检索结果-内蒙古大学图书馆

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： YEUNG, K ZAKARAUSKAS, P MCCRAY, A Defence Research Establishment Pacific FMO Victoria V0S 1B0 BC Canada

ISBN: (纸本)081940697X

This paper presents a neural network approach to determine the heading orientation of a known object in a noisy image. The grey-scaled image is first preprocessed by the following four procedures: 1. An edge map of the object is extracted using the Sobel edge operator;2. The discrete 2D Fourier transform is applied to the edge map to eliminate the translational variance;3. The Fourier power coefficients are mapped into a polar coordinate system;4. The amplitudes of the Fourier coefficients in each five-degree angular sector are summed to form a one-dimensional input vector to the neural network. A backpropagation neural network with one hidden layer was trained with a sequence of seven noisefree object outlines with heading ranging from 0 to 90 degrees in 15 degree increments. After the training was complete, the network was tested with three noisy images taken from randomly selected object orientations. The network successfully classified the appropriate headings in each case. These results illustrate the robustness of this neural network design in performing heading classification from noisy images. © 1991 SPIE. All rights reserved.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

CONSIDERING MULTIPLE SURFACE HYPOTHESES IN A BAYESIAN HIERARCHY

CONSIDERING MULTIPLE SURFACE HYPOTHESES IN A BAYESIAN HIERAR...

引用

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： LAVALLE, SM HUTCHINSON, SA Univ. of Illinois (United States)

ISBN: (纸本)081940697X

This paper presents a probabilistic approach to segmentation that maintains a set of competing, plausible segmentation hypotheses. This is in contrast to previous approaches, in which probabilistic methods are used to converge to a single segmentation. The benefit of the approach is that belief values associated with segmentation hypotheses can be used to guide the recognition process, and the recognition process can, in turn, exert influence on the belief values associated with segmentation hypotheses in the network. In this way, segmentation and recognition can be coupled together to achieve a combination of expectation-driven segmentation and data-driven recognition. Algorithms were based on the formalism of Bayesian belief networks. By storing segmentation hypotheses in a tree structured network, the storage demands associated with maintaining the competing hypotheses can be limited. An implicit representation for segmentation hypotheses is introduced (without this implicit representation, the power set of region groupings would need to be enumerated). Likelihood measures are used both to control the expansion of the hypothesis tree and to evaluate belief in hypotheses. Local likelihood measures are used during an expansion phase, in which leaf nodes are refined into more specific hypotheses. Global likelihood measures are applied during an evaluation phase. The global likelihood measures are derived by fitting quadric surfaces to the range data. By using this expand and evaluate approach guided by a measure of entropy defined on the leaves of the tree, the application of costly numerical fitting algorithms can be limited to a small number of nodes in the tree.

关键词： image segmentation image processing signal processing stochastic processes Computer vision technology Machine vision Detection and tracking algorithms 3D image processing image processing algorithms and systems Laser scanners

来源：评论

学校读者我要写书评

暂无评论

CHALLENGES OF VISION THEORY - SELF-ORGANIZATION OF neural MECHANISMS FOR STABLE STEERING OF OBJECT-GROUPING DATA IN VISUAL-MOTION PERCEPTION

CHALLENGES OF VISION THEORY - SELF-ORGANIZATION OF NEURAL ME...

引用

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： MARSHALL, JA Univ. of North Carolina/Chapel Hill (United States)

ISBN: (纸本)081940697X

Psychophysical studies on motion perception suggest that human visual systems perform certain nonlocal operations. In some cases, data about one part of an image can influence the processing or perception of data about another part of the image, across a long spatial range. In others, data about nearby parts of an image can fail to influence one another strongly, despite their proximity. Several types of nonlocal interaction may underlie cortical processing for accurate, stable perception of visual motion, depth, and form: (1) trajectory-specific propagation of computed moving stimulus information to successive image locations where a stimulus is predicted to appear; (2) grouping operations (establishing linkages among perceptually related data); (3) scission operations (breaking linkages between unrelated data); and (4) steering operations, whereby visible portions of a visual group or object can control the representations of invisible or occluded portions of the same group. Nonlocal interactions like these could be mediated by long-range excitatory horizontal intrinsic connections (LEHICs), discovered in visual cortex of several animal species. LEHICs often span great distances across cortical image space. Typically, they have been found to interconnect regions of like specificity with regard to certain receptive field attributes, e.g., stimulus orientation. It has recently been shown that several visual processing mechanisms can self-organize in model recurrent neural networks using unsupervised `EXIN' (excitatory + inhibitory) learning rules. Because the same rules are used in each case, EXIN networks provide a means to unify explanations of how different visual processing modules acquire their structure and function. EXIN networks learn to multiplex (or represent simultaneously) multiple spatially overlapping components of complex scenes, in a context-sensitive fashion. Modeled LEHICs have been used together with the EXIN learning rules to show how visual expe

关键词： Neurons Visualization image processing Visual system signal processing Visual process modeling Computer vision technology Machine vision stochastic processes Transparency

来源：评论

学校读者我要写书评

暂无评论

ROBUST STATISTICAL-METHOD FOR BACKGROUND EXTRACTION IN image SEGMENTATION

ROBUST STATISTICAL-METHOD FOR BACKGROUND EXTRACTION IN IMAGE...

