Keywords Data compression, image processing, NCD, Kolmogorov complexity, JPEG, ZIP
|
|
- Allan Russell
- 6 years ago
- Views:
Transcription
1 Volume 3, Issue 7, July 203 ISSN: X International Journal of Avance Research in Computer Science an Software Engineering Research Paper Available online at: wwwijarcssecom Compression Techniques for Image Processing Tasks Avi Roman-Gonzalez TELECOM Paris Tech Paris, rance Abstract This article aims to present an overview of the ifferent applications of ata compression techniques in the image processing file Since some time ago, several research groups in the worl have been eveloping various methos base on ifferent ata compression techniques to classify, segment, filter an etect igital images fakery In this sense, it is necessary to analyze an clarify the relationship between ifferent methos an put them into a framework to better unerstan an better exploit the possibilities that compression provies us respect to image processing techniques; compression becomes a very easy techniques to apply without much technical requirement In this article we will also see the types of compression an specific image compressors Keywors Data compression, image processing, NCD, Kolmogorov complexity, JPEG, ZIP I INTRODUCTION The work presente in this paper is an extension of the work presente in [] Actually aroun the worl, we can observe more often an increasingly, that various research groups an research works, using ata compression for ifferent applications in the image processing fiel In fact, we can see that many authors use ata compression techniques for classification an / or segmentation images, filter or enoising image, artifacts etection in images, etecting altere images, etc The analysis of igital images has a great importance in many fiels for which there are many methos, processes an techniques as shown in [2], an if the compression techniques can help more easily to these ifferent purposes, it is a breakthrough In [3] an [4] the authors present methos of image classification base on ata compression techniques, in the first case using a vieo compressor such as MPEG4 to texture classification an in the secon case is use as general purpose compressor as ZIP compressor an images compressor as JPEG lossless compressor In general, in [5] the author presents a summary of ifferent application of compression techniques in the classification of ifferent ata types The authors of [6] present a new general metho for etecting forge images also base on ata compression techniques an rate-istortion analysis, in this case, the author use the JPEG lossy compressor In [7] the authors apply lossy compression to filter the noise in the images Also the ata compression is use as a technique for artifacts etection in satellite images as shown in [8], [9] an [0] where the authors use both lossy compression an lossless compression The use of compression techniques in ifferent areas escribe above is very interesting an useful; it becomes possible on the basis of information theory, complexity theory an the various applications aroun these notions The information theory was evelope by Claue E Shannon in 948 to fin funamental limits in compression an reliable storage of ata communication Consiering the probability approach, we can establish a first principle of the measurement information This principle establishes that the message that has more probability, it provie less information This can be expresse as follows: I( xi ) I( xk ) P( xi ) P( xk ) () Where: I ( x i P( x i ) : Amount of information provie by x i ) : Probability of x i Accoring to this principle, it is the probability of a message to be sening an not its content, which etermines their informational value or a message x, with an occurrence probability P(x ), the information content can be expresse by: Where: I(x i ) will have as unit, the bit x log 2 Px I i (2) Within information theory, we have the algorithmic approach that talk about the Kolmogorov complexity K(x) which is efine as the length of the shortest program capable to proucing x on a universal machine Intuitively, K(x) is the minimum amount of information necessary to generate x through an algorithm 203, IJARCSSE All Rights Reserve Page 379
