检索结果-内蒙古大学图书馆

Object oriented motion-segmentation for video-compression in the CNN-UM

JOURNAL OF VLSI signal processing SYSTEMS FOR signal image AND VIDEO TECHNOLOGY 1999年第2-3期23卷 479-496页

作者： Szirányi, T László, K Czúni, L Ziliani, F Hungarian Acad Sci Inst Comp & Automat Analog & Neural Comp Lab H-1111 Budapest Hungary Univ Veszprem Dept Image Proc & Neurocomp H-8200 Veszprem Hungary

Object-oriented motion segmentation is a basic step of the effective coding of image-series. Following the MPEG-4 standard we should define such objects. In this paper, a fully parallel and locally connected computation model is described for segmenting frames of image sequences based on spatial and motion information. The first type of the algorithm is called early segmentation. It is based on spatial information only and aims at providing an over-segmentation of the frame in real-time. Even if the obtained results do not minimize the number of regions, it is a good starting point for higher level post processing, when the decision on how to regroup regions in object can rely on both spatial and temporal information. In the second type of the algorithm stochastic optimization methods are used to form homogenous dense optical vector fields which act directly on motion vectors instead of 2D or 3D motion parameters. This makes the algorithm simple and less time consuming than many other relaxation methods. Then we apply morphological operators to handle disocclusion effects and to map the motion field to the spatial content. computer simulations of the CNN architecture demonstrate the usefulness of our methods. All solutions in our approach suggest a fully parallel implementation in a newly developed CNN-UM VLSI chip architecture.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational representation of increasing lattice-valued image operators

Computational representation of increasing lattice-valued im...

引用

Conference on neural, Morphological, and stochastic methods in image and signal processing

作者： SINHA, D DOUGHERTY, ER CUNY COLL STATEN ISL NEW YORKNY

ISBN: (纸本)0819419273

Computational mathematical morphology provides zeta-function-based representation for windowed, translation-invariant image operators taking their values in a complete lattice. image operators are induced via windowing by product lattice operators and, in both the increasing and nonincreasing cases, these reduce to classical logical representation for binary operators. The present paper presents the image-operator theory for increasing filters. In particular, it treats gray-to-binary and gray-to-gray morphological operators, as well as representation of lattice-valued stack filters via threshold decomposition.

关键词： Binary data Digital filtering Electroluminescence Mathematical morphology Fermium Frequency modulation image filtering Logic computer architecture image processing

来源：评论

学校读者我要写书评

暂无评论

Learning to Predict Visibility and Invisibility from Occlusion Events 8

Learning to Predict Visibility and Invisibility from Occlusi...

引用

8th International Conference on neural Information processing Systems, NIPS 1995

作者： Marshall, Jonathan A. Alley, Richard K. Hubbard, Robert S. Department of Computer Science CB 3175 Sitterson Hall University of North Carolina Chapel HillNC27599-3175 United States

Visual occlusion events constitute a major source of depth information. This paper presents a self-organizing neural network that learns to detect, represent, and predict the visibility and invisibility relationships that arise during occlusion events, after a period of exposure to motion sequences containing occlusion and disocclusion events. The network develops two parallel opponent channels or "chains" of lateral excitatory connections for every resolvable motion trajectory. One channel, the "On" chain or 'Visible" chain, is activated when a moving stimulus is visible. The other channel, the "Off" chain or "invisible" chain, carries a persistent, amodal representation that predicts the motion of a formerly visible stimulus that becomes invisible due to occlusion. The learning rule uses disinhibition from the On chain to trigger learning in the Off chain. The On and Off chain neurons can learn separate associations with object depth ordering. The results are closely related to the recent discovery (Assad & Maunsell, 1995) of neurons in macaque monkey posterior parietal cortex that respond selectively to inferred motion of invisible stimuli. © NIPS 1995: Proceedings of the 8th International Conference on neural Information processing Systems. All rights reserved.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

