Pub Date : 2002-07-24DOI: 10.1109/CNNA.2002.1035104
Chung-Yu Wu, Chieh-Yu Hsieh, Sheng-Hao Chen, B. C. Hsieh, Cheng-Ruei Chen
In this paper, cellular neural network with ratio memory is proposed for non-saturated binary image processing. The Hebbien leaming lule will be used to leam the weight oftemplate A. The RMCNN system can recognize one non-saNmted binary image and remove most ofthe noise added to the image pattem during the recognition period. The behavior of recognizing non-saturated binary images will be proved by mathematics equations. The effect will be simulated by Matlab sothare. With the method for non-SaNrated binarylmage processing, this theory can be easily implemented in hardware.
{"title":"Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)","authors":"Chung-Yu Wu, Chieh-Yu Hsieh, Sheng-Hao Chen, B. C. Hsieh, Cheng-Ruei Chen","doi":"10.1109/CNNA.2002.1035104","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035104","url":null,"abstract":"In this paper, cellular neural network with ratio memory is proposed for non-saturated binary image processing. The Hebbien leaming lule will be used to leam the weight oftemplate A. The RMCNN system can recognize one non-saNmted binary image and remove most ofthe noise added to the image pattem during the recognition period. The behavior of recognizing non-saturated binary images will be proved by mathematics equations. The effect will be simulated by Matlab sothare. With the method for non-SaNrated binarylmage processing, this theory can be easily implemented in hardware.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121986262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035029
W. Porod, G. Csaba, Á. Csurgay
In this paper we review some newly-emerging nanotechnologies, including new ways of imaging and manipulating matter on the nanometer scale. Electronic devices based on metallic and magnetic nanoscale dots and molecular structures have been suggested, but no technologically viable architecture for nanoelectronic circuit integration has emerged. The natural architecture on the nanoscale is near-neighbor cellular networking, and promising alternative ways of integrating nanodevices by field coupling, i.e. either by Coulomb coupling or magnetic coupling are being explored. In this paper, new architectures for such field-coupled nanocircuits are reviewed.
{"title":"The role of field coupling in nano-scale cellular nonlinear networks","authors":"W. Porod, G. Csaba, Á. Csurgay","doi":"10.1109/CNNA.2002.1035029","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035029","url":null,"abstract":"In this paper we review some newly-emerging nanotechnologies, including new ways of imaging and manipulating matter on the nanometer scale. Electronic devices based on metallic and magnetic nanoscale dots and molecular structures have been suggested, but no technologically viable architecture for nanoelectronic circuit integration has emerged. The natural architecture on the nanoscale is near-neighbor cellular networking, and promising alternative ways of integrating nanodevices by field coupling, i.e. either by Coulomb coupling or magnetic coupling are being explored. In this paper, new architectures for such field-coupled nanocircuits are reviewed.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115725816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035027
S. Tõkés, L. Orzó, T. Roska
Within the programmable opto-electronic analogic computer (POAC) framework a new, feed forward only optical CNN-UM implementation has been introduced. It is grounded on an innovative semi-incoherent optical correlator architecture. Angular coding of the template pixels determines the operation of this optical CNN implementation, therefore it is real time and flexibly programmable. We have demonstrated its feasibility and operation by an experimental setup. Our correlator architecture makes it possible to execute algorithms real time, which cannot be done by any other existing optical correlator so far. Our architecture unifies the advantages of coherent and incoherent optical correlators, provides a more robust frame and avoids their main hindrances. In the POAC framework the resulting correlogram is measured by a programmable adaptive sensor array, a special visual CNN-UM chip. So, local parallel programs fulfill both the necessary pre and post processing with the required adaptive thresholding. However, because of the limited resolution of available visual CNN chips (28/spl times/28), all-optical optical pre- and post-processing will be used, as well.
