A hybrid approach for image half-toning combining simulated annealing and Neural Networks based techniques

Size: px
Start display at page:

Download "A hybrid approach for image half-toning combining simulated annealing and Neural Networks based techniques"

Transcription

1 A hybrid approach for image half-toning combining simulated annealing and Neural Networks based techniques Kurosh Madani Intelligence in Instrumentation and Systems Lab. (I 2 S) SENART Institute of Technology - University PARIS XII Avenue Pierre POINT - F LIEUSAINT France Abstract: A classes of stochastic algorithms, which are very powerful in the case of the degraded image reconstruction, are simulated annealing based algorithms. However, the reconstruction of a degraded image using iterative stochastic process require a large number of operations and is still out of real time. On the other hand, learning and generalization capability of ANN models allows a large panel of techniques improving classical techniques limitations. We are investigating in parallel implementation of image processing techniques. In this paper, we present a hybrid approach for image half-toning combining simulated annealing and neural network based techniques. Simulation and experimental results will be reported. Key-Words: Hybrid Technique, Simulated Annealing, Neural Networks, Degraded Image Reconstruction, ZISC-036, Hardware Implementation, Parallel, Image Processing, Half-Toning. 1 Introduction A classes of stochastic algorithms, which are very powerful in the case of the degraded image reconstruction, are simulated annealing based algorithms. The main advantage of such approach is related to the fact that in this kind of processing, there is not necessity to any prior hypothesis on nature of information to be restored. However, the reconstruction of a degraded image using iterative stochastic process require a large number of operations and is still out of real time. On the other hand, learning and generalization capability of ANN models allows a large panel of techniques improving classical techniques limitations. We are investigating in parallel implementation of image processing techniques. In this paper, we present an hybrid approach for image half-toning combining simulated annealing and neural network based techniques. Theoretical studies on simulated annealing show that the convergence of such process is obtained for the number of infinite iterations : so, an implementation of such algorithms become uninteresting from the point view of computation time. The goal is here to use the neural network s learning and generalization capabilities to complete an unfinished simulated annealing process. The present paper has been organized as following: The section 2 presents the principle of Simulated Annealing (SA) based image processing, especially the half-toning. A brief description of RCE based neural model and the basic properties of the IBM ZISC-036 component implementing such model are reported in section 3. The section 4 is dedicated to the hybrid approach combining simulated annealing and neural based techniques. Finally the section 5 conclude this paper and gives perspectives to the present work. 2 About Simulated Annealing approach and derived image half-toning technique Since it's introduction by Metropolis and Ulam [1] in 1949, and later by Kirkpatrick and others ([2] to [5]), the importance of Monte-Carlo algorithms for solving computation problems in high dimensional spaces is well known. In 1985, Carnevali & al. show the equivalence between the Ising model (a

2 physical system) and the image reconstruction dilemma proposing a powerful iterative stochastic relaxation based algorithm for picture half-toning and picture smoothing [6] : an image is considered as some global state of a 2-D physical system and it's processing is based on global energy minimization of such physical system. The image half-toning consists on encoding a multilevel (gray level) image to a binary image in which the gray levels are represented by some spatial (2-D) density of binary states (for example, a spatial density of "1" in a given region of the halftoned image). Let us to consider this case. We have chosen the following notation : ai,j : pixel of the multilevel image, with ai,j [ -1, +1 ], bi,j : corresponding pixel of the half-toned image and Vi,j,k,l : some kernel with the following properties : V i, j, k, l 0 and V i, j, k, l = 1 The pixel's energy then could be defined by relation (1), where ri,j is some representation relative to the corresponding region in the half-toned image. E = i j r i, j = k 2 ( a i, j r i, j ) k l l V i, j, k, l (1) with Developing relation (1), one can show (Carnevali & al.) that the energy function could be written as relation (2). 1 E = λ âi, j bi, j + i j 1 λ with λ = 2, i, j = I i, j, k, l = n i1 j1 i2 j2 m k l I V i, j, n, m b k, l b b i2, j1, i2, j2 i1, j1 i2, j2 V i, j, k, l V n, m, k, l a k, l and To update the pixel's value, two dynamics are generally used. In both of them, the updating is performed randomly. The difference is related to the probabilistic decision function that will be used to valid the new value of the pixel (in the case of the half-toning process, the decision concerns the validation of pixel's value to be "1" or "0"). (2) The original Carnevali's algorithm uses pixels values belonging to the continuous interval [-1, +1]. Moreover, the energy is also encoded supposing an infinite precision (all possible values belonging to the continuos interval [-1, +1]). Such hypothesis could not be implemented simply because of the computer's precision limitation. We have considered the following modifications : all used values in our version of this algorithm are integers with finite number of bits (number which should be determined). Moreover : all Vi,j,k,l are supposed to be constants and identical, the value of λ parameter in relation (2) is supposed to be 1, and the simulated annealing control parameter T is also supposed to be an integer. The first consequence of such hypothesis is related to the energy value that will be also integer and not normalized. According to the above mentioned hypothesis (relative to the algorithm's modifications), and considering the fact that in the Carnevali's process the neighborhood doesn't change, the energy variation will be given by the relation (3) with : b i, j { 0, 1 } and b i, j { 1, 0, 1 }. E = E E = i 0, j 0 b i, j + I b i, j b i, j k i 0 l j 0 The decision dynamics is based on the Glauber dynamics (relation (4)). ( ) = 1 n + 1 P X i " 0 " P X n + 1 " 1 " i E 1 + exp i T n ( ) = 1 P ( X i ) 3 About RCE Model and the ZISC-036 Neuroprocessor The RCE (Restricted Coulomb Energy) like ANNs include three layers: an input layer, a hidden layer and an output layer. Each node of the hidden layer is a processing unit which computes the distance between the input layer and the prototype stored within each node (thanks to a connection between the input and the hidden layer). The output layer is used to give the categories which correspond to the input data. Connections between hidden and output layers are dynamically established during the learning phase. These models consist of mapping an