2 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp Kx min q qq x (3) Qx is the set of coes that instantly generate x The Kolmogorov complexity K(x y) from x to y is efine as the length of the shortest program that computes x when y is given as an auxiliary input for the program The function K(x y) is the length of the shortest program that prouces the concatenation of x an y But K(x) is a non-calculable function Both, the probabilistic approach of Shannon an the algorithmic approach of Kolmogorov for information theory, have a relationship with ata compression The compression serves to transport the same information, but using the least amount of space Data compression is funamentally base on search ata series repetitions There are two general approaches for compression: lossless compression an lossy compression In lossless compression approach, we can mention ZIP compressor, JPEG-LS compressor an Delta compressor Compressor ZIP is a general purpose lossless compressor base on the combination of LZW coe an the Huffman coe The compressor JPEG-LS is a lossless compressor, the algorithm begins with a preiction process, each image pixel value is preicte base on the ajacent pixels, after that, it is necessary to apply an entropy encoer, an get the compresse image Delta compression is the process of computing a compact an invertible encoing of a target file T with respect to a source file S In lossy compression approach we can mention the JPEG -DCT Compressor, the first step in this compressor is to ivie the image into blocks of 8x8 pixels, to each block, the secon step is to apply a Discrete Cosine Transform (DCT), after that, to apply a quantifier an finally an entropy encoer for to get the image compresse The structure of this paper is as follows: In Section II we present the image classification an image segmentation methos base on compression techniques Section III presents a metho for etecting forge images base on ata compression (lossy compression) In Section IV is shown a metho where ata compression also serves for image enoising Section V presents ifferent methos for artifacts etection in satellite images inally in Section VI we present the conclusions an iscussion II IMAGE CLASSIICATION AND IMAGE SEGMENTATION BASED ON COMPRESSION Base on the Normalize Compression Distance (NCD) presente an efine in [] an [2] which is one applications of Kolmogorov complexity, in [4] the authors perform image classification The Normalize Information Distance (NID) is a similarity measure proportional to the length of the shortest program that represents x given y, as far as the shortest program that represents y given x The calculate istance is normalize, meaning that its value is between 0 an, 0 when x an y are totally equal an when the maximum ifference between them NID x, y max max K x y, Ky x K x, Ky K x, y min K x, Ky maxk x, Ky (4) Since the Kolmogorov complexity K(x) is a non-calculable function, in [] the authors approximate K(x) with C(x) where C(x) is the compression factor of x Base on this approach we obtain the Normalize Compression Distance NCD (Normalize Compression Distance) C NCD x, y x, y minc x, Cy maxc x, Cy (5) Where C(x,y) is an approximation of the Kolmogorov complexity K(x,y) an represents the file size by compressing the concatenation of x an y ig Image Classification 203, IJARCSSE All Rights Reserve Page 380
3 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp or image classification using the approach base on Normalize Compression Distance (NCD); the first step is calculate the istance matrix between the images base on NCD using the Equation 5, thus ij = NCD(I i,i j ) where I i is the i-th image of the image atabase Thus, we can calculate the istance matrix D between all images I i as: D i n i2 n2 j 2 j ij nj n 2n in nn The matrix D is a square matrix of size n x n, where n is the number of images to classify in the atabase inally we can apply a supervise or non-supervise classification metho like SVM, KNN or KMEANS In this case, we apply a non-supervise classification metho like hierarchical classification enrogram like is shown in igure The enrogram is a type of graphical representation of ata as a tree that organizes the ata into subcategories that are iviing in others to reach the level of etail esire, this type of representation allows appreciating clearly the relationship between ata classes To plot the enrogram we use the Eucliean Distance metho for evaluate the istance between the ata using the following instruction in MATLAB: Calculate the Eucliean Distance (Distance = pist(d)) Linkage the istances (Tree = linkage(distance)) Rea the labels (Labels = importata('labelstxt')) Plot the enrogram: enrogram(tree,'colorthreshol','efault','labels',labels); set(denrogram,'linewith',2) There are also applications of the classification metho base on compression techniques, in remote sensing such as those presente in [3] where the authors use the NCD to classify hyperspectral image compressing the spectral signature As for classification, we can use the same metho escribe above for image segmentation The iea is to take an image an ivie it into small pieces or patches, we can calculate the istance