检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and Systems 2005, ISCAS 2005

作者： Zarándy, Ákos Földesy, Péter Szolgay, Péter Tokés, Szabolcs Rekeczky, Csaba Roska, TamÁs Analogical and Neural Computing Laboratory MTA-SZTAKI Budapest Hungary

ISBN: (纸本)9780780388345

The Cellular Wave Computer architecture, based on the CNN Universal Machine principle, has been implemented recently in many different physical forms. The mixed mode CMOS, the emulated digital (cell wise or as aggregated arrays), FPGA, DSP, as well as optical implementations are the main examples. In many cases, the sensory array is integrated as well. The new self contained unit, called Bi-i, winning the product of the year title at the Vision 2003 in Stuttgart as the fastest camera-computer, shows the application interest and impact being capable of sensing-computing with 50, 000 frame per second. In this paper a clear and concise comparison will be presented between the various implementation modes. © 2005 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

CNN Universal Machine as Classificaton Platform: An ART-like Clustering Algorithm

引用

International Journal of neural Systems 2003年第6期13卷 415-425页

作者： Balya, David Analogical and Neural Computing Laboratory HAS Computer and Automation Research Institute Kende u. 13 BudapestH-1111 Hungary

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) can be very efficient as a feature detector. The next step is to post-process the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) can be mapped to the CNN-UM. Moreover, this mapping is general enough to include different types of feed-forward neural networks. The designed analogic CNN algorithm is capable of classifying the extracted feature vectors keeping the advantages of the ART networks, such as robust, plastic and fault-tolerant behaviors. An analogic algorithm is presented for unsupervised classification with tunable sensitivity and automatic new class creation. The algorithm is extended for supervised classification. The presented binary feature vector classification is implemented on the existing standard CNN-UM chips for fast classification. The experimental evaluation shows promising performance after 100% accuracy on the training set. © 2003 World Scientific Publishing Company.

关键词： Classification (of information)

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

Per-pixel integration time controlled image sensor

Per-pixel integration time controlled image sensor

引用

2005 European Conference on Circuit Theory and Design

作者： Zarándy, Ákos Földesy, Péter Roska, Tamás Analogical and Neural Computing Laboratory Pázmány Péter Catholic University Hungarian Academy of Sciences Hungary

ISBN: (纸本)0780390660

A per-pixel integration time controlled CMOS image sensor is presented. The main advantage of the device is that it converts high dynamic range scenes to regular dynamic range (8 bits) images on the focal plane. This is achieved by pixel level integration time control. The classic 3 transistor Active Pixel Sensor (APS) architecture has been extended by a one bit latch, which controls a shutter switch. The content of the shutter latch (shutter map) is permanently updated in the entire sensor during the integration time from an external source. The shutter map is calculated by a biologically motivated adaptation algorithm.

关键词： Image sensors

来源：评论

学校读者我要写书评

暂无评论

Computer-Sensors: Spatial-Temporal Computers for Analog Array Signals, Dynamically Integrated with Sensors

引用

Journal of VLSI signal processing systems for signal, image and video technology 1999年第2期23卷 221-237页

作者： Roska, Tamás Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Budapest Hungary

In this paper, first, an overview is given about the whole scenario of analogic CNN computing, as a paradigm of Spatial-temporal Instruction Set Computer (StISC) operating on flows of signal arrays. Next, two areas on CNN computing Technology are considered briefly: (i) the architectural advances, especially the variable resolution and adaptation in space, time, and value and (ii) the computational infrastructure from high level language and compiler to physical implementations. Three basic physical implementations are supposed: analogic CMOS, emulated digital CMOS and optical. The computational infrastructure is the same for all implementations, except the physical interfaces. Finally, the systematic description of the Non-equilibrium Spatial-temporal (NEST) algorithms is given, as a new way of array signal processing, and some practical aspects of NEST algorithms are discussed.

关键词：

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 random fields Image segmentation Cellular neural networks Very large scale integration Computer vision Parallel processing Image processing Computer architecture Memory architecture Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Face and Eye Detection by CNN Algorithms

引用

Journal of VLSI signal processing systems for signal, image and video technology 1999年第2期23卷 497-511页

作者： Balya, David Roska, Tamás Analogical and Neural Computing Laboratory Computer and Automation Research Institute Budapest Hungary

A novel approach to critical parts of face detection problems is given, based on analogic cellular neural network (CNN) algorithms. The proposed CNN algorithms find and help to normalize human faces effectively while their time requirement is a fraction of the previously used methods. The algorithm starts with the detection of heads on color pictures using deviations in color and structure of the human face and that of the background. By normalizing the distance and position of the reference points, all faces should be transformed into the same size and position. For normalization, eyes serve as points of reference. Other CNN algorithm finds the eyes on any grayscale image by searching characteristic features of the eyes and eye sockets. Tests made on a standard database show that the algorithm works very fast and it is reliable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-i: A standalone ultra high speed cellular vision system

引用

IEEE Circuits and Systems Magazine 2005年第2期5卷 36-45页

作者： Zarándy, Ákos Rekeczky, Csaba Analogical and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences Budapest Hungary Faculty of Information Technology Péter Pázmány Catholic University Budapest Hungary Analogic Computers Ltd. Budapest Hungary

The Bi-i standalone cellular vision system is introduced and discussed. In the first part, the underlying sensor and system level architectures are presented and various implementations are overviewed. This computing platform consists of state-of-the-art sensing, cellular-sensing-processing, digital signal processing and communication devices that make it possible to use the system as an ideal computing platform for combined topographic and non-topographic calculations in sensing-processing-actuation scenarios. In the second part of the paper, ultra-high frame rate laboratory experiments are shown and discussed to highlight the most peculiar features of the system and its applicability in various industrial quality control areas. The overview underlines the potentials of the Bi-i vision system for unmanned intelligent vehicle applications in visual exploration, identification, tracking and navigation. ©2005 IEEE.

关键词： Sensors

来源：评论

学校读者我要写书评

暂无评论

Various implementations of topographic, sensory, cellular wave computers

Various implementations of topographic, sensory, cellular wa...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： A. Zarandy M. Foldesy P. Szolgay S. Tokes C. Rekeczky T. Roska MTA-SZTAKI Analogical and Neural Computing Laboratory Budapest Hungary

The cellular wave computer architecture, based on the CNN universal machine principle, has been implemented recently in many different physical forms. The mixed mode CMOS, the emulated digital (cell wise or as aggregated arrays), FPGA, DSP, as well as optical implementations are the main examples. In many cases, the sensory array is integrated as well. The new self contained unit, called Bi-i, winning the product of the year title at the Vision 2003 in Stuttgart as the fastest camera-computer, shows the application interest and impact being capable of sensing-computing with 50000 frames per second. In this paper a clear and concise comparison is presented between the various implementation modes.

关键词： Sensor arrays Optical sensors Computer architecture Sensor phenomena and characterization Optical arrays CMOS technology Physics computing Biomedical optical imaging Biology computing Optical feedback

来源：评论

学校读者我要写书评

暂无评论

Programmable optical CNN implementation based on the template pixels' angular coding

Programmable optical CNN implementation based on the templat...

引用

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

作者： S.T. Kes L. Orzo T. Roska Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Budapest Hungary

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：