检索结果-内蒙古大学图书馆

Spatial depth extraction using random stereograms in analogic CNN framework

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第1期24卷 69-92页

作者： Radvanyi, AG Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences POB 63 H-1518 Budapest Hungary

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robustness of cellular neural networks in image deblurring and texture segmentation

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第3期24卷 381-396页

作者： Sziranyi, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) pf. 63 H-1518 Budapest Hungary

Template parameters of cellular neural networks (CNNs) should be robust enough to random variability of VLSI tolerances and noise. Using the CNN for image processing, one of the main problems is the robustness of a given task in a real VLSI chip. It will be shown that very different tasks such as 2D or 3D deconvolution and texture segmentation can be solved in a real VLSI CNN environment without significant loss of efficiency and accuracy under low precision (about 6-8 bits) and random variability of the VLSI parameters. The CNN turns out to be very robust against template noise, image noise, imperfect estimation of templates and parameter accuracy. The parameters of a template are tuned using genetic learning. These optimized parameters depend on the precision of the architecture. It was found that about 6-8 bits of precision is enough for a complicated multilayer deconvolution, while only 4 bits of precision is enough for difficult texture segmentation in the presence of noise and parameter variances, The tolerance sensitivity of template parameters is considered for VLSI implementation. Theory and examples are demonstrated by many results using real-life microscopic images and natural textures.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

SUBPIXEL PATTERN-RECOGNITION BY IMAGE HISTOGRAMS

引用

PATTERN RECOGNITION 1994年第8期27卷 1079-1092页

作者： SZIRANYI, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) P.O. Box 63 H-1518 Budapest Hungary

Recognition of small patterns covering only a few pixels in an image cannot be done by conventional recognition methods. A theoretically new pattern recognition method has been developed for undersampled objects which are (much) smaller than the window-size of a picture element (pixel), i.e. these objects are of subpixel size. The proposed statistical technique compares the gray-level histogram of the patterns of a set of scanned objects to be examined with the (calculated) gray-level densities of different (in shape or size) possible objects, and the recognition is based on this comparison. This method does not need high-precision movement of scanning sensors or any additional hardware. Moreover, the examined patterns should be randomly distributed on the screen, or a random movement of camera is (or target or both are) needed. Effects of noise are analysed, and filtering processes are suggested in the histogram domain. Several examples of different object shapes (triangle, rectangle, square, circle, curving lines, etc.) are presented through simulations and experiments. A number of possible application areas are suggested, including astronomy, line-drawing analysis and industrial laser measurements.

关键词： SUBPIXEL-RECOGNITION HISTOGRAM NOISE FILTERING UNDERSAMPLING SUPERRESOLUTION IMAGE ANALYSIS PATTERN CLASSIFICATION CONVOLUTION STATISTICAL PATTERN RECOGNITION LIGHT-SENSOR ARRAYS DENSITY ESTIMATION

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of postage stamps using an iterative approach of CNN

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 1996年第10期E79A卷 1741-1746页

作者： Kishida, J Rekeczky, C Nishio, Y Ushida, A Faculty of Engineering Tokushima University Tokushima-shi 770 Japan Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences 27 H-1111 Budapest Kende-u. 13-17 Hungary

In this article, a new analogic CNN algorithm to extract features of postage stamps in fray-scale images is introduced. The Gradient Controlled Diffusion method plays an important role in the approach. In our algorithm, it is used for smoothing and separating Arabic figures drawn with a color which is similar to the background color. We extract Arabic figures in postage stamps by combining Gradient Controlled Diffusion with nearest neighbor linear CNN template and logic operations. Applying the feature extraction algorithm to different test images it has been verified that it is also effective in complete segmentation problems.

关键词： cellular neural networks analogic algorithm image processing feature extraction gradient controlled diffusion

来源：评论

学校读者我要写书评

暂无评论

Markov random field image segmentation using cellular neural network

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-FUNDAMENTAL THEORY AND APPLICATIONS 1997年第1期44卷 86-89页

作者： Sziranyi, T Zerubia, J Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA-SZTAKI) Budapest Hungary I.N.R.I.A. Sophia Antipolis Sophia-Antipolis France

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image processing toot is coming into consideration, Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein se use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN, We are able to implement a (pseudo) random held generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell, We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw, With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms, In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits, Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64, +64), the accuracy is 0.002) can result in an effective and acceptable segmentation.

关键词： Markov processes VLSI analogue integrated circuits analogue processing circuits cellular neural nets estimation theory image segmentation neural chips neural net architecture parallel algorithms probability CNN UM architecture Markov random field image s Parallel algorithms Cellular neural networks neural network hardware Probability estimation theory image segmentation neural net architecture Analog integrated circuits analogue processing circuits Very large scale integration Markov random fields Markov chain

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired flight control and visual search with CNN technology