matrix D between these ifferent patches, an then we can classify the patches that will give us as results a segmentation of the original image This kin of application is frequently for remote sensing applications or example, if we take an image I of 024 x 024 pixels an we ivie the image I in patches p i of 64 x 64 pixels, we have 256 patches p i with i =,, 256 After applying the NCD to all patches, we obtain e istance matrix D compose by ij = NCD(p i,p j ) where p i is the i-th patch of the image D i n i2 n2 j 2 j ij nj n 2n in nn inally with this istance matrix D, we can apply a supervise or non-supervise classification metho like SVM, KNN or KMEANS ig 2 Image Segmentation 203, IJARCSSE All Rights Reserve Page 38
4 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp In igure 2 we can observe an example of the image segmentation base on compression techniques applie to an Earth observation image We can see clearly the goo segmentation between city environment an fiel environment III IMAGE KERY DETECTION In [6] the authors use the Rate-Distortion experimental curve (RD) using lossy compression, JPEG DCT lossy compressor The RD function inirectly measure the visual complexity of the images, for example, plotting the experimental RD curve where the horizontal axis represents the compression factor (size of the compresse image file / size of the original image file) an the vertical axis represents the istortion calculate using the Mean Square Error (MSE); we can make an analysis of the image We can say that the falsification of an image can alter the experimental RD curve of the image, for example we can see from igure 3 that shown in (a) an original image an (b) the same image but with an alteration which the person has been remove (a) Original Image [6] (b) Manipulate Image [6] ig 3: (a) Original photograph of a Car Show (b) is the same image (a) but the person was erase an replace by uplication of regions Analyzing the image of igure 3 (a) an (b) using the graph of the experimental RD curves, it can be seen that there is a variation on these curves ue to the manipulation of the image igure 4 shows the variation, with the blue curve for igure 3 (b) an the green curve for igure 3 (a) Thus, using the variation in the experimental curve RD of images, we can etect when an image was manipulate or not ig 4 Rate-Distortion Experimental curve, the horizontal axis represents the compression factor (size of the compresse image file / size of the original image file), the vertical axis represents the istortion calculate using the MSE (mean square error) Blue for igure 3 (a) an green for igure 3 (b), the RD experimental curve of the original image is ifferent from the experimental curve RD for image that contains manipulations [6] 203, IJARCSSE All Rights Reserve Page 382
5 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp Also it is possible to use the Kolmogorov Structure unction (KS) for image fakery etection In [4] the authors present an analysis about the Kolmogorv s structure function The relation between an iniviual ata an its moel is expresse by Kolmogorov s structure function The original Kolmogorov structure function for a ata x is efine by: min log S : S x, K( S) hx (6) S Where: S is a contemplate moel for x α is a non-negative integer value bouning the complexity of the contemplate S The Kolmogorov s structure function h x (α) tell us all stochastic properties of ata x [4] In the same way, it is introuce the Best-it function, given by: Where: x is regare as a typical member of S ( ) min ( x S): S x, K( S) x (7) S The MDL function is given by: ( ) min ( S): S x, K( S) x (8) S Where: ( S) log S K( S) K( x) O() (9) (S) is the total length of two parts of x coe with an S moel The conitional Kolmogorov structure function is given by: h ( i y) min log S : S x, K( S y) i (0) x S The Kolmogorov structure function is a non-computable since the Kolmogorov complexity is also a non-computable function; that is the reason why we use the compression factor as an approximation to complexity The KS is an approximation of the Rate-unction Distortion using Kolmogorov complexity theory In that sense, we will use this function to see the changes in the experimental curve of the KS when the image is manipulate, we will use the same test images were use for analysis with the RD curve In igure 5 we can observe the KS curves for images in igure 3, the blue curve for the image (a) an the green curve for image (b) x ig 5 Experimental KS curve, the horizontal axis represents the Kolmogorov complexity approximation as the size of the image compresse file in bytes, the vertical axis represents the amount of bits that is neee to represent a moel of original image Blue for igure 3 (a) an green for igure 3 (b), the KS experimental curve of the original image is ifferent from the experimental curve KS for image that contains manipulations [6] It can be seen that as RD curves, in KS curves, variation may be observe when there is a manipulation of images, we use this variation to etermine whether an image has been altere or not 203, IJARCSSE All Rights Reserve Page 383 x 0 6