3 n-dimensional space by prototypes where each prototype is associated with a category and a threshold, influence field (for RCE), a part of the n- dimensional space around the prototype where generalization is possible (see figure 1). A prototype is a vector defining the coordinates of the prototype within the n-dimensional space. Within the network, several prototypes may be associated with one category, and influence fields can partially overlap one another. The ZISC-036 hardware can implement the RCE and the KNN algorithms. Based on this model, the ZISC operates in two phases, the learning phase and the recognition phase [11][12] [12]. were P represents the memorized prototype and V is the input pattern. compare the distance to its threshold, communicate with other neurons (in order to find the minimum distance, category, etc.), adjust its threshold (during learning phase). V 1 Fig.2 : Example of an input mapping in a 2-D space: ROI (a) and 1-NN (b) using norm L1 in the case of the ZISC-036 RCE I/O bus HOST Neuron 1 Neuron n weight weight Fig.1 : Example of RCE-like map of a two dimensional space. V 0 Norm distance evaluator... Norm distance evaluator The IBM ZISC-036 is a parallel neural processor based on the RCE and KNN algorithms. Each chip is capable of performing up to recognitions per second. Thanks to the integration of an incremental learning algorithm, this circuit is very easy to program in order to develop applications; a very few number of functions (about ten functions) are necessary to control it. ZISC-036 is composed of 36 neurons. This chip is fully cascadable which allows the use of as many neurons as the user needs (a PCI card has been developed with a capacity of 684 neurons). A neuron is an element which is able to: memorize a prototype (64 components coded on 8 bits), the associated category (14 bits), a threshold (14 bits), a context (7 bits), compute the distance, based on the selected norm (norm L1 given by relation 2 or LSUP given by relation 3) between its memorized prototype and the input vector (the distance is coded on fourteen bits), n L1 : dist = V i P i (2) and i= 0 LSUP : dist = max i = 0... n V i P i (3) category context (sub-network index) thresholding Inter-neuron communication bus category context (sub-network index) Fig.3 : IBM ZISC-036 bloc diagram. thresholding Figure 2 shows an example of the input mapping of a 2-dimensional space with the ZISC-036. Figure 2(a) using ROI shows that due to the close proximity of neighboring neurons, the ROI are adjusted while figure 2(b) is an example of the KNN (in the case of the figure a 1-NN has been considered). Figures 3 gives the ZISC-036 structure s bloc diagram. 4 The hybrid approach combining RCE and SA techniques As it has been mentioned previously, the convergence of a simulated annealing based process is obtained for infinite iterations and so, an implementation of such algorithms become uninteresting from the point view of computation time. The goal is here to use the neural network s

4 learning and generalization capabilities to complete an unfinished simulated annealing process. The approach we propose is a hybrid solution combining a simulated annealing based module and an RCE (RBF) based neural unit. Figure 4 shows the bloc diagram of such hybrid processing unit. input image (issued from an unfinished simulated annealing) to a pixel of the output image (in this case the category is a pixel. This association dose not lead to good results because the neighborhood correlation is not taken into account. The second association strategy consists on association a region of the input image to a category which is also a region of the output image. SIMULATED ANNEALING BASE MODULE NERAL NETWORK BASE UNIT Fig.4 : Bloc diagram of the proposed hybrid processing unit. The simulated annealing module stops the process after a finite number of iterations, leading to an unfinished result. Then the neural network based unit improves the result basing on the learning and generalization capabilities of such process unit. The interest here is to take advantage from the fact that the simulated annealing based process will process the input information (images in our case) without any prior hypothesis on nature of that input information : minimizing some global energy associated to the system. However, as the simulated annealing based process has been stopped after a finite number of iterations the results quality will not be acceptable. Then, the neural network based unit will act as a function approximation unit approximating the unfinished process by the most appropriated function. The approximation is performed locally (considering some neighborhood for each pixel of the image). Fig.6 : Original multi-leveled image (Left) and an unfinished simulated annealing based result with a insufficient number of iterations. The figure 5 compares results obtained for each association relative to a 3 by 3 neighborhood. The figure 6 shows an unfinished simulated annealing based image half-toning obtained from the original multi-leveled image of Lena. The figure 7 represents the output image of the ZISC-036 based neural unit considering a 3 by 3 neighborhood around each pixel. For the figure 7, a randomly pixel to pixel learning process has been performed. The first image of the figure 8 (left side) corresponds to the half-toned image obtained after a large number of iterations using the presented simulated annealing technique. The second image of the same figure (right side) reproduces the result obtained from an unfinished simulated annealing half-toning using the presented hybrid approach only after one single iteration (reconstruction). Fig.5.: Results obtained for a region to pixel association (left) and region to region association (right) relative to a 3 by 3 neighborhood. Two kind of associations (between input and output images) could be considered : the most simplest is to associate a region (some neighborhood) of the Fig.7 : Hybrid technique based result with a pixel to pixel learning process after only one iteration.

