboratory Department of Electrical Engineering McGill University Montreal QUE Canada Canadian Institute for Advanced Research Montreal QUE Canada

The problem of obtaining reliable estimates of the optic flow field and its variation is discussed. It is argued that circuitry in the middle temporal (MT) visual area is arranged to provide mean field approximations of the optical flow field, that is, the maximal neighborhood over which the local field can be well-approximated as uniform, parallel translation. In addition, the way the mean field approximation varies with neighborhood size and position is informative about the variation of the flow field. It is shown how receptive fields can be synthesized to represent the first-order differential information about the flow field. The same ideas are applicable to the binocular disparity vector field, and lead one to predict the existence of extrastriate neurons that are specialized for the local shear and stretch of the disparity and motion vector fields.< >

关键词： Neurons Image motion analysis Circuits computer architecture computer vision Robot vision systems Laboratories Shape Optical devices Retina

来源：评论

学校读者我要写书评

暂无评论

Parallel distributed networks for image smoothing and segmentation in analog VLSI

Parallel distributed networks for image smoothing and segmen...

引用

IEEE Conference on Decision and Control

作者： A. Lumsdaine J. Wyatt I. Elfadel Research Laboratory of Electronics Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA

Consideration is given to switched linear resistive networks and nonlinear resistive networks for image smoothing and segmentation problems in robot vision. The latter network type is derived from the former by way of an intermediate stochastic formulation, and a new result relating the solution sets of the two is given for the so-called zero-temperature limit. The authors present simulation studies of several continuation methods that can be gracefully implemented in analog VLSI and that seem to given good results for these nonconvex optimization problems.< >

关键词： Smoothing methods Image segmentation Intelligent networks Very large scale integration Stochastic processes Minimization methods computer vision Laboratories computer science Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

CONTROL POINT TRANSFORMS FOR SHAPE REPRESENTATION AND MEASUREMENT

引用

computer vision GRAPHICS AND IMAGE PROCESSING 1988年第1期42卷 87-111页

作者： PAGLIERONI, DW JAIN, AK Computer Vision Research Laboratory Department of Electrical and Computer Engineering University of California Davis California 95616 USA

A new fast transform from curve samples to least-squares normalized B-spline control points is developed and their relation to Fourier descriptors is established. Contour control point sequence scale, translation, and rotation are known to produce identical shape model variations. It is shown that under the conditions of our transform, such sequences are also directly applicable to efficient computation of many useful shape features or characteristics. First, methods for computing boundary curvature and mean contour sample from control points are presented. Then, transforms from contour control points to shape moments and projections are developed and tested.

关键词： MATHEMATICAL TRANSFORMATIONS

来源：评论

学校读者我要写书评

暂无评论

Hyperpyramids for vision-driven navigation

Hyperpyramids for vision-driven navigation

引用

Applications of Artificial Intelligence VI 1988

作者： Jain, R. Roth-Tabak, Y. Skifstad, K. Computer Vision Research Laboratory Electrical Engineering and Computer Science Department University of Michigan Ann ArborMI48109-2122 United States

If an autonomous vehilce is to operate in an environment of arbitrary complexity, it must be able to perceive the locations of the obstacles in its environment and store this information in a world model. It is important that the world model be structured in such a manner that the information may be easily utilized. An object-oriented data structure called Hyper-Pyramids is presented for representing the environment in the navigation problem. A summary of preliminary research efforts on the navigation problem is also presented. This includes work on the implementation and manipulation of octtree-like data structures, and the introduction of a new technique for the recovery of depth information from grey-scale images. © 1988 Proceedings of SPIE - The International Society for Optical engineering. All rights reserved.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Pyramidal edge detection and image representation 3

Pyramidal edge detection and image representation

引用

Visual Communications and Image Processing III 1988

作者： Schrift, A. Zeevi, Y.Y. Porat, M. Department of Electrical Engineering Computer Vision Laboratory Technion-Israel Institute of Technology Haifa32000 Israel

We present a scheme of extracting edge information from parallel spatial frequency bands. From these we create an integrated image of most significant edges of different scales. The frequency bands are realized using the formalism of a Gaussian pyramid in which the levels represent a bank of spatial lowpass filters. The integrated edge image is created in a top-down algorithm, starting from the smallest version of the image. The sequential algorithm uses mutual edge information of two consecutive levels to control the processing in the lower one. This edge detection algorithm constitutes an image-dependent nonuniform processing scheme. Computational results show that only 20%-50% of the operations are needed to create an edge pyramid, compared to the number required in the regular scheme. The proposed generic scheme of image-dependent processing can be also implemented with operators other than edge detectors to exploit the advantages inherent in biological processing of images. © 1988 SPIE. All rights reserved.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Pattern analysis and texture discrimination in the Gabor space

Pattern analysis and texture discrimination in the Gabor spa...

引用

International Conference on Pattern Recognition

作者： M. Porat Y.Y. Zeevi Vision Research and Computer Vision Laboratory Department of Electrical Engineering Technion-Israel Institute of Technology Haifa Israel

The basic biological principles of nonuniform image representation in the combined frequency-position space are utilized in an approach to image representation and processing. A scheme of image decomposition into optimal localized frequency operators, the so-called Gabor elementary functions which minimize the uncertainty inherent in image representation, is accordingly proposed. Applications to size-invariance and object-separable pattern analysis, localized texture discrimination, and representation by partial information are discussed, illustrating the advantages of the Gabor transform.< >

关键词： Pattern analysis Frequency Space technology Image representation Visual system Image sampling Image processing Shape computer vision Image decomposition

来源：评论

学校读者我要写书评

暂无评论

Wide baseline dynamic stereo: approximation and refinement

Wide baseline dynamic stereo: approximation and refinement

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： T.E. Weymouth S. Moezzi Computer Vision Research Laboratory Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA

Stereo algorithms using a wide baseline must cope with a large search space on top of the problems due to noise. A single pair of images is not a reliable source of depth information. One solution is to integrate the information from several image pairs. By incrementally refining estimates of the depth as the camera changes position, it is possible to build a description of the scene which, in turn, can be used as feedback to improve the extraction of depth information. The authors have developed a stereo algorithm based on correlation matching that is especially suited to being integrated into a proposed feedback loop. They have begun experiments with the integration of depth information over a sequence into a single environmental map.< >

关键词： Cameras Stereo vision Layout Data mining Working environment noise Joining processes computer vision Laboratories Feedback loop Noise reduction

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：