6 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp IV IMAGE DENOISING A metho for filtering an enoising is presente in [7] where the authors use lossy compression techniques for computing experimental RD curve of an image while calculating the Minimum Description Length function [7] an thus obtain the minimum point an ientify the image whose noise was eliminate by lossy compression Similarly, we can use a new calculation of experimental RD curve as a measure of istortion using the Normalize Compression Distance NCD between the error E (prouce by the ifference between the original image X an the compresse-ecompresse image Y) an the compresse-ecompresse image Y The Rate-NCD(E,Y) curve between the error E an the compresse-ecompresse image Y shoul have a particular behavior as shown in igure 6, for a moment, when there is not much compression, the compresse-ecompresse image Y is almost equal to the original image X an hence the error E is little information which makes the istance between E an Y large, this istance ecreases as the compression increases, because the information is going to error an this will seem a bit to the image, but there comes a point (calle here ARG point) which shoul be more information on the error E that on the compresse-ecompresse image Y thus the istance between them will increase again ARG point ig 6 Rate-NCD curve, hypothetical comparison between the error E an the compresse-ecompresse image Y In this way we can ientify the minimum point (ARG point) which woul correspon to the image without noise as shown in igure 7 (using the same image use in [7]) This process can also serve to inicate how to fin the minimum amount of information neee to interpret the information, how much etail we can loss without to arrive until a not interpretable ata In igure 7, we can see clearly that the mouse image for the minimum point has the enough etail to recognize a mouse ARG point ig 7 Image Denoising V ARTIACT DETECTION In the research works [8], [9] y [0], the authors present ifferent methos for artifacts etection in satellite images, ifferent methos base on compression techniques, lossless compression an lossy compression The metho that has better results is the metho that uses a lossy compression to calculate the experimental RD curve presente in [0] The iea is to examine how an artifact can have a high egree of regularity or irregularity for compression [0] an analyze the error space prouce by the lossy compression The RD analysis was one as the blocks iagram shown in igure 8 203, IJARCSSE All Rights Reserve Page 384
7 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp ig 8 Block Diagram for Rate-Distortion Analysis [0] irst the author take the image uner test I, they ive the image I in ifferent n patches X i of 64 x 64 pixels, with i =, 2,, n, thus I = {X, X 2, X n } or each i-th patch X i, they compress the patch with ifferent quality q using a lossy compression, using ifferent quality they obtain ifferent compression factor After that, they ecompress the image an obtain a ecompresse image Y iq The next step is to calculate the error for each compression factor between the original patch X i an the compresse-ecompresse patch Y iq, for calculate the error; they use the Mean Square Error (MSE) Base on the errors for each compression factor q an for each patch X i, they compose a features vector V i = [ i, i2, iq iq ] where iq = MSE(X i, Y iq ) Thus, they have a matrix: V i n i2 n2 q 2q iq nq Q 2Q iq nq inally, with this matrix V, they apply a supervise or non-supervise classification metho like SVM, KNN or KMEANS In this case, the authors use KMEANS classification metho, which is an unsupervise algorithm; KMEANS classifies ata accoring to K (positive an integer value) centrois or groups as assigne, the algorithm calculates the minimum istance of these centrois to all other ata an the group as the minimum istance or our purpose, we take a value of K = 2 that represents one group for images with artifacts an other group for images without artifacts or authors, the quality factor vary between 0 an 00, so Q = 0, an for an image of 52 x 52 pixels, we obtain 64 patches of 64 x 64 pixels, thus n woul be n = 64 An example of the application of this metho base on the RD analysis is the Dropout etection shown in igure 9, In this case it is a SPOT image containing actual artifacts, an the etection is one correctly (a) CNES (b) ig 9 Dropout (SPOT) (a) Some electronic losses uring the image formation process create these ranomly saturate pixels The ropouts often follow a line pattern (corresponing to the structure of the SPOT sensor) (b) Artifact is etecte 203, IJARCSSE All Rights Reserve Page 385