引用

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： RODRIGUEZ, AA MITCHELL, OR IBM Multimedia Technology Dept. (United States) Univ. of Texas/Arlington (United States)

ISBN: (纸本)081940697X

A method that adaptively extracts the gray-tone distribution of the background of the image without a priori knowledge is described, and the method's performance is shown to be superior when log-transformed image data is used. The image is decomposed into rectangular regions to adaptively extract the background's gray-tone distribution throughout the image. The background distribution of each region is modeled with a left-half and right-half Gaussian to compensate for its asymmetrical nature. Statistical criteria are used to classify each rectangular region as background-homogeneous, object-homogeneous, or uncertain. Measured statistical parameters of background homogeneous regions are propagated throughout the image to estimate the statistics of object-homogeneous regions and uncertain regions. The local background of each region is extracted by using the measured or estimated statistical parameters to compute the left and right shoulder thresholds of the background distribution. A logarithmic transformation implementation for gray-tone image data and a procedure to map log-transformed data into integer-valued histograms are proposed. The background extraction method is shown to yield superior results when log-transformed image data is used. The proposed algorithm is robust by virtue of the logarithmic transformation implementation; it can perform over a wide range of applications without parameter adjustments or human interaction. The algorithm performs successfully whether the image contains objects darker and/or brighter than the background, or no object at all. The method is demonstrated on background-only scenes imaged under different lighting conditions, industrial scenes, and outdoor scenes of moderate complexity that exhibit different smooth backgrounds within the same image.

关键词： image segmentation Data modeling Statistical analysis Computer vision technology Machine vision image processing signal processing stochastic processes Feature extraction image analysis

来源：评论

学校读者我要写书评

暂无评论

FUZZY-LOGIC AND neural NETWORKS IN ARTIFICIAL-INTELLIGENCE AND PATTERN-RECOGNITION

FUZZY-LOGIC AND NEURAL NETWORKS IN ARTIFICIAL-INTELLIGENCE A...

引用

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： SANCHEZ, E Institut Mediterraneen de Technologie (France)

ISBN: (纸本)081940697X

With the use of fuzzy logic techniques, neural computing can be integrated in symbolic reasoning to solve complex real world problems. In fact, artificial neural networks, expert systems, and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A model of Fuzzy Connectionist Expert System is introduced, in which an artificial neural network is designed to construct the knowledge base of an expert system from, training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the synaptic connections in an AND-OR structure: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through min-max fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feedforward network is described and first illustrated in a biomedical application (medical diagnosis assistance from inflammatory-syndromes/proteins profiles). Then, it is shown how this methodology can be utilized for handwritten pattern recognition (characters play the role of diagnoses): in a fuzzy neuron describing a number for example, the linguistic weights represent fuzzy sets on cross-detecting lines and the numerical weights reflect the importance (or weakness) of connections between cross-detecting lines and characters.

关键词： FUZZY LOGIC SYMBOLIC neural NETWORKS LINGUISTIC WEIGHTS WEIGHTED MINIMUM OF MAXIMA MEDICAL DIAGNOSIS HAND-WRITTEN CHARACTER RECOGNITION

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional signal deconvolution: Design issues related to a novel multisensor-based approach

Two-dimensional signal deconvolution: Design issues related ...

引用

stochastic and neural methods in signal processing, image processing, and Computer Vision 1991

作者： Sicliropoulos, N.D. Baras, J.S. Berenstein, C.A. Systems Research Center University of Maryland College ParkMD20742 United States

We employ recent results of analysis in several complex variables to come up with a set of compactly supported approximate deconvolution kernels for the reconstruction of a two dimensional signal based on multiple linearly degraded versions of the signal with a family of kernels that satisfy suitable technical conditions. We discuss the question of convergence of the proposed deconvolution kernels, present simulation results that demonstrate the gain in bandwidth, and propose two data parallel grid layouts for the off-line computation of the deconvolution kernels. © 1991 SPIE. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

OPTIC FLOW-MULTIPLE INSTANTANEOUS RIGID MOTIONS

OPTIC FLOW-MULTIPLE INSTANTANEOUS RIGID MOTIONS

引用

CONF ON stochastic AND neural methods IN signal processing, image processing, AND COMPUTER VISION

作者： ZHUANG, XH WANG, T ZHANG, P Univ. of Missouri/Columbia (United States) Zhejiang Univ. (China) Univ. of Washington (United States)