DECONVOLUTION OF MULTIPLE imageS OF THE SOME OBJECT

引用

APPLIED OPTICS 1994年第11期33卷 2157-2162页

作者： YAROSLAVSKY, LP CAULFIELD, HJ RUSSIAN ACAD SCI INST INFORMAT TRANSMISS PROBLEMS MOSCOW 101447 RUSSIA ALABAMA A&M UNIV DEPT PHYS NORMAL AL 35762 USA

Deconvolution of images of the same object from multiple sensors with different point spread functions as suggested by Berenstein [Proc. IEEE 78, 723 (1990);stochastic and neural methods in signal processing, image processing, and computer vision, S. Chen, ed., Proc. Soc. Photo-Opt. Instrum. Eng. 1569, 35 (1991)], opens new opportunities in solving the image-deconvolution problem, which has challenged researchers for years. We attack this problem in a more realistic formulation than that used by Berenstein;it explicitly takes into account image sensor noise and the necessity for adaptive restoration with estimation of all required signal and noise parameters directly from the observed noisy signals. We show that arbitrary restoration accuracy can be achieved by the appropriate choice of the number of sensor channels and the signal-to-noise ratio in each channel. The results are then extended to the practically important situation when true images in different sensor channels are not identical.

关键词： image deconvolution image processing image quality Machine vision Point spread function signal processing

来源：评论

学校读者我要写书评

暂无评论

HIERARCHICAL MARKOV RANDOM-FIELDS WITH STABLE POINTS 3

HIERARCHICAL MARKOV RANDOM-FIELDS WITH STABLE POINTS

引用

Conference on neural and stochastic methods in image and signal processing III

作者： BUDZBAN, G STIREWALT, T SO ILLINOIS UNIV DEPT MATHCARBONDALEIL 62901

ISBN: (纸本)0819416282

Markov random field techniques for region labeling have become prevalent in image processing research since the seminal work of Geman and Geman in the early 1 980's. Their use in actual working systems, however, has been hampered by a number ofdifficult problems. Perhaps the most intractable of the problems has been the convergence rate of the algorithm. In this paper, we present a technique that introduces stable points in the labeling array of the random field. The stable points are determined by using a simple statistical pixel classifier together with a confidencemeasure at each pixel. The most confident (top 1% )pixellabels are selected and these labels are used to initiate the evolution of the random field. The stable points introduce pockets of "certainty" in the evolution of the process. The labeling is locally stable and even small numbers of stable points vastly decrease convergence rates of the algorithm.

关键词： Algorithms Magnetorheological finishing Computing systems stochastic processes Machine vision computer vision technology Detection and tracking algorithms image filtering Probability theory Systems modeling

来源：评论

学校读者我要写书评

暂无评论

LOGARITHMIC CONVERGENCE OF RANDOM HEURISTIC-SEARCH 3

LOGARITHMIC CONVERGENCE OF RANDOM HEURISTIC-SEARCH

引用

Conference on neural and stochastic methods in image and signal processing III

作者： VOSE, MD UNIV TENNESSEE DEPT COMP SCIKNOXVILLETN 37996

A general class of stochastic search algorithms, random heuristic search, is reviewed. A general convergence theorem for this class is proved. Since the simple genetic algorithm is an instance of random heuristic sear... 详细信息

ISBN: (纸本)0819416282

关键词： Genetic algorithms Binary data stochastic processes computer science Genetics Optical spheres Polonium Transition metals

来源：评论

学校读者我要写书评

暂无评论

KNOWLEDGE-DIRECTED EEG signal ANALYSIS WITH RECURRENT CONTEXT-LEARNING neural NETWORKS 3

KNOWLEDGE-DIRECTED EEG SIGNAL ANALYSIS WITH RECURRENT CONTEX...