8 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp Another metho for artifacts etection is base on the similarity space using the Normalize Compression Distance (NCD), the authors propose to analysis the possible similarity between images with artifacts ue to possible similarity pattern between artifacts The first step is to take the satellite image I an ivie it into n patches X i of 64x64 pixels like is shown in igure 0, with i =, 2,, n, thus I = {X, X 2, X n } With these patches X i, after that, it is necessary to calculate the istance matrix between them using the NCD, thus we have ij = NCD(X i,x j ) Thus, it is possible to calculate the istance matrix D between all patches X i as: D i n i2 n2 j 2 j ij nj n 2n in nn The matrix D is a square matrix of size n x n, where n is the number of patches; for an image of 52 x 52 pixels, we obtain 64 patches of 64 x 64 pixels, thus n woul be n = 64 ig 0 Separate image in patches of 64x64 pixels for calculate the istance matrix between the patches inally, with this istance matrix D, the authors apply a non-supervise classification metho like hierarchical classification enrogram like is shown in igure 2 The enrogram is a type of graphical representation of ata as a tree that organizes the ata into subcategories that are iviing in others to reach the level of etail esire, this type of representation allows appreciating clearly the relationship between ata classes The blocks iagram an process for application of this metho base on NCD to artifacts etection, is represente in igure ig Experiment Process: we take the satellite image an ivie it into patches of 64x64 pixels, with these patches we calculate the istance matrix between them using NCD an finally we applie a hierarchical classification metho to cluster an ientify the patches with artifacts We use the NCD to evaluate how patches with artifacts can have a similar structure an see if it is possible to make a cluster with all patches with artifacts 203, IJARCSSE All Rights Reserve Page 386
9 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp Patches without Artifacts Patches with Artifacts ig 2 Hierarchical Classification of the Patches: we can see two cluster, re cluster for patches with artifacts, an cyan cluster for patches without artifacts In this enrogram representation, we can observe clearly how the patches with artifacts an the patches without artifacts can form two ifferent clusters in certain hierarchical level VI CONCLUSIONS AND DISCUSSION As has been seen, there are many stuies which use ata compression techniques for image processing purposes In this paper we have trie to present the ifferent evelopments mae by numerous research groups aroun the worl about the applications of ata compression, specifically in image processing Each group uses ifferent techniques, ifferent types of compression methos an ifferent approaches for ifferent applications but all of them relate to two important points: the compression an its application to image analysis in orer to make this task easier, unerstanable an with goo results The use of compression techniques in image processing, makes this task easier an more accessible, since everyboy know to use a compressor, everyboy use a compressors in your aily lives to reuce the size of the files an to transmit or transport them more efficiently No specific knowlege is neee to use a compressor Through this article, we provie the backgroun an funaments to better unerstan why we can use ata compression on igital image analysis an thus continue to evelop more applications an improving existing ones It was clearly observe that the application of ata compression for image processing is entirely feasible It is possible because ata compression is fully relate to the information theory in the two approaches In the image processing an image analyzing, the important thing is the image information content, base on this information we can reach a correct analysis The results obtaine in the ifferent applications are very encouraging, so it is necessary to continue in this line of research an evelop more applications REERENCES [] A Roman-Gonzalez, K Asale-Alvarez, Image Processing by Compression, Worl Congress on Engineering an Computer Science WCECS 202; San rancisco USA; October 202; pp [2] A Roman-Gonzalez, Digital Images Analysis, Revista ECIPeru, vol 9, N, 202, pp 6-68 [3] BJL Campana y EJ Keogh, A Compression Base Distance Measure for Texture, University of California, Riversie, EEUU , IJARCSSE All Rights Reserve Page 387
