检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： C. Menard A. Leonardis Department for Pattern Recognition and Image Processing Technical University of of Vienna Vienna Austria Computer and InformationScience. Computer Vision Laboratory University of Ljubljana Ljubljana Slovenia

Stereo computation is one of the vision problems where the presence of outliers cannot be neglected. Most standard algorithms make unrealistic assumptions about noise distributions, which leads to erroneous results that cannot be corrected in subsequent postprocessing stages. In this paper we present a modification of the standard area-based correlation approach so that it can tolerate a significant number of outliers. The approach exhibits a robust behavior not only in the presence of mismatches but also in the case of depth discontinuities. The confidence measure of the correlation and the number of outliers provide two complementary sources of information which, when implemented in a multiresolution framework, result in a robust and efficient method. We present the results of this approach on a number of synthetic and real images.

关键词： Stereo vision computer vision Noise robustness Information resources Correlation Pattern recognition image processing Layout Cameras Laboratories

来源：评论

学校读者我要写书评

暂无评论

Robust recovery of eigenimages in the presence of outliers and occlusions

引用

Journal of Computing and Information Technology 1996年第1期4卷 25-38页

作者： Leonardis, Aleš Bischof, Horst Department for Pattern Recognition and Image Processing Technical University Vienna Treitlstraße 3/1832 ViennaA-1040 Austria Computer Vision Laboratory Faculty of Computer and Information Science University of Ljubljana Tržaška 25 Ljubljana1000 Slovenia

The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which successfully solves these problems. The major novelty of our approach lies in the way how the coefficients of the eigenimages are determined. Instead of computing the coefficients by a projection of the data onto the eigenimages. we extract them by a hvpothesize-and-test paradigm using subsets of image points. Competing hypotheses arc then subject to a selection procedure based on the Minimum Description Length principle. The approach enables us not only lo reject outliers and to deal with occlusions but also to simultaneously use multiple classes of eigenimages.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Bayesian approach to error concealment in encoded video streams

A Bayesian approach to error concealment in encoded video st...

引用

IEEE International Conference on image processing

作者： P. Salama N. Shroff E.J. Delp Computer Vision and Image Processing Laboratory Purdue Multimedia Testbed Laboratory School of Electrical Engineering Purdue University West Lafayette IN USA Purdue University System West Lafayette IN US

In ATM networks cell loss causes data to be dropped in the channel. When digital video is transmitted over these networks one must be able to reconstruct the missing data so that the impact of these errors is minimized. In this paper we describe a Bayesian approach to conceal these errors. Assuming that the digital video has been encoded using the MPEG1 or MPEG2 compression scheme, each frame is modeled as a Markov random field. A maximum a posteriori estimate of the missing macroblocks and motion vectors is described based on the model.

关键词： Bayesian methods Streaming media Intelligent networks Laboratories Markov random fields Video sequences Interpolation image reconstruction Motion estimation computer errors

来源：评论

学校读者我要写书评

暂无评论

Measuring the distance and orientation of a planar surface using nonstructured lighting

引用

SYSTEMS AND computerS IN JAPAN 1996年第8期27卷 83-92页

作者： Tsukiyama, T Member Electrotechnical Laboratory Tsukuba Japan 305 Tosbifumi Tsukiyama:graduated in 1972 from the Biological Engineering Department Osaka University where he also received his Dr. of Eng. degree. He joined Electrotechnical Laboratory Ministry of Tread and Industry (Japan) in 1972. At present he is Senior Researcher at Computer Vision Section Intelligent Systems Division ETL. He was a Visiting Researcher at University of Illinois during 1984–1985. He has been interested in vision system for mobile robots and image processing architectures. He is a member of the Society of Instrumental and Control Engineers Japan Robotics Society of Japan and Information Processing Society of Japan.

This paper proposes a method of 3-dimensional measurement of a planar surface by using two fixed light sources and a TV camera. A set of two images is recorded by the camera switching on each light alternately. The peak of the luminance distribution in each image is detected, and the orientation and distance of the planar surface are calculated. The position of the peak of a luminance distribution can be estimated accurately by using an image processing. The light sources can be conventional apparatus with no particular structure. The method is simple and suitable for a vision system on an indoor mobile robot.

关键词： distance to surface orientation of planar surface point light source luminance distribution ring light

来源：评论

学校读者我要写书评

暂无评论

Adaptability of K-L expansion technique for ambiguous face image retrieval

引用

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 1996年第10期79卷 35-46页

作者： Oda, M Akamatsu, S Fukamachi, H ATR Human Information Processing Laboratories Kyoto Japan 619-02 Shigeru Akamatsu received his B.E. M.E. and Dr. of Eng. degrees in Mathematical Enginwring and Instrumentation Physics in 1975 1977 and 1994 respectively from the University of Tokyo Japan. In 1977 he joined the Electrical Communications Laboratories Nippon Telegraph and Telephone Public Corporation Yokosuka Japan. From 1977 through 1985 he was engaged in the research and development of optical character recognition systems for handwritten Chmese characters. During the academic year 1985-86 he was a Visiting Researcher at the University of California Irvine California U.S.A. Until 1992 he was a Senior Research Engineer Supervisor at W Human Interface Laboratories and conducted research on human image recognition with a special interest in face recognition. Since 1992 he has been with ATR Human Information Processing Research Laboratories Kyoto Japan where he is currently Head of Department 2. His research interests include computational and cognitive studies on high-level vision with a special interest in facial information processing by man and computer. He is a member of the Institute of Electronics Information and Communication Engineers of Japan the Information Processing Society of Japan ACM and the IEEE Computer Society. Hidm Fukamachi received his B.E. degree in Image Technology from the Tokyo Institute of Polytechnics in 1990. He joined NTT Software Corp. in 1990 where he was engaged in the development of image processing software. Since 1993 he has been with ATR Human Information Processing Research Laboratories.