引用

Conference on neural and stochastic methods in image and signal processing III

作者： FU, LM UNIV FLORIDA DEPT COMP & INFORMAT SCIGAINESVILLEFL 32611

ISBN: (纸本)0819416282

EEG signal analysis is a key to the understanding of brain activities. Traditionally, this process involves quantifying the signal in terms of frequency and amplitude, on which basis a number of waveforms have been identified. The complexity of EEG signals warrants the construction of a computer program for automatic interpretation. Symbolic knowledge is being built up for correlating the quantity of certain waveforms and brain behavior, and this knowledge can be readily programmed into a knowledge-based system (expert system) for various purposes such as cognitive research, neurological evaluation, and clinical diagnosis. The presented approach employs a knowledge-based neural network in conjunction with a recurrent neural network model as a memory device which conducts context processing. This research emphasizes the need for the exploitation of "knowledge" and "context" in signal analysis. © 1994 SPIE.

关键词： EEG CONTEXT KNOWLEDGE-BASED neural NETWORKS PATTERN ANALYSIS

来源：评论

学校读者我要写书评

暂无评论

Two dimensional chromosomes and their application to computer vision 3

Two dimensional chromosomes and their application to compute...

引用

neural and stochastic methods in image and signal processing III 1994

作者： Bills, Trent Samal, Ashok University of Nebraska-Lincoln Department of Computer Science and Engineering LincolnNB68588-0115 United States

Genetic algorithms have been used for many diverse applications. In these applications, possible solutions are represented by linear strings. In many other applications, however, strings can not adequately model the solutions. A very large class of such problems is in the area of computer vision and image processing. Here the images are two dimensional and the objects present in them are either two or three dimensional. Hence the strings and the associated genetic operators are not applicable directly. It is necessary to allow the genetic algorithm to operate directly on images or two dimensional arrays since the underlying processes that are responsible for the formation of the solutions are inherently two dimensional in nature, e.g. rotation, translation, etc. We have extended the concepts defined for linear strings to two dimensional chromosomes. Several new concepts have also been developed to describe genetic operators on two dimensional chromosomes. The traditional genetic operators are also extended and some new geometric operators are also introduced for the two dimensional chromosomes. The operators include the primary geometric transformations, i.e. translation, rotation, and scaling. Both the genetic and geometric operators lend themselves to parallel implementations. With an efficient parallel implementation, this method could be used in real-time vision systems. A typical computer vision problem is used to demonstrate the use of the operators. A prototype parallel implementation on a CM-2 (SIMD) has been implemented and a CM-S (MIMD) version is currently being explored. © 1994 SPIE.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

neural-NETWORK ARCHITECTURE FOR OBJECT RECOGNITION 3

NEURAL-NETWORK ARCHITECTURE FOR OBJECT RECOGNITION

引用

Conference on neural and stochastic methods in image and signal processing III

作者： PENG, MK NAPIER UNIV DEPT ELECTEDINBURGH EH14 1DJSCOTLAND

ISBN: (纸本)0819416282

Model-based 2-D object recognition is investigated by using neural network. Object recognition is treated as a subgraph matching. A neural network system is proposed to complete subgraph matching. The system consists of a large Hopfield network, called global network, and several small Hopfield networks, called subnetworks. The system starts with a randomly set initial state of the global network. The subnetworks are dynamically created based on the stable output state of the global network and then the outputs of the subnetworks are feedbacked to the global network to reset its initial state. This process continues until the whole system is stabilized, where the optimal subgraph matching is obtained. This method avoids the local minimum problem from using a single Hopfield network and also uses much less calculating time than simulated annealing algorithm. computer simulation is done to verify it.

关键词： neural NETWORK HOPFIELD NETWORK OBJECT RECOGNITION SUBGRAPH MATCHING

来源：评论

学校读者我要写书评

暂无评论

Unification of several image compression methods

Unification of several image compression methods

引用

Hybrid image and signal processing IV

作者： Liu, Ying Savannah State College (United States)

In this paper, several image compression theories are unified. These theories are: Hilbert image compression, Fractal image compression, image compression using Boltzmann machines, using stochastic artificial neural n... 详细信息

ISBN: (纸本)0819415421

关键词： computer programming image compression Fractal analysis stochastic processes Dynamical systems Binary data Iterated function systems Space operations Artificial neural networks Neurons

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：