10 Gonzalez et al, International Journal of Avance Research in Computer Science an Software Engineering 3(7), July - 203, pp [4] M R Quispe-Ayala, K Asale-Alvarez, A Roman-Gonzalez, Image Classification Using Data Compression Techniques ; 200 IEEE 26th Convention of Electrical an Electronics Engineers in Israel IEEEI 200; Eilat Israel; November 200, pp [5] A Roman-Gonzalez, Clasificación e Datos Basao en Compresión, Revista ECIPeru, vol 9, N, 202, pp [6] A Roman-Gonzalez, CJ Reynaga-Carenas, Implementacion e un Métoo General para la Detección e Imágenes Alteraas Utilizano Técnicas e Compresion, Engineering Thesis, Universia Anina el Cusco, 202 [7] S Rooij, P Vitanyi, Approximating Rate-Distortion Graphs of iniviual Data: Experiments in Lossy Compression an Denoising, IEEE Transaction on Computers, vol6, N 3, March 202, pp [8] A Roman-Gonzalez, M Datcu, Satellite Image Artifacts Detection Base on Complexity istortion Theory, IEEE International Geosciences an Remote Sensing Symposium IGARSS 20, Vancouver Canaa, July 20, pp [9] A Roman-Gonzalez, M Datcu, Data Cleaning: Approaches for Earth Observation Image Information Mining, ESA-JRC-EUSC Image Information Mining: Geospatial Intelligence from Earth Observation Conference, Ispra Italy, March 30 April, 200, pp 7-20 [0] A Roman-Gonzalez, M Datcu, Parameter ree Image Artifacts Detection: A Compression Base Approach, 200 SPIE Remote Sensing, vol 7830, , Toulouse rance, September 200 [] M Li an P Vitányi, The Similarity Metric, IEEE Transaction on Information Theory, vol 50, N 2, 2004, pp [2] R Cilibrasi, P M B Vitanyi; Clustering by Compression, IEEE Transaction on Information Theory, vol 5, N 4, April 2005, pp [3] A Roman-Gonzalez, M A Veganzones, M Graña, M Datcu, A Novel Data Compression for Remote Sensing ata Mining, ESA-JRC-EUSC Image Information Mining: Geospatial Intelligence from Earth Observation Conference, Ispra Italy, March 30 April, 200, pp 0-04 [4] N K Vereshchagin, P M B Vitanyi; (2004, iciembre); Kolmogorov s Structure unctions an Moel Selection ; IEEE Transaction on Information Theory, Vol 50, N 2, pp [5] Tussell, Complejia Estocástica, San Sebastián 996 [6] D McKay, Information Theory, Inference, an Learning Algorithms, Cambrige University Press, , IJARCSSE All Rights Reserve Page 388
Parameter Free Image Artifacts Detection: A Compression Based Approach
Parameter Free Image Artifacts Detection: A Compression Based Approach Avid Roman-Gonzalez a*, Mihai Datcu b a TELECOM ParisTech, 75013 Paris, France b German Aerospace Center (DLR), Oberpfaffenhofen ABSTRACT
More informationImage Classification Using Data Compression Techniques
Image Classification Using Data Compression Techniques Martha Roxana Quispe Ayala, Krista Asalde Alvarez, Avid Roman Gonzalez To cite this version: Martha Roxana Quispe Ayala, Krista Asalde Alvarez, Avid
More informationImage Segmentation using K-means clustering and Thresholding
Image Segmentation using Kmeans clustering an Thresholing Preeti Panwar 1, Girhar Gopal 2, Rakesh Kumar 3 1M.Tech Stuent, Department of Computer Science & Applications, Kurukshetra University, Kurukshetra,
More informationFeature Extraction and Rule Classification Algorithm of Digital Mammography based on Rough Set Theory
Feature Extraction an Rule Classification Algorithm of Digital Mammography base on Rough Set Theory Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative
More informationRough Set Approach for Classification of Breast Cancer Mammogram Images
Rough Set Approach for Classification of Breast Cancer Mammogram Images Aboul Ella Hassanien Jafar M. H. Ali. Kuwait University, Faculty of Aministrative Science, Quantitative Methos an Information Systems
More informationThe SNCD as a Metrics for Image Quality Assessment
The SNCD as a Metrics for Image Qualit Assessment Avid Roman-Gonzalez TELECOM ParisTech, Departement TSI Paris, France Abstract In our era, when we have a lot of instrument to capture digital images and
More informationTHE BAYESIAN RECEIVER OPERATING CHARACTERISTIC CURVE AN EFFECTIVE APPROACH TO EVALUATE THE IDS PERFORMANCE
БСУ Международна конференция - 2 THE BAYESIAN RECEIVER OPERATING CHARACTERISTIC CURVE AN EFFECTIVE APPROACH TO EVALUATE THE IDS PERFORMANCE Evgeniya Nikolova, Veselina Jecheva Burgas Free University Abstract:
More informationShift-map Image Registration
Shift-map Image Registration Svärm, Linus; Stranmark, Petter Unpublishe: 2010-01-01 Link to publication Citation for publishe version (APA): Svärm, L., & Stranmark, P. (2010). Shift-map Image Registration.
