检索结果-内蒙古大学图书馆

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

作者： K. Laszlo F. Ziliani T. Roska M. Kunt Analogical and Neural Computing Laboratory Computer and Automation Institute Budapest Hungary Signal Processing Laboratory Swiss Federal Institute of Technology Lausanne Switzerland

Two analogic (analog and logic) CNN algorithms are presented which segment a video sequence into objects. The algorithms are mainly based on 3 by 3, linear templates. This allows the CNN Universal Machine to execute the task achieving enormous computation speed (10/sup 12/ equivalent operation per second). The proposed segmentation algorithms rely on texture and contour information only. They differ in the use or not of the color information. The estimated execution time proves that the proposed segmentation method may be implemented in real time. This result and the quality of the obtained frame description are very appealing in the context of the new video coding standard MPEG-4.

关键词： Video compression Cellular neural networks Analog computers Signal processing algorithms Image segmentation Laboratories Turing machines MPEG 4 Standard Layout Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Analogic algorithms running on the CNN Universal Machine

Analogic algorithms running on the CNN Universal Machine

引用

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

作者： T. Roska Analogical and Neural Computing Laboratory Comp. Aut. Inst. Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this paper first we classify the analogic CNN algorithms; instructions, subroutines, and programs. The complexity of analogic algorithms is defined based on Chaitin's definition of algorithmic computational complexity for digital algorithms. The algorithmic design and implementation phases are analyzed. It is shown how the analogic CNN algorithms are related to the living sensory systems.< >

关键词： Cellular neural networks Turing machines Spatiotemporal phenomena Logic Neuromorphics Failure analysis Pattern analysis Algorithm design and analysis Minimization methods Laboratories

来源：评论

学校读者我要写书评

暂无评论

PDE based histogram modification with embedded morphological processing of the level-sets

PDE based histogram modification with embedded morphological...

引用

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

作者： G. Cserey C. Rekeczky P. Foldesy Analogical and Neural Computing System Laboratory Computer ond Automarion Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

This paper describes parallel histogram modification techniques with embedded morphological preprocessing methods within the CNN-UM framework. The procedure is formulated in terms of nonlinear partial differential equations (PDE) and approximated through finite differences in space, resulting in coupled nonlinear ordinary differential equations (ODE). The I/O mapping of the system (containing both local and global couplings) can be calculated by a complex analogic (analog and logic) algorithm executed on a stored program nonlinear array processor, called the cellular nonlinear network universal machine (CNN-UM). We describe and illustrate how implementation of the algorithm results in an adaptive multi-thresholding scheme when histogram modification is combined with embedded morphological processing at a finite (low) number of grayscale levels. This has obvious advantages if the further processing steps are segmentation and/or recognition. Experimental results processing real-life and echocardiography images are measured on different hardware/software platforms, including a 64/spl times/64 CNN-UM chip (ACE4k).

关键词： Histograms Couplings Programmable logic arrays Partial differential equations Finite difference methods Differential equations Logic arrays Cellular networks Turing machines Gray-scale

来源：评论

学校读者我要写书评

暂无评论

computing on silicon with trigger waves: Experiments on CNN-UM chips

Computing on silicon with trigger waves: Experiments on CNN-...

引用

2001 IEEE International Symposium on Circuits and Systems, ISCAS 2001

作者： Rekeczky, Csaba Szatmari, Istvan Foldesy, Peter Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences Kende U. 13-17 Budapest 1111 Hungary Jedlik Laboratories Department of Information Technology Peter Pazmany Catholic University Szentkirdyi U. 28 Budapest 1088 Hungary

ISBN: (纸本)0780366859

In this paper, experimental results on Cellular neural Network Universal Machine (CNN-UM) chips will be presented. These analogic spatio-temporal visual microprocessors make it possible that one can use nonlinear waves as the basic kernels of algorithms solving filtering-reconstruction and/or detection-classification problems. Showing output results from series of experiments it will be demonstrated how trigger waves, the simplest nonlinear waves, can constructively be used in a number of important application areas. © 2001 IEEE.

关键词： Silicon

来源：评论

学校读者我要写书评

暂无评论

Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks

Picture segmentation with introducing an anisotropic prelimi...