5 Concerning future perspective of the present work, we are working on a significant learning data base construction including a panel of various half-toned images. We also working on improving the hybrid technique by associating another kind of neural models (competitive and general). Acknowledgments: Fig.8 : Left : Half-toned Lena obtained from simulated annealing based process after a large number of iterations. Right : Hybrid technique based result with a region to region association learning process after only one iteration. 5 Conclusion The image half-toning consists on encoding a multilevel (gray level) image to a binary image in which the gray levels are represented by some spatial (2-D) density of binary states. Simulated annealing based algorithms, very powerful in the case of the degraded image reconstruction, are used to obtain a half-toned image from an originally gray level image. The main advantage of such approach is related to the fact that in this kind of processing, there is not necessity to any prior hypothesis on nature of information to be restored. However, the reconstruction of a degraded image using iterative stochastic process require a large number of operations and is still out of real time. In this paper, we have presented an hybrid approach for image half-toning, combining simulated annealing and neural network based techniques. The neural part of the system we proposed is based on RCE-RBF like neural network. The goal is to use the neural network s learning and generalization capabilities to complete an unfinished simulated annealing process, and so, to accelerate the processing duration saving the above mentioned advantages related to the simulated annealing based processing. We have implemented our neural module on a IBM ZISC-036 based board including 16 neuro-processors with 36 neurons per processor. Experimental results, obtained from unfinished simulated annealing based processing, showing half-toned image quality improvement, have been presented validating our approach. The author wish thank Dr. Nabil Mesbah for his participation during his Ph.D. period to simulated annealing and neural networks aspects of the present work and for useful discussions. References: [1] N. Metropolis, S. Ulam, J. of Am. Statistical Assn. 44, [2] S. Kirkpatrick, S. D. Gelatt, M.P. Vecchi, Optimization by simulated annealing, Science 8-67, [3] S. Kirkpatrick, Optimization by simulated annealing: Quantitative studies, J. of Statistical Phys. 34, 975, [4] S. Geman, D. Geman, Stochastic relaxation, Gibbs distribution and Bayesian restoration of images, IEEE Trans. PAMI, Vol. 3, 1984, pp [5] D. W. Murray, A. Kashko, H. Buxton, A parallel approach to the picture restoration algorithm of Geman and Geman, Image Vision Computing Vol. 4, N 6, 1986, pp [6] P. Carnevalli, L. Coletti, S. Patarnello, Image processing by simulated annealing, IBM J. of Res. and Dev. Vol 29 N 6, Nov. 1985, pp [7] P. Garda, K. Madani, F. Devos, P. Chavel, P. Lallane, J. Taboury, A massively parallel image processor for stochastic relaxation using optical random number generation, Optical Computing, Ed. J.W. Goodman, P. Chavel, G. Roblin, SPIE Volume 963. [8] P. GARDA, K. MADANI, F. DEVOS, P. CHAVEL, P. LALANNE, J. TABOURY, A monolithic processor array for stochastic relaxation using optical random number generation, NATO Series, Vol. F 68, Neurocomputing, Edited by F. Fogelman Soulié and J. Hérolt, Springer - Verlag Berlin Heidelberg [9] K. MADANI, N. MESBAH, Discussion on a massively parallel implementation of simulated annealing algorithms for image processing, International Symposium on Intelligent Systems and advanced manufactoring, Unconventional Imaging for Industrial Inspection, Philadelphia, Pennsylvania, USA, 23-26october 1995.

6 [10] K. MADANI, N. MESBAH, Compromise Discussion around Two Dynamics for Implementation of Simulated Annealing based Image restoration, Aerospace remote Sensing, EUROPTO'97, IEE, London, United Kingdom, September 1997, Image and Signal Processing for Remote sensing SPIE Vol [11] ZISC036 data book, IBM Essonnes Component Development Laboratory, IBM Microelectronics, Corbeil-Essonnes, France. [12] Eide A., Lindblad Th., Lindsey C.S., Minerskjöld M., Sekhviaidze G. and Székely G.: An Implementation of the Zero Instruction Set Computer (ZISC-036) on a PC/ISA-bus Card, 1994 WNN/FNN Proc., Washington D.C., December [13] Robert David, Erin Williams, Ghislain de Trémiolles, Pascal Tannhof, Description and Practical Uses of IBM ZISC-036, VI-DYNN'98 - Virtual Intelligence - Dynamic Neural Networks Stockholm - Sweden - June 22-26, 1998.

Applied Intelligence 18, 195 213, 2003 c 2003 Kluwer Academic Publishers. Manufactured in The Netherlands. Image Processing Using RBF like Neural Networks: A ZISC-036 Based Fully Parallel Implementation

More information

Image Restoration using Markov Random Fields

Image Restoration using Markov Random Fields Image Restoration using Markov Random Fields Based on the paper Stochastic Relaxation, Gibbs Distributions and Bayesian Restoration of Images, PAMI, 1984, Geman and Geman. and the book Markov Random Field

More information

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing

Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Image Segmentation Using Iterated Graph Cuts BasedonMulti-scaleSmoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200, Kasugai,

More information

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing

Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Image Segmentation Using Iterated Graph Cuts Based on Multi-scale Smoothing Tomoyuki Nagahashi 1, Hironobu Fujiyoshi 1, and Takeo Kanade 2 1 Dept. of Computer Science, Chubu University. Matsumoto 1200,

More information

Image segmentation using an annealed Hopfield neural network

Image segmentation using an annealed Hopfield neural network Iowa State University From the SelectedWorks of Sarah A. Rajala December 16, 1992 Image segmentation using an annealed Hopfield neural network Yungsik Kim, North Carolina State University Sarah A. Rajala,

More information

MRF Based LSB Steganalysis: A New Measure of Steganography Capacity

MRF Based LSB Steganalysis: A New Measure of Steganography Capacity MRF Based LSB Steganalysis: A New Measure of Steganography Capacity Debasis Mazumdar 1, Apurba Das 1, and Sankar K. Pal 2 1 CDAC, Kolkata, Salt Lake Electronics Complex, Kolkata, India {debasis.mazumdar,apurba.das}@cdackolkata.in

More information

Reduced Dimensionality Space for Post Placement Quality Inspection of Components based on Neural Networks

Reduced Dimensionality Space for Post Placement Quality Inspection of Components based on Neural Networks Reduced Dimensionality Space for Post Placement Quality Inspection of Components based on Neural Networks Stefanos K. Goumas *, Michael E. Zervakis, George Rovithakis * Information Management Department

More information

Texture Modeling using MRF and Parameters Estimation

Texture Modeling using MRF and Parameters Estimation Texture Modeling using MRF and Parameters Estimation Ms. H. P. Lone 1, Prof. G. R. Gidveer 2 1 Postgraduate Student E & TC Department MGM J.N.E.C,Aurangabad 2 Professor E & TC Department MGM J.N.E.C,Aurangabad

More information

Simultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Network and Fuzzy Simulation

Simultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Network and Fuzzy Simulation .--- Simultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Networ and Fuzzy Simulation Abstract - - - - Keywords: Many optimization problems contain fuzzy information. Possibility

More information

A Graph Theoretic Approach to Image Database Retrieval

A Graph Theoretic Approach to Image Database Retrieval A Graph Theoretic Approach to Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington, Seattle, WA 98195-2500

More information

MRF-based Algorithms for Segmentation of SAR Images

MRF-based Algorithms for Segmentation of SAR Images This paper originally appeared in the Proceedings of the 998 International Conference on Image Processing, v. 3, pp. 770-774, IEEE, Chicago, (998) MRF-based Algorithms for Segmentation of SAR Images Robert

More information

Coarse-to-Fine Search Technique to Detect Circles in Images

Coarse-to-Fine Search Technique to Detect Circles in Images Int J Adv Manuf Technol (1999) 15:96 102 1999 Springer-Verlag London Limited Coarse-to-Fine Search Technique to Detect Circles in Images M. Atiquzzaman Department of Electrical and Computer Engineering,

More information

Training Digital Circuits with Hamming Clustering

Training Digital Circuits with Hamming Clustering IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I: FUNDAMENTAL THEORY AND APPLICATIONS, VOL. 47, NO. 4, APRIL 2000 513 Training Digital Circuits with Hamming Clustering Marco Muselli, Member, IEEE, and Diego

More information

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas Table of Contents Recognition of Facial Gestures...................................... 1 Attila Fazekas II Recognition of Facial Gestures Attila Fazekas University of Debrecen, Institute of Informatics

More information

Morphological Change Detection Algorithms for Surveillance Applications

Morphological Change Detection Algorithms for Surveillance Applications Morphological Change Detection Algorithms for Surveillance Applications Elena Stringa Joint Research Centre Institute for Systems, Informatics and Safety TP 270, Ispra (VA), Italy elena.stringa@jrc.it

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

Image analysis. Computer Vision and Classification Image Segmentation. 7 Image analysis

Image analysis. Computer Vision and Classification Image Segmentation. 7 Image analysis 7 Computer Vision and Classification 413 / 458 Computer Vision and Classification The k-nearest-neighbor method The k-nearest-neighbor (knn) procedure has been used in data analysis and machine learning

More information

Task Allocation for Minimizing Programs Completion Time in Multicomputer Systems

Task Allocation for Minimizing Programs Completion Time in Multicomputer Systems Task Allocation for Minimizing Programs Completion Time in Multicomputer Systems Gamal Attiya and Yskandar Hamam Groupe ESIEE Paris, Lab. A 2 SI Cité Descartes, BP 99, 93162 Noisy-Le-Grand, FRANCE {attiyag,hamamy}@esiee.fr

More information

VIDEO OBJECT SEGMENTATION BY EXTENDED RECURSIVE-SHORTEST-SPANNING-TREE METHOD. Ertem Tuncel and Levent Onural

VIDEO OBJECT SEGMENTATION BY EXTENDED RECURSIVE-SHORTEST-SPANNING-TREE METHOD. Ertem Tuncel and Levent Onural VIDEO OBJECT SEGMENTATION BY EXTENDED RECURSIVE-SHORTEST-SPANNING-TREE METHOD Ertem Tuncel and Levent Onural Electrical and Electronics Engineering Department, Bilkent University, TR-06533, Ankara, Turkey

More information

Two-step Modified SOM for Parallel Calculation

Two-step Modified SOM for Parallel Calculation Two-step Modified SOM for Parallel Calculation Two-step Modified SOM for Parallel Calculation Petr Gajdoš and Pavel Moravec Petr Gajdoš and Pavel Moravec Department of Computer Science, FEECS, VŠB Technical

More information

HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation

HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation 009 10th International Conference on Document Analysis and Recognition HMM-Based Handwritten Amharic Word Recognition with Feature Concatenation Yaregal Assabie and Josef Bigun School of Information Science,

More information

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-"&"3 -"(' ( +-" " " % '.+ % ' -0(+$,

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-&3 -(' ( +-   % '.+ % ' -0(+$, The structure is a very important aspect in neural network design, it is not only impossible to determine an optimal structure for a given problem, it is even impossible to prove that a given structure

More information

Power Functions and Their Use In Selecting Distance Functions for. Document Degradation Model Validation. 600 Mountain Avenue, Room 2C-322

Power Functions and Their Use In Selecting Distance Functions for. Document Degradation Model Validation. 600 Mountain Avenue, Room 2C-322 Power Functions and Their Use In Selecting Distance Functions for Document Degradation Model Validation Tapas Kanungo y ; Robert M. Haralick y and Henry S. Baird z y Department of Electrical Engineering,

More information

Parallel Evaluation of Hopfield Neural Networks

Parallel Evaluation of Hopfield Neural Networks Parallel Evaluation of Hopfield Neural Networks Antoine Eiche, Daniel Chillet, Sebastien Pillement and Olivier Sentieys University of Rennes I / IRISA / INRIA 6 rue de Kerampont, BP 818 2232 LANNION,FRANCE

More information

Images Reconstruction using an iterative SOM based algorithm.