More informationOnline Appendix to: Generalizing Database Forensics
Online Appenix to: Generalizing Database Forensics KYRIACOS E. PAVLOU an RICHARD T. SNODGRASS, University of Arizona This appenix presents a step-by-step iscussion of the forensic analysis protocol that
More informationA PSO Optimized Layered Approach for Parametric Clustering on Weather Dataset
Vol.3, Issue.1, Jan-Feb. 013 pp-504-508 ISSN: 49-6645 A PSO Optimize Layere Approach for Parametric Clustering on Weather Dataset Shikha Verma, 1 Kiran Jyoti 1 Stuent, Guru Nanak Dev Engineering College
More informationStudy of Network Optimization Method Based on ACL
Available online at www.scienceirect.com Proceia Engineering 5 (20) 3959 3963 Avance in Control Engineering an Information Science Stuy of Network Optimization Metho Base on ACL Liu Zhian * Department
More informationFast Fractal Image Compression using PSO Based Optimization Techniques
Fast Fractal Compression using PSO Base Optimization Techniques A.Krishnamoorthy Visiting faculty Department Of ECE University College of Engineering panruti rishpci89@gmail.com S.Buvaneswari Visiting
More informationNEW METHOD FOR FINDING A REFERENCE POINT IN FINGERPRINT IMAGES WITH THE USE OF THE IPAN99 ALGORITHM 1. INTRODUCTION 2.
JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 13/009, ISSN 164-6037 Krzysztof WRÓBEL, Rafał DOROZ * fingerprint, reference point, IPAN99 NEW METHOD FOR FINDING A REFERENCE POINT IN FINGERPRINT IMAGES
More informationClassifying Facial Expression with Radial Basis Function Networks, using Gradient Descent and K-means
Classifying Facial Expression with Raial Basis Function Networks, using Graient Descent an K-means Neil Allrin Department of Computer Science University of California, San Diego La Jolla, CA 9237 nallrin@cs.ucs.eu
More informationCoupling the User Interfaces of a Multiuser Program
Coupling the User Interfaces of a Multiuser Program PRASUN DEWAN University of North Carolina at Chapel Hill RAJIV CHOUDHARY Intel Corporation We have evelope a new moel for coupling the user-interfaces
More informationYet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama and Hayato Ohwada Faculty of Sci. and Tech. Tokyo University of Scien
Yet Another Parallel Hypothesis Search for Inverse Entailment Hiroyuki Nishiyama an Hayato Ohwaa Faculty of Sci. an Tech. Tokyo University of Science, 2641 Yamazaki, Noa-shi, CHIBA, 278-8510, Japan hiroyuki@rs.noa.tus.ac.jp,
More informationObject Recognition Using Colour, Shape and Affine Invariant Ratios
Object Recognition Using Colour, Shape an Affine Invariant Ratios Paul A. Walcott Centre for Information Engineering City University, Lonon EC1V 0HB, Englan P.A.Walcott@city.ac.uk Abstract This paper escribes
More informationModelling image complexity by independent component analysis, with application to content-based image retrieval
Modelling image complexity by independent component analysis, with application to content-based image retrieval Jukka Perkiö 1,2 and Aapo Hyvärinen 1,2,3 1 Helsinki Institute for Information Technology,
More informationTHE APPLICATION OF ARTICLE k-th SHORTEST TIME PATH ALGORITHM
International Journal of Physics an Mathematical Sciences ISSN: 2277-2111 (Online) 2016 Vol. 6 (1) January-March, pp. 24-6/Mao an Shi. THE APPLICATION OF ARTICLE k-th SHORTEST TIME PATH ALGORITHM Hua Mao
More informationCluster Center Initialization Method for K-means Algorithm Over Data Sets with Two Clusters
Available online at www.scienceirect.com Proceia Engineering 4 (011 ) 34 38 011 International Conference on Avances in Engineering Cluster Center Initialization Metho for K-means Algorithm Over Data Sets
More informationShift-map Image Registration