ISBN: (纸本)081940697X

In Zhuang et al. (1988), a linear algorithm was presented to estimate a single instantaneous rigid motion from optic flow image point data. In order to obtain reasonable answers, however, the data must be quite accurate. This was shown by a lot of simulated experiments. As was well recognized, all machine vision feature extractors, recognizers, and matchers explicitly or implicitly needed for computing optic flow are unavoidably error prone and seem to make occasional errors which indeed are blunders. The realistic assumption for errors in optic flow should be a contaminated Gaussian noise which is a regular white Gaussian noise with probability 1 - (epsilon) plus an outlier process with probability (epsilon) , Huber (1981). Either the linear algorithm or the least-squares estimator are very sensitive to minor deviations from the Gaussian noise model assumption. In Haralick et al. (1989), the classical M-estimator was successfully applied to solve a single pose estimation from corresponding point data. However, lots of experiments conducted in Haralick et al. (1989) showed that the M-estimator only allowed a low proportion of outliers. For multiple pose segmentation and estimation, an estimator of high robustness is needed. A highly robust estimator called by the MF-estimator for general regression is presented and is applied to an important problem in computer vision, i.e., segmenting and estimating multiple instantaneous rigid motions from optic flow data. To be realistic, the observed or processed optic flow data are contaminated by various noises including outliers. Notationally, `MF' represents an abbreviation of `Model Fitting.' The MF- estimator is a result of partially modeling the unknown log likelihood function.

关键词： Machine vision Computer vision technology Motion estimation image processing image segmentation Motion analysis stochastic processes signal processing Visual process modeling Motion models

来源：评论

学校读者我要写书评

暂无评论

Texture classification and neural network methods

Texture classification and neural network methods

引用

Applications of Artificial neural Networks ii

作者： Visa, Ari J. Helsinki Univ. of Technology Espoo Finland

ISBN: (纸本)0819405787

Some neural network based methods for texture classification and segmentation have been published. The motivation for this kind of work might be doubted, because there are many traditional methods that work well. In this paper, a neural network based method for stochastic texture classification and segmentation suggested by Visa is compared with traditional K- means and k-nearest neighbor classification methods. Both simulated and real data are used. The complexity of the considered methods is also analyzed. The conclusion is the K-means method is the least successful of the three tested methods. The developed method is slightly more powerful than the k-nearest neighbor method for map sizes 9 × 9 and 10 × 10. The differences are, however, quite small. This means that the choice of classification method depends more on other aspects, like computational complexity and learning capability, than on the classification capability.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

A fast algorithm for a neocognitron neural network with back-propagation

A fast algorithm for a neocognitron neural network with back...

引用

stochastic and neural methods in signal processing, image processing, and Computer Vision 1991

作者： Qing, Pu Means, Robert W. HNC Inc. 5501 Oberlin Drive San DiegoCA92121 United States

The neocognitron is a neural network that consists of many layers of partially connected cells. In this paper, we propose a new neocognitron architecture called the Multi-layer NEOcognitron with BackPropagation learning (MNEOBP), and show that the original Neocongnitron that learned by backpropagation1'2 is a special case of what we propose here. The MNEOBP has a number of advantages: a) The algorithm for the MNEOBP is 4 times faster thatn the earlier algorithm since the number of cells calculated is reduced by a factor of 4. b) During the learning process, the mask (kernel) size is changed. This can speed up the training time by almost a factor of 3. c) The MNEOBP architecture can be implemented with a new digital neural network VLSI chip set called the Vision Processor (ViP).3 The ViP exploits the convolution structure of the network and can processes a single 32 x 32 input layer in only 25.6 microseconds with an 8 x 8 receptive field kernel. © 1991 SPIE. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

stochastic AND DETERMINISTIC NETWORKS FOR TEXTURE SEGMENTATION

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1990年第6期38卷 1039-1049页

作者： MANJUNATH, BS SIMCHONY, T CHELLAPPA, R UNIV SO CALIF INST SIGNAL & IMAGELOS ANGELESCA 90089

Several texture segmentation algorithms based on deterministic and stochastic relaxation principles, and their implementation on parallel networks, are described. The segmentation process is posed as an optimization problem and two different optimality criteria are considered. The first criterion involves maximizing the posterior distribution of the intensity field given the label field (maximum a posteriori estimate). The posterior distribution of the texture labels is derived by modeling the textures as Gauss Markov random fields (GMRFs) and characterizing the distribution of different texture labels by a discrete multilevel Markov model. A stochastic learning algorithm is proposed. This iterated hill-climbing algorithm combines fast convergence of deterministic relaxation with the sustained exploration of the stochastic algorithms, but is guaranteed to find only a local minimum. The second optimality criterion requires minimizing the expected percentage of misclassification per pixel by maximizing the posterior marginal distribution, and the maximum posterior marginal algorithm is used to obtain the corresponding solution. All these methods implemented on parallel networks can be easily extended for hierarchical segmentation; results of the various schemes in classifying some real textured images are presented.< >

关键词： stochastic processes image segmentation neural networks Markov random fields Simulated annealing Computer vision Optical computing Gaussian distribution Hopfield neural networks Remote sensing

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：