Images Reconstruction using an iterative SOM based algorithm. Images Reconstruction using an iterative SOM based algorithm. M.Jouini 1, S.Thiria 2 and M.Crépon 3 * 1- LOCEAN, MMSA team, CNAM University, Paris, France 2- LOCEAN, MMSA team, UVSQ University Paris, France

More information

Markov Random Fields and Gibbs Sampling for Image Denoising

Markov Random Fields and Gibbs Sampling for Image Denoising Markov Random Fields and Gibbs Sampling for Image Denoising Chang Yue Electrical Engineering Stanford University changyue@stanfoed.edu Abstract This project applies Gibbs Sampling based on different Markov

More information

Image Compression Using BPD with De Based Multi- Level Thresholding

Image Compression Using BPD with De Based Multi- Level Thresholding International Journal of Innovative Research in Electronics and Communications (IJIREC) Volume 1, Issue 3, June 2014, PP 38-42 ISSN 2349-4042 (Print) & ISSN 2349-4050 (Online) www.arcjournals.org Image

More information

Numerical Analysis of IEEE Broadcast Scheme in Multihop Wireless Ad Hoc Networks

Numerical Analysis of IEEE Broadcast Scheme in Multihop Wireless Ad Hoc Networks Numerical Analysis of IEEE 802.11 Broadcast Scheme in Multihop Wireless Ad Hoc Networks Jong-Mu Choi 1, Jungmin So 2, and Young-Bae Ko 1 1 School of Information and Computer Engineering Ajou University,

More information

University of Toronto Department of Statistics

University of Toronto Department of Statistics Optimising Monte Carlo Search Strategies for Automated Pattern Detection by Jeffrey S. Rosenthal Department of Statistics University of Toronto Technical Report No. 0805 June 30, 2008 TECHNICAL REPORT

More information

A Quantitative Approach for Textural Image Segmentation with Median Filter

A Quantitative Approach for Textural Image Segmentation with Median Filter International Journal of Advancements in Research & Technology, Volume 2, Issue 4, April-2013 1 179 A Quantitative Approach for Textural Image Segmentation with Median Filter Dr. D. Pugazhenthi 1, Priya

More information

SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS

SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS J. KORNIS, P. PACHER Department of Physics Technical University of Budapest H-1111 Budafoki út 8., Hungary e-mail: kornis@phy.bme.hu, pacher@phy.bme.hu

More information

This leads to our algorithm which is outlined in Section III, along with a tabular summary of it's performance on several benchmarks. The last section

This leads to our algorithm which is outlined in Section III, along with a tabular summary of it's performance on several benchmarks. The last section An Algorithm for Incremental Construction of Feedforward Networks of Threshold Units with Real Valued Inputs Dhananjay S. Phatak Electrical Engineering Department State University of New York, Binghamton,

More information

Feature selection in environmental data mining combining Simulated Annealing and Extreme Learning Machine

Feature selection in environmental data mining combining Simulated Annealing and Extreme Learning Machine Feature selection in environmental data mining combining Simulated Annealing and Extreme Learning Machine Michael Leuenberger and Mikhail Kanevski University of Lausanne - Institute of Earth Surface Dynamics

More information

IN recent years, neural networks have attracted considerable attention

IN recent years, neural networks have attracted considerable attention Multilayer Perceptron: Architecture Optimization and Training Hassan Ramchoun, Mohammed Amine Janati Idrissi, Youssef Ghanou, Mohamed Ettaouil Modeling and Scientific Computing Laboratory, Faculty of Science

More information

An Edge-Based Approach to Motion Detection*

An Edge-Based Approach to Motion Detection* An Edge-Based Approach to Motion Detection* Angel D. Sappa and Fadi Dornaika Computer Vison Center Edifici O Campus UAB 08193 Barcelona, Spain {sappa, dornaika}@cvc.uab.es Abstract. This paper presents

More information

Generalized Coordinates for Cellular Automata Grids

Generalized Coordinates for Cellular Automata Grids Generalized Coordinates for Cellular Automata Grids Lev Naumov Saint-Peterburg State Institute of Fine Mechanics and Optics, Computer Science Department, 197101 Sablinskaya st. 14, Saint-Peterburg, Russia

More information

Comparison of supervised self-organizing maps using Euclidian or Mahalanobis distance in classification context

Comparison of supervised self-organizing maps using Euclidian or Mahalanobis distance in classification context 6 th. International Work Conference on Artificial and Natural Neural Networks (IWANN2001), Granada, June 13-15 2001 Comparison of supervised self-organizing maps using Euclidian or Mahalanobis distance

More information

A linear algebra processor using Monte Carlo methods

A linear algebra processor using Monte Carlo methods A linear algebra processor using Monte Carlo methods Conference or Workshop Item Accepted Version Plaks, T. P., Megson, G. M., Cadenas Medina, J. O. and Alexandrov, V. N. (2003) A linear algebra processor

More information

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

Akarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different

More information

Hybrid Particle Swarm-Based-Simulated Annealing Optimization Techniques

Hybrid Particle Swarm-Based-Simulated Annealing Optimization Techniques Hybrid Particle Swarm-Based-Simulated Annealing Optimization Techniques Nasser Sadati Abstract Particle Swarm Optimization (PSO) algorithms recently invented as intelligent optimizers with several highly

More information

Genetic Algorithm for Circuit Partitioning

Genetic Algorithm for Circuit Partitioning Genetic Algorithm for Circuit Partitioning ZOLTAN BARUCH, OCTAVIAN CREŢ, KALMAN PUSZTAI Computer Science Department, Technical University of Cluj-Napoca, 26, Bariţiu St., 3400 Cluj-Napoca, Romania {Zoltan.Baruch,

More information

Image Smoothing and Segmentation by Graph Regularization

Image Smoothing and Segmentation by Graph Regularization Image Smoothing and Segmentation by Graph Regularization Sébastien Bougleux 1 and Abderrahim Elmoataz 1 GREYC CNRS UMR 6072, Université de Caen Basse-Normandie ENSICAEN 6 BD du Maréchal Juin, 14050 Caen

More information

Self-Organizing Maps for cyclic and unbounded graphs

Self-Organizing Maps for cyclic and unbounded graphs Self-Organizing Maps for cyclic and unbounded graphs M. Hagenbuchner 1, A. Sperduti 2, A.C. Tsoi 3 1- University of Wollongong, Wollongong, Australia. 2- University of Padova, Padova, Italy. 3- Hong Kong

More information

Efficient Object Extraction Using Fuzzy Cardinality Based Thresholding and Hopfield Network

Efficient Object Extraction Using Fuzzy Cardinality Based Thresholding and Hopfield Network Efficient Object Extraction Using Fuzzy Cardinality Based Thresholding and Hopfield Network S. Bhattacharyya U. Maulik S. Bandyopadhyay Dept. of Information Technology Dept. of Comp. Sc. and Tech. Machine