Bio-inspired flight control and visual search with CNN techn...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： C. Rekeczky D. Balya G. Timar I. Szatmari AnaLogical and Neural Computing Systems Laboratory Computer and Automation Institute of the Hungarian Academy of Sciences Budapest Hungary Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this paper it is shown that by building on parallel topographic CNN preprocessing of image flows, efficient terrain exploration and visual navigation algorithms can be developed. The approach combines several channels of nonlinear spatio-temporal feature detectors within an analogic CNN algorithm and produces unique binary maps of salient feature locations. This preprocessing scheme is embedded into a multi-target tracking (MTT) framework where these features are statistically described and assigned to numbered tracks. The MTT output has two distinct roles. First, its feature descriptors drive a classifier based on the adaptive resonance theory (ART), which is also implemented on CNN architecture. Second, it provides an optical flow ("target displacement") estimate to the navigation system, which in turn calculates the flight control parameters (Yaw-Pitch-Roll). An upper level visual attention and selection mechanism uses both the feature descriptors and the optical flow estimates to automatically adjust the focus and scale (zoom) during navigation. The paper describes the architecture and the algorithmic frameworks and provides the first experimental results on aerial video-flows.

关键词： Aerospace control Cellular neural networks Navigation Target tracking Biomedical optical imaging Nonlinear optics Image motion analysis Computer vision Detectors Resonance

来源：评论

学校读者我要写书评

暂无评论

Collision prediction via the CNN Universal Machine

Collision prediction via the CNN Universal Machine

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： V. Gal T. Roska Analogical & Neural Computing Systems Laboratory at the computer Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Hungary

We present an analogic CNN algorithm that estimates the time to an impending collision between an approaching object and the observer. Calculation is based on a context insensitive method, which is well known in neuro... 详细信息

关键词： Cellular neural networks Turing machines Animals Equations Geometrical optics Object detection Image edge detection Detectors Pixel Optical arrays

来源：评论

学校读者我要写书评

暂无评论

Real-life application case studies using CMOS 0.8 /spl mu/m CNN universal chip: analogic algorithm for motion detection and texture segmentation

Real-life application case studies using CMOS 0.8 /spl mu/m ...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： P. Foldesy A. Zarandy P. Szolgay T. Sziranyi Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

Using a 20/spl times/22 CNN Universal Machine chip two application case studies are presented. A new analogic CNN algorithm is shown to detect objects having larger size than a given value on black-and-white image sequences moving in a given range of direction and speed (17 /spl mu/s processing speed could be achieved). An extremely fast texture classification analogic algorithm is given next with approximately 2 /spl mu/s processing speed and with less than 5% misclassification error rate for 4 natural textures in a real-life testing environment.

关键词： Computer aided software engineering Cellular neural networks Switches Logic Motion detection Turing machines Testing Prototypes Registers Thyristors

来源：评论

学校读者我要写书评

暂无评论

High speed stand-alone visual decision maker device based on focal plane analogic processor array chip

High speed stand-alone visual decision maker device based on...

引用

IEEE International Workshop on Virtual and Intelligent Measurement systems

作者： L. Torok A. Zarandy T. Roska Analogical & Neural Computing Systems Laboratory at Computer and Automation Research Institute of the Hungarian Academy of Sciences Budapest Hungary

ISBN: (纸本)0780365682

Newly emerging problems require high speed decision making based on visual perception of the environment. A project was set up to construct an intelligent agent like self-contained device that is capable to act in real-time and show collaborative behavior. Giving the hardware basis for decisions to be made a cellular nonlinear network CNN (Chua and Yang, 1988) chip implementation's optical input is used in combination with the cooperative devices' information that is received via binary ports and serial ports. The proposed design is a self-contained compact device that is prepared to operate stand-alone for up to 10 hours running on medium sized batteries while doing measurements, logging and collaborating with its environment via parallel port (for image transfer), RS-232 port (using modbus, profibus, PPP protocols) and binary I/O-s. Intelligent power module, optical isolation, watch dog capability is also considered.

关键词： Collaboration High speed optical techniques Nonlinear optics Decision making Visual perception Intelligent agent Hardware Cellular networks Cellular neural networks Nonlinear optical devices

来源：评论

学校读者我要写书评

暂无评论

Optimal CNN templates for deconvolution

Optimal CNN templates for deconvolution

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： L. Orzo Analogical & Neural Computing Systems Laboratory at the Computer and Automation Research Institute of the Hungarian Academy of Sciences Budapest Hungary

A simplified version of the gradient descent method is introduced as a straightforward way to find optimal 3/spl times/3 CNN templates for the inversion of known point spread functions (PSF). In practical applications the determination of this inverse is necessary to fulfil deconvolution tasks. The proposed method is much faster than the previously applied algorithms (like genetic algorithm) and still, in almost all practically important cases, it is convergent. Moreover, unlike a closed form method, it leads to 3/spl times/3 templates instead of 5/spl times/5 or bigger ones. In several important practical cases the PSF, which can be caused by motion, out of focus or the aberration of the imaging system, can be computed from object positions and from the optical system's parameters. Iterative deconvolution algorithms, which are necessary for volume reconstruction from microscopic image sequences, require considerable computation time. Using CNN-UM chips for these deconvolution tasks, a much higher speed, even real time processing seems to be achievable.

关键词： Cellular neural networks Deconvolution Genetic algorithms Focusing Optical imaging Optical computing Iterative algorithms Image reconstruction Microscopy Image sequences

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：