Some facial images are not necessarily clear images in the human brain. However, it can be easily judged whether a face matches the image in our mind;this is true even when the drawing or the expression of the target image is difficult to comprehend. This is because even if the image cannot be imagined like a picture, it does exist. The authors have proposed a system with which a retriever can retrieve an ambiguous target image from an image database. The system's retrieval efficiency and ease-of-retrieval were clarified by experiments using line drawn facial images. In this paper, the system is extended to photographs of faces. The most difficult problem in treating photographs is determining the retrieval key. One consideration is to add the subjective impressions or features of physical figures as keywords for each image data. Regardless of the method, however, significant manpower is necessary. The K-L expansion technique is used here, which has been verified as effective for face identification, and expect to need only a small amount of manpower. This paper investigates whether the technique can also be useful in ambiguous image retrieval.

关键词： ambiguous image image retrieval K-L expansion facial image subjective similarity

来源：评论

学校读者我要写书评

暂无评论

Texture segmentation using hierarchical wavelet decomposition

引用

PATTERN RECOGNITION 1995年第12期28卷 1819-1824页

作者： Salari, E Ling, Z Computer Vision and Image Processing Laboratory Department of Electrical Engineering University of Toledo Toledo OH 43606 U.S.A.

This paper presents a texture segmentation algorithm based on a hierarchical wavelet decomposition. Using Daubechies' four-tap filter, an original image is decomposed into three detail images and one approximate image. The decomposition can be recursively applied to the approximate image to generate a lower resolution of the pyramid. The segmentation starts at the lowest resolution using the K-means clustering scheme and textural features obtained from various sub-bands. The result of segmentation is propagated through the pyramid to a higher resolution with continuously improving the segmentation. The lower resolution levels help to build the contour of the segmented texture, while higher levels refine the process, and correct possible errors.

关键词： Texture segmentation Wavelet transform Clustering algorithm Multiresolution segmentation

来源：评论

学校读者我要写书评

暂无评论

Multiresolution sequential edge linking

Multiresolution sequential edge linking

引用

IEEE International Conference on image processing

作者： G.W. Cook E.J. Delp School of Electrical Engineering Computer Vision and Image Processing Laboratory Purdue University West Lafayette IN USA

We describe a multiresolution approach to edge detection using a sequential search algorithm. The use of a multiresolution image pyramid allows the integration of global edge information contained in lower resolutions to guide the sequential search at higher resolutions. As a consequence, the dependence on a priori knowledge of the image edges is greatly reduced. Estimating the sequential search parameters from lower resolution images provides for a more accurate and less costly search of edge paths in the image.

关键词： Joining processes image edge detection image resolution Spatial resolution Pixel computer vision image processing Signal to noise ratio Technological innovation Laboratories

来源：评论

学校读者我要写书评

暂无评论

A fast algorithm for video parsing using MPEG compressed sequences

A fast algorithm for video parsing using MPEG compressed seq...

引用

IEEE International Conference on image processing

作者： K. Shen E.J. Delp School of Electrical Engineering Computer Vision and Image Processing Laboratory Purdue University West Lafayette IN USA

Video parsing is a fundamental operation used in many digital video applications such as digital libraries and video servers. The accuracy and execution speed of the parsing algorithm is critical if large amounts of video data are to be processed, particularly in real-time. We present a new algorithm to reconstruct DC coefficient images of a DCT and motion compensation compressed video sequence, e.g. MPEG. The histograms of the DC coefficient images can be used to detect scene changes.

关键词： Video compression Transform coding Software libraries image reconstruction Discrete cosine transforms Motion compensation image coding Video sequences Histograms Layout

来源：评论

学校读者我要写书评

暂无评论

Error concealment techniques for encoded video streams

Error concealment techniques for encoded video streams

引用

IEEE International Conference on image processing

作者： P. Salama N.B. Shroff E.J. Coyle E.J. Delp School of Electrical Engineering Computer Vision and Image Processing Laboratory Purdue University West Lafayette IN USA

In this paper we describe two error-recovery approaches for MPEG encoded video over ATM networks. The first approach aims at reconstructing each lost pixel by spatial interpolation from the nearest undamaged pixels. The second approach recovers lost macroblocks by minimizing intersample variations within each block and across its boundaries. Moreover, a new technique for packing ATM cells with compressed data is also proposed.

关键词： Streaming media Asynchronous transfer mode Decoding Video compression image coding Video sequences computer errors computer vision image processing Laboratories

来源：评论

学校读者我要写书评

暂无评论

AN INVESTIGATION OF JPEG image AND VIDEO COMPRESSION USING PARALLEL processing

AN INVESTIGATION OF JPEG IMAGE AND VIDEO COMPRESSION USING P...

引用

1994 IEEE International Conference on Acoustics, Speech and Signal processing

作者： COOK, GW DELP, EJ Computer Vision Ond Image Processing Laboratory School of Electrical Engineering Purdue University West Lafayette IN 47907-1285 United States

The problem inherent with any digital image (or digital video) system is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop more complex algorithms that compress images to lower data rates with better fidelity. One approach that can be used to increase the execution speed of these complex algorithms is through the use of parallel processing. In this paper we address one aspect of the parallel implementation of the JPEG still image compression standard on the MasPar MP-1, a massively parallel SIMD computer. We develop a novel byte alignment algorithm used to efficiently output compressed data from the parallel system. © 1994 IEEE.

关键词： image compression

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：