More information

A Video Watermarking Algorithm Based on the Human Visual System Properties

A Video Watermarking Algorithm Based on the Human Visual System Properties A Video Watermarking Algorithm Based on the Human Visual System Properties Ji-Young Moon 1 and Yo-Sung Ho 2 1 Samsung Electronics Co., LTD 416, Maetan3-dong, Paldal-gu, Suwon-si, Gyenggi-do, Korea jiyoung.moon@samsung.com

More information

Multiview Pedestrian Detection Based on Online Support Vector Machine Using Convex Hull

Multiview Pedestrian Detection Based on Online Support Vector Machine Using Convex Hull Multiview Pedestrian Detection Based on Online Support Vector Machine Using Convex Hull Revathi M K 1, Ramya K P 2, Sona G 3 1, 2, 3 Information Technology, Anna University, Dr.Sivanthi Aditanar College

More information

Improved Non-Local Means Algorithm Based on Dimensionality Reduction

Improved Non-Local Means Algorithm Based on Dimensionality Reduction Improved Non-Local Means Algorithm Based on Dimensionality Reduction Golam M. Maruf and Mahmoud R. El-Sakka (&) Department of Computer Science, University of Western Ontario, London, Ontario, Canada {gmaruf,melsakka}@uwo.ca

More information

Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial Region Segmentation

Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial Region Segmentation IJCSNS International Journal of Computer Science and Network Security, VOL.13 No.11, November 2013 1 Moving Object Segmentation Method Based on Motion Information Classification by X-means and Spatial

More information

Time Series Prediction as a Problem of Missing Values: Application to ESTSP2007 and NN3 Competition Benchmarks

Time Series Prediction as a Problem of Missing Values: Application to ESTSP2007 and NN3 Competition Benchmarks Series Prediction as a Problem of Missing Values: Application to ESTSP7 and NN3 Competition Benchmarks Antti Sorjamaa and Amaury Lendasse Abstract In this paper, time series prediction is considered as

More information

COMPARATIVE STUDY OF CIRCUIT PARTITIONING ALGORITHMS

COMPARATIVE STUDY OF CIRCUIT PARTITIONING ALGORITHMS COMPARATIVE STUDY OF CIRCUIT PARTITIONING ALGORITHMS Zoltan Baruch 1, Octavian Creţ 2, Kalman Pusztai 3 1 PhD, Lecturer, Technical University of Cluj-Napoca, Romania 2 Assistant, Technical University of

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

Improving the detection of excessive activation of ciliaris muscle by clustering thermal images

Improving the detection of excessive activation of ciliaris muscle by clustering thermal images 11 th International Conference on Quantitative InfraRed Thermography Improving the detection of excessive activation of ciliaris muscle by clustering thermal images *University of Debrecen, Faculty of

More information

CLASSIFICATION is one of the most important applications of neural systems. Approximation

CLASSIFICATION is one of the most important applications of neural systems. Approximation Neural minimal distance methods Włodzisław Duch Department of Computer Methods, Nicholas Copernicus University, Grudzia dzka 5, 87-100 Toruń, Poland. E-mail: duch@phys.uni.torun.pl Abstract Minimal distance

More information

Image Inpainting Using Sparsity of the Transform Domain

Image Inpainting Using Sparsity of the Transform Domain Image Inpainting Using Sparsity of the Transform Domain H. Hosseini*, N.B. Marvasti, Student Member, IEEE, F. Marvasti, Senior Member, IEEE Advanced Communication Research Institute (ACRI) Department of

More information

A new predictive image compression scheme using histogram analysis and pattern matching

A new predictive image compression scheme using histogram analysis and pattern matching University of Wollongong Research Online University of Wollongong in Dubai - Papers University of Wollongong in Dubai 00 A new predictive image compression scheme using histogram analysis and pattern matching

More information

Using Genetic Algorithms to Improve Pattern Classification Performance

Using Genetic Algorithms to Improve Pattern Classification Performance Using Genetic Algorithms to Improve Pattern Classification Performance Eric I. Chang and Richard P. Lippmann Lincoln Laboratory, MIT Lexington, MA 021739108 Abstract Genetic algorithms were used to select

More information

Color Space Projection, Feature Fusion and Concurrent Neural Modules for Biometric Image Recognition

Color Space Projection, Feature Fusion and Concurrent Neural Modules for Biometric Image Recognition Proceedings of the 5th WSEAS Int. Conf. on COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS, Venice, Italy, November 20-22, 2006 286 Color Space Projection, Fusion and Concurrent Neural

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

F003 Monte-Carlo Statics on Large 3D Wide-azimuth Data

F003 Monte-Carlo Statics on Large 3D Wide-azimuth Data F003 Monte-Carlo Statics on Large 3D Wide-azimuth Data D. Le Meur* (CGGVeritas) SUMMARY Estimation of surface-consistent residual statics on large 3D wide-azimuth data using a Monte-Carlo approach is a

More information

Content Based Image Retrieval system with a combination of Rough Set and Support Vector Machine

Content Based Image Retrieval system with a combination of Rough Set and Support Vector Machine Shahabi Lotfabadi, M., Shiratuddin, M.F. and Wong, K.W. (2013) Content Based Image Retrieval system with a combination of rough set and support vector machine. In: 9th Annual International Joint Conferences

More information

Combined Weak Classifiers

Combined Weak Classifiers Combined Weak Classifiers Chuanyi Ji and Sheng Ma Department of Electrical, Computer and System Engineering Rensselaer Polytechnic Institute, Troy, NY 12180 chuanyi@ecse.rpi.edu, shengm@ecse.rpi.edu Abstract