{"title":"Programmable optical CNN implementation based on the template pixels' angular coding","authors":"S. Tõkés, L. Orzó, T. Roska","doi":"10.1109/CNNA.2002.1035027","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035027","url":null,"abstract":"Within the programmable opto-electronic analogic computer (POAC) framework a new, feed forward only optical CNN-UM implementation has been introduced. It is grounded on an innovative semi-incoherent optical correlator architecture. Angular coding of the template pixels determines the operation of this optical CNN implementation, therefore it is real time and flexibly programmable. We have demonstrated its feasibility and operation by an experimental setup. Our correlator architecture makes it possible to execute algorithms real time, which cannot be done by any other existing optical correlator so far. Our architecture unifies the advantages of coherent and incoherent optical correlators, provides a more robust frame and avoids their main hindrances. In the POAC framework the resulting correlogram is measured by a programmable adaptive sensor array, a special visual CNN-UM chip. So, local parallel programs fulfill both the necessary pre and post processing with the required adaptive thresholding. However, because of the limited resolution of available visual CNN chips (28/spl times/28), all-optical optical pre- and post-processing will be used, as well.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123081869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035092
R. Perfetti, M. Salerno, G. Costantini
We present a new learning algorithm used to implement associative memories on digital cellular neural networks. The algorithm can be easily implemented in hardware or simulated on a digital computer without numerical errors. These attractive features come from the finite precision of connection weights, automatically taken into account as a design constraint; moreover, no multiplication is needed for weight computation.
{"title":"Hardware-oriented algorithm for associative memories on cellular neural networks","authors":"R. Perfetti, M. Salerno, G. Costantini","doi":"10.1109/CNNA.2002.1035092","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035092","url":null,"abstract":"We present a new learning algorithm used to implement associative memories on digital cellular neural networks. The algorithm can be easily implemented in hardware or simulated on a digital computer without numerical errors. These attractive features come from the finite precision of connection weights, automatically taken into account as a design constraint; moreover, no multiplication is needed for weight computation.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124269621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035098
T. Szabó, P. Barsi, P. Szolgay
A CNN-based image processing system as a part of a telemedical consulting system is introduced in this paper. A consulting network for early detection of acute ischemic stroke is outlined. CT images are processed by analogic CNN algorithms.
{"title":"Application of analogic CNN algorithms in telemedical neuroradiology","authors":"T. Szabó, P. Barsi, P. Szolgay","doi":"10.1109/CNNA.2002.1035098","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035098","url":null,"abstract":"A CNN-based image processing system as a part of a telemedical consulting system is introduced in this paper. A consulting network for early detection of acute ischemic stroke is outlined. CT images are processed by analogic CNN algorithms.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128229903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035087
G. Barrows
New classes of small and micro-sized UAVs, with wingspans on the order of meters and tens of centimeters, respectively, present interesting challenges to the field of autonomous flight enabling sensing and control technologies. There is currently a desire to develop a sensor/control suite that will allow such UAVs to fly through complex environments, such as in an "urban canyon" or underneath a forest canopy, at altitudes of just meters above the ground. The development of such capabilities requires new approaches for perceiving the environment. There is an increasing interest in borrowing ideas from flying animals such as insects, which are able to fly through such environments with high reliability. This has led to the development of optical flow sensing techniques that currently are able to provide such capabilities as altitude control and terrain following. However, more difficult tasks such as flying in the urban canyon or in a forest require advances in image processing that allow obstacles to be reliably detected by a machine vision package weighing tens of grams, including all optics, hardware, and software. A blueprint for such a visual sensor is proposed that makes use of anticipated developments in microelectronic technology. With disciplined "best engineering practices", cellular nonlinear network techniques can make significant contributions to the development of such sensors.
{"title":"Future visual microsensors for mini/micro-UAV applications","authors":"G. Barrows","doi":"10.1109/CNNA.2002.1035087","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035087","url":null,"abstract":"New classes of small and micro-sized UAVs, with wingspans on the order of meters and tens of centimeters, respectively, present interesting challenges to the field of autonomous flight enabling sensing and control technologies. There is currently a desire to develop a sensor/control suite that will allow such UAVs to fly through complex environments, such as in an \"urban canyon\" or underneath a forest canopy, at altitudes of just meters above the ground. The development of such capabilities requires new approaches for perceiving the environment. There is an increasing interest in borrowing ideas from flying animals such as insects, which are able to fly through such environments with high reliability. This has led to the development of optical flow sensing techniques that currently are able to provide such capabilities as altitude control and terrain following. However, more difficult tasks such as flying in the urban canyon or in a forest require advances in image processing that allow obstacles to be reliably detected by a machine vision package weighing tens of grams, including all optics, hardware, and software. A blueprint for such a visual sensor is proposed that makes use of anticipated developments in microelectronic technology. With disciplined \"best engineering practices\", cellular nonlinear network techniques can make significant contributions to the development of such sensors.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124640690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035070
T. Hidvégi, P. Keresztes, P. Solgay
Different CNN-UM architecture implementations, analog and emulated digital, were developed. The emulated digital architecture (CASTLE) is accurate but slower than the analog CNN-UMs. It is generally disadvantageous especially if transient computing is critical. The operation speed of the emulated digital implementations, namely CASTLE, can be increased significantly using the pipeline technique. This solution is analyzed with respect to area, time, etc. These arithmetic cores were tested and simulated using a VIRTEX FPGA development system.