引用

13th International Conference on Pattern Recognition, ICPR 1996

作者： Szirányi, Tamás Czúni, László Department of Image Processing and Neurocomputing University of Veszprém 8200 Veszprém Egyetem út 10. Hungary Analogical and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences Kende u. 13-17 H- 1111 Budapest Hungary

ISBN: (纸本)081867282X

Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future. © 1996 IEEE.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Morphological and wave segmentation by cellular neural networks

Morphological and wave segmentation by cellular neural netwo...

引用

Seminar on neural Network Applications in Electrical Engineering

作者： T. Szabo P. Szolgay Neurocomputing and Image Processing Department University of Veszprém Veszprem Hungary Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Hungary

This paper aims to carry out region-based segmentation in medical images. The main goal is to separate regions with the image features of a stroke, and moreover to develop algorithms for a special type of neural netwo... 详细信息

关键词： Cellular neural networks Image segmentation Smoothing methods Biomedical imaging Analog computers Computer networks Concurrent computing neural networks Anatomical structure Gaussian processes

来源：评论

学校读者我要写书评

暂无评论

Analysis of Multidimensional neural Activity Via CNN-UM

引用

International Journal of neural Systems 2003年第6期13卷 479-487页

作者： Gal, Viktor Grun, Sonja Tetzlaff, Ronald Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Computer Automation Research Institute Ldgymdnyosi u. 13 BudapestH-1111 Hungary Dept. Neurophysiology Max Planck Inst for Brain Research Deutschordnerstr. 46 Frankfurt/MainD-60528 Germany Institute for Applied Physics University of Frankfurt Robert-Mayer-Str. 2-4 Frankfurt/MainD-60325 Germany

In this paper we show that the Cellular Nonlinear Network Universal Machine (CNN-UM) is an excellent tool for analyzing time series of multidimensional binary signals. The developed algorithm is dedicated to process electrophysiological multi-neuron recordings: our aim is to find specific multidimensional activity patterns, which may reflect higher order functional cell-assemblies. The analysis consists of two parts: first, the occurrences of different patterns are counted, then the statistical significance of each occurrence frequency is calculated separately. © 2003 World Scientific Publishing Company.

关键词： Electrophysiology

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

European Conference on Circuit Theory and Design, ECCTD

作者： A. Zarandy P. Foldesy T. Roska Analogical and Neural Computing Laboratory Hungarian Academy of Sciences and Faculty of Information Technology Pázmány Péter Catholic University Hungary

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 Switches Layout Dynamic range Photodiodes CMOS technology Biosensors Capacitive sensors Capacitance Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Design of analogic CNN algorithms for mammogram analysis

Design of analogic CNN algorithms for mammogram analysis

引用

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

作者： A. Zarandy T. Roska G. Liszka J. Hegyesi L. Kek C. Rekeczky Analogical and Neural computing Laboratory Hitachi Micro-computer Engineer Budapest Hungary Department of Diagnostic Radiology National Institute of Oncology Budapest Hungary

CNN analogic algorithms were developed for detecting the features of breast cancer on X-ray mammograms.

CNN analogic algorithms were developed for detecting the features of breast cancer on X-ray mammograms.< >

关键词： Algorithm design and analysis Cellular neural networks X-ray imaging Breast neoplasms Image analysis Cancer Turing machines Testing Image restoration Malignant tumors

来源：评论

学校读者我要写书评

暂无评论

Trainable post-processing method to reduce false alarms in the detection of small blotches of archive films

Trainable post-processing method to reduce false alarms in t...

引用

IEEE International Conference on Image Processing

作者： A. Licsar L. Czuni T. Sziranyi Department of Image Processing and Neurocomputing University of Veszprém Veszprem Hungary Analogical & Neural Computing Laboratory Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

We have developed a new semi-automatic neural network based method to detect blotches with low false alarm rate on archive films. Blotches can be modeled as temporal intensity discontinuities, hence false detection results originate from object motion (e.g. occlusion), non-rigid objects or erroneous motion estimation. In practice, usually, after the automatic detection step the false alarms are removed manually by an operator, significantly decreasing the efficiency of the restoration process. Our post-processing method classifies each detected blotch by its image features to minimize false results and the necessity of human intervention. The proposed method is tested on real archive sequences.

关键词： Object detection Image restoration Motion detection Motion estimation Humans neural networks Optical films Degradation Costs Image motion analysis

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：