More information

A NEURAL NETWORK APPLICATION FOR A COMPUTER ACCESS SECURITY SYSTEM: KEYSTROKE DYNAMICS VERSUS VOICE PATTERNS

A NEURAL NETWORK APPLICATION FOR A COMPUTER ACCESS SECURITY SYSTEM: KEYSTROKE DYNAMICS VERSUS VOICE PATTERNS A NEURAL NETWORK APPLICATION FOR A COMPUTER ACCESS SECURITY SYSTEM: KEYSTROKE DYNAMICS VERSUS VOICE PATTERNS A. SERMET ANAGUN Industrial Engineering Department, Osmangazi University, Eskisehir, Turkey

More information

COMPUTER AND ROBOT VISION

COMPUTER AND ROBOT VISION VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington A^ ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California

More information

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra Pattern Recall Analysis of the Hopfield Neural Network with a Genetic Algorithm Susmita Mohapatra Department of Computer Science, Utkal University, India Abstract: This paper is focused on the implementation

More information

A Hierarchial Model for Visual Perception

A Hierarchial Model for Visual Perception A Hierarchial Model for Visual Perception Bolei Zhou 1 and Liqing Zhang 2 1 MOE-Microsoft Laboratory for Intelligent Computing and Intelligent Systems, and Department of Biomedical Engineering, Shanghai

More information

Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations

Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations Mehran Motmaen motmaen73@gmail.com Majid Mohrekesh mmohrekesh@yahoo.com Mojtaba Akbari mojtaba.akbari@ec.iut.ac.ir

More information

Unsupervised learning in Vision

Unsupervised learning in Vision Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual

More information

THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM

THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM THREE PHASE FAULT DIAGNOSIS BASED ON RBF NEURAL NETWORK OPTIMIZED BY PSO ALGORITHM M. Sivakumar 1 and R. M. S. Parvathi 2 1 Anna University, Tamilnadu, India 2 Sengunthar College of Engineering, Tamilnadu,

More information

A Boosting-Based Framework for Self-Similar and Non-linear Internet Traffic Prediction

A Boosting-Based Framework for Self-Similar and Non-linear Internet Traffic Prediction A Boosting-Based Framework for Self-Similar and Non-linear Internet Traffic Prediction Hanghang Tong 1, Chongrong Li 2, and Jingrui He 1 1 Department of Automation, Tsinghua University, Beijing 100084,

More information

COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING

COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING COLLABORATIVE AGENT LEARNING USING HYBRID NEUROCOMPUTING Saulat Farooque and Lakhmi Jain School of Electrical and Information Engineering, University of South Australia, Adelaide, Australia saulat.farooque@tenix.com,

More information

Iterative CT Reconstruction Using Curvelet-Based Regularization

Iterative CT Reconstruction Using Curvelet-Based Regularization Iterative CT Reconstruction Using Curvelet-Based Regularization Haibo Wu 1,2, Andreas Maier 1, Joachim Hornegger 1,2 1 Pattern Recognition Lab (LME), Department of Computer Science, 2 Graduate School in

More information

Classification of Hand-Written Numeric Digits

Classification of Hand-Written Numeric Digits Classification of Hand-Written Numeric Digits Nyssa Aragon, William Lane, Fan Zhang December 12, 2013 1 Objective The specific hand-written recognition application that this project is emphasizing is reading

More information

Developing a Data Driven System for Computational Neuroscience

Developing a Data Driven System for Computational Neuroscience Developing a Data Driven System for Computational Neuroscience Ross Snider and Yongming Zhu Montana State University, Bozeman MT 59717, USA Abstract. A data driven system implies the need to integrate

More information

Statistical and Learning Techniques in Computer Vision Lecture 1: Markov Random Fields Jens Rittscher and Chuck Stewart

Statistical and Learning Techniques in Computer Vision Lecture 1: Markov Random Fields Jens Rittscher and Chuck Stewart Statistical and Learning Techniques in Computer Vision Lecture 1: Markov Random Fields Jens Rittscher and Chuck Stewart 1 Motivation Up to now we have considered distributions of a single random variable

More information

Temporal Pooling Method for Rapid HTM Learning Applied to Geometric Object Recognition

Temporal Pooling Method for Rapid HTM Learning Applied to Geometric Object Recognition Temporal Pooling Method for Rapid HTM Learning Applied to Geometric Object Recognition 1,2 S. Štolc, 1,2 I. Bajla, 3 K. Valentín, 3 R. Škoviera 1 Institute of Measurement Science, Department of Theoretical

More information

Object Classification Using Tripod Operators

Object Classification Using Tripod Operators Object Classification Using Tripod Operators David Bonanno, Frank Pipitone, G. Charmaine Gilbreath, Kristen Nock, Carlos A. Font, and Chadwick T. Hawley US Naval Research Laboratory, 4555 Overlook Ave.

More information

GiRaF: a toolbox for Gibbs Random Fields analysis

GiRaF: a toolbox for Gibbs Random Fields analysis GiRaF: a toolbox for Gibbs Random Fields analysis Julien Stoehr *1, Pierre Pudlo 2, and Nial Friel 1 1 University College Dublin 2 Aix-Marseille Université February 24, 2016 Abstract GiRaF package offers

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:

More information

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Markus Turtinen, Topi Mäenpää, and Matti Pietikäinen Machine Vision Group, P.O.Box 4500, FIN-90014 University

More information

Sketchable Histograms of Oriented Gradients for Object Detection

Sketchable Histograms of Oriented Gradients for Object Detection Sketchable Histograms of Oriented Gradients for Object Detection No Author Given No Institute Given Abstract. In this paper we investigate a new representation approach for visual object recognition. The

More information

The Elimination of Correlation Errors in PIV Processing

The Elimination of Correlation Errors in PIV Processing 9 th International Symposium on Applications of Laser Techniques to Fluid Mechanics, Lisbon, Portugal, July, 1998 The Elimination of Correlation Errors in PIV Processing Douglas P. Hart Massachusetts Institute

More information

A Randomized Algorithm for Minimizing User Disturbance Due to Changes in Cellular Technology