{"title":"An accelerated digital CNN-UM (CASTLE) architecture by using the pipe-line technique","authors":"T. Hidvégi, P. Keresztes, P. Solgay","doi":"10.1109/CNNA.2002.1035070","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035070","url":null,"abstract":"Different CNN-UM architecture implementations, analog and emulated digital, were developed. The emulated digital architecture (CASTLE) is accurate but slower than the analog CNN-UMs. It is generally disadvantageous especially if transient computing is critical. The operation speed of the emulated digital implementations, namely CASTLE, can be increased significantly using the pipeline technique. This solution is analyzed with respect to area, time, etc. These arithmetic cores were tested and simulated using a VIRTEX FPGA development system.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134020083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035038
P. Arena, A. Basile, L. Fortuna, M. Yalçin, J. Vandewalle
Digital watermarks have been proposed for authentication of both video and still images. In such applications, the watermark is embedded within a host image such that subsequent alteration to the watermarked image can be detected with high probability. In this paper the possibility of implementing real time watermarking on a video stream is presented. In fact the new CNN-UM implementation offers time operation of only microseconds working on 64/spl times/64 images.
{"title":"Watermarking for the authentication of video on CNN-UM","authors":"P. Arena, A. Basile, L. Fortuna, M. Yalçin, J. Vandewalle","doi":"10.1109/CNNA.2002.1035038","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035038","url":null,"abstract":"Digital watermarks have been proposed for authentication of both video and still images. In such applications, the watermark is embedded within a host image such that subsequent alteration to the watermarked image can be detected with high probability. In this paper the possibility of implementing real time watermarking on a video stream is presented. In fact the new CNN-UM implementation offers time operation of only microseconds working on 64/spl times/64 images.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127372929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035106
J. Kowalski
A VLSI implementation of an analogue weighted median filter based on Cellular Neural Network (CNN) paradigm for standard video signal processing is described in this paper. This filter consists of feedforward nonlinear template B operating within the window of 3 by 3 pixels around the central pixel being filtered. The feedforward nonlinear coefficients are realized using a programmable nonlinear coupler circuits. Basic weighted median filter blocks and chip layout are presented. Technology applied for this implementation is CMOS AMS 0.8/spl mu/m CYE.
{"title":"Analogue weighted median filter based on cellular neural network for standard video signal processing","authors":"J. Kowalski","doi":"10.1109/CNNA.2002.1035106","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035106","url":null,"abstract":"A VLSI implementation of an analogue weighted median filter based on Cellular Neural Network (CNN) paradigm for standard video signal processing is described in this paper. This filter consists of feedforward nonlinear template B operating within the window of 3 by 3 pixels around the central pixel being filtered. The feedforward nonlinear coefficients are realized using a programmable nonlinear coupler circuits. Basic weighted median filter blocks and chip layout are presented. Technology applied for this implementation is CMOS AMS 0.8/spl mu/m CYE.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133718403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035074
D. Feiden, R. Tetzlaff
Obstacle detection in planar worlds is an important part of computer vision because it is indispensable for collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need robust prediction of potential obstacles, like other vehicles or pedestrians. Most common approaches of obstacle detection so far have used analytical and statistical methods like motion estimation or generation of maps. The proposed procedures are mostly composed of many processing steps, so that error propagation of successive steps often leads to inaccurate results. Another problem is the necessity of high computing power for real time applications. In this contribution we demonstrate that obstacle detection in planar worlds can be performed efficiently using cellular neural networks. Beside a fast processing speed the proposed method is also very robust.
{"title":"Obstacle detection in planar worlds using cellular neural networks","authors":"D. Feiden, R. Tetzlaff","doi":"10.1109/CNNA.2002.1035074","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035074","url":null,"abstract":"Obstacle detection in planar worlds is an important part of computer vision because it is indispensable for collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need robust prediction of potential obstacles, like other vehicles or pedestrians. Most common approaches of obstacle detection so far have used analytical and statistical methods like motion estimation or generation of maps. The proposed procedures are mostly composed of many processing steps, so that error propagation of successive steps often leads to inaccurate results. Another problem is the necessity of high computing power for real time applications. In this contribution we demonstrate that obstacle detection in planar worlds can be performed efficiently using cellular neural networks. Beside a fast processing speed the proposed method is also very robust.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123959633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：