A Randomized Algorithm for Minimizing User Disturbance Due to Changes in Cellular Technology A Randomized Algorithm for Minimizing User Disturbance Due to Changes in Cellular Technology Carlos A. S. OLIVEIRA CAO Lab, Dept. of ISE, University of Florida Gainesville, FL 32611, USA David PAOLINI

More information

Gauss-Sigmoid Neural Network

Gauss-Sigmoid Neural Network Gauss-Sigmoid Neural Network Katsunari SHIBATA and Koji ITO Tokyo Institute of Technology, Yokohama, JAPAN shibata@ito.dis.titech.ac.jp Abstract- Recently RBF(Radial Basis Function)-based networks have

More information

A Feature Point Matching Based Approach for Video Objects Segmentation

A Feature Point Matching Based Approach for Video Objects Segmentation A Feature Point Matching Based Approach for Video Objects Segmentation Yan Zhang, Zhong Zhou, Wei Wu State Key Laboratory of Virtual Reality Technology and Systems, Beijing, P.R. China School of Computer

More information

Module 7 VIDEO CODING AND MOTION ESTIMATION

Module 7 VIDEO CODING AND MOTION ESTIMATION Module 7 VIDEO CODING AND MOTION ESTIMATION Lesson 20 Basic Building Blocks & Temporal Redundancy Instructional Objectives At the end of this lesson, the students should be able to: 1. Name at least five

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction A Monte Carlo method is a compuational method that uses random numbers to compute (estimate) some quantity of interest. Very often the quantity we want to compute is the mean of

More information

CNN Template Design Using Back Propagation Algorithm

CNN Template Design Using Back Propagation Algorithm 2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA) CNN Template Design Using Back Propagation Algorithm Masashi Nakagawa, Takashi Inoue and Yoshifumi Nishio Department

More information

COMBINING NEURAL NETWORKS FOR SKIN DETECTION

COMBINING NEURAL NETWORKS FOR SKIN DETECTION COMBINING NEURAL NETWORKS FOR SKIN DETECTION Chelsia Amy Doukim 1, Jamal Ahmad Dargham 1, Ali Chekima 1 and Sigeru Omatu 2 1 School of Engineering and Information Technology, Universiti Malaysia Sabah,

More information

Iterative Removing Salt and Pepper Noise based on Neighbourhood Information

Iterative Removing Salt and Pepper Noise based on Neighbourhood Information Iterative Removing Salt and Pepper Noise based on Neighbourhood Information Liu Chun College of Computer Science and Information Technology Daqing Normal University Daqing, China Sun Bishen Twenty-seventh

More information

Image Segmentation for Image Object Extraction

Image Segmentation for Image Object Extraction Image Segmentation for Image Object Extraction Rohit Kamble, Keshav Kaul # Computer Department, Vishwakarma Institute of Information Technology, Pune kamble.rohit@hotmail.com, kaul.keshav@gmail.com ABSTRACT

More information

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment L.-M. CHANG and Y.A. ABDELRAZIG School of Civil Engineering, Purdue University,

More information

IMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM

IMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM Annals of the University of Petroşani, Economics, 12(4), 2012, 185-192 185 IMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM MIRCEA PETRINI * ABSTACT: This paper presents some simple techniques to improve

More information

Placement Algorithm for FPGA Circuits

Placement Algorithm for FPGA Circuits Placement Algorithm for FPGA Circuits ZOLTAN BARUCH, OCTAVIAN CREŢ, KALMAN PUSZTAI Computer Science Department, Technical University of Cluj-Napoca, 26, Bariţiu St., 3400 Cluj-Napoca, Romania {Zoltan.Baruch,

More information

Sampling informative/complex a priori probability distributions using Gibbs sampling assisted by sequential simulation

Sampling informative/complex a priori probability distributions using Gibbs sampling assisted by sequential simulation Sampling informative/complex a priori probability distributions using Gibbs sampling assisted by sequential simulation Thomas Mejer Hansen, Klaus Mosegaard, and Knud Skou Cordua 1 1 Center for Energy Resources

More information

Rough Set Approach to Unsupervised Neural Network based Pattern Classifier

Rough Set Approach to Unsupervised Neural Network based Pattern Classifier Rough Set Approach to Unsupervised Neural based Pattern Classifier Ashwin Kothari, Member IAENG, Avinash Keskar, Shreesha Srinath, and Rakesh Chalsani Abstract Early Convergence, input feature space with

More information

Digital correlation hologram implemented on optical correlator

Digital correlation hologram implemented on optical correlator Digital correlation hologram implemented on optical correlator David Abookasis and Joseph Rosen Ben-Gurion University of the Negev Department of Electrical and Computer Engineering P. O. Box 653, Beer-Sheva

More information

Dictionary Based Compression for Images

Dictionary Based Compression for Images Dictionary Based Compression for Images Bruno Carpentieri Abstract Lempel-Ziv methods were original introduced to compress one-dimensional data (text, object codes, etc.) but recently they have been successfully

More information

Transactions on Information and Communications Technologies vol 19, 1997 WIT Press, ISSN

Transactions on Information and Communications Technologies vol 19, 1997 WIT Press,   ISSN Hopeld Network for Stereo Correspondence Using Block-Matching Techniques Dimitrios Tzovaras and Michael G. Strintzis Information Processing Laboratory, Electrical and Computer Engineering Department, Aristotle

More information

Bayesian Statistics Group 8th March Slice samplers. (A very brief introduction) The basic idea

Bayesian Statistics Group 8th March Slice samplers. (A very brief introduction) The basic idea Bayesian Statistics Group 8th March 2000 Slice samplers (A very brief introduction) The basic idea lacements To sample from a distribution, simply sample uniformly from the region under the density function

More information

FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS

FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS FPGA IMPLEMENTATION FOR REAL TIME SOBEL EDGE DETECTOR BLOCK USING 3-LINE BUFFERS 1 RONNIE O. SERFA JUAN, 2 CHAN SU PARK, 3 HI SEOK KIM, 4 HYEONG WOO CHA 1,2,3,4 CheongJu University E-maul: 1 engr_serfs@yahoo.com,

More information