Shift-map Image Registration Linus Svärm Petter Stranmark Centre for Mathematical Sciences, Lun University {linus,petter}@maths.lth.se Abstract Shift-map image processing is a new framework base on energy
More informationA New Search Algorithm for Solving Symmetric Traveling Salesman Problem Based on Gravity
Worl Applie Sciences Journal 16 (10): 1387-1392, 2012 ISSN 1818-4952 IDOSI Publications, 2012 A New Search Algorithm for Solving Symmetric Traveling Salesman Problem Base on Gravity Aliasghar Rahmani Hosseinabai,
More informationAPPLYING GENETIC ALGORITHM IN QUERY IMPROVEMENT PROBLEM. Abdelmgeid A. Aly
International Journal "Information Technologies an Knowlege" Vol. / 2007 309 [Project MINERVAEUROPE] Project MINERVAEUROPE: Ministerial Network for Valorising Activities in igitalisation -
More informationLecture 1 September 4, 2013
CS 84r: Incentives an Information in Networks Fall 013 Prof. Yaron Singer Lecture 1 September 4, 013 Scribe: Bo Waggoner 1 Overview In this course we will try to evelop a mathematical unerstaning for the
More informationA multiple wavelength unwrapping algorithm for digital fringe profilometry based on spatial shift estimation
University of Wollongong Research Online Faculty of Engineering an Information Sciences - Papers: Part A Faculty of Engineering an Information Sciences 214 A multiple wavelength unwrapping algorithm for
More informationThreshold Based Data Aggregation Algorithm To Detect Rainfall Induced Landslides
Threshol Base Data Aggregation Algorithm To Detect Rainfall Inuce Lanslies Maneesha V. Ramesh P. V. Ushakumari Department of Computer Science Department of Mathematics Amrita School of Engineering Amrita
More information6 Gradient Descent. 6.1 Functions
6 Graient Descent In this topic we will iscuss optimizing over general functions f. Typically the function is efine f : R! R; that is its omain is multi-imensional (in this case -imensional) an output
More information5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015)
5th International Conference on Avance Design an Manufacturing Engineering (ICADME 25) Research on motion characteristics an application of multi egree of freeom mechanism base on R-W metho Xiao-guang
More informationA Neural Network Model Based on Graph Matching and Annealing :Application to Hand-Written Digits Recognition
ITERATIOAL JOURAL OF MATHEMATICS AD COMPUTERS I SIMULATIO A eural etwork Moel Base on Graph Matching an Annealing :Application to Han-Written Digits Recognition Kyunghee Lee Abstract We present a neural
More informationAlmost Disjunct Codes in Large Scale Multihop Wireless Network Media Access Control
Almost Disjunct Coes in Large Scale Multihop Wireless Network Meia Access Control D. Charles Engelhart Anan Sivasubramaniam Penn. State University University Park PA 682 engelhar,anan @cse.psu.eu Abstract
More informationModifying ROC Curves to Incorporate Predicted Probabilities
Moifying ROC Curves to Incorporate Preicte Probabilities Cèsar Ferri DSIC, Universitat Politècnica e València Peter Flach Department of Computer Science, University of Bristol José Hernánez-Orallo DSIC,
More informationGeneralized Edge Coloring for Channel Assignment in Wireless Networks
Generalize Ege Coloring for Channel Assignment in Wireless Networks Chun-Chen Hsu Institute of Information Science Acaemia Sinica Taipei, Taiwan Da-wei Wang Jan-Jan Wu Institute of Information Science
More informationParticle Swarm Optimization Based on Smoothing Approach for Solving a Class of Bi-Level Multiobjective Programming Problem
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 17, No 3 Sofia 017 Print ISSN: 1311-970; Online ISSN: 1314-4081 DOI: 10.1515/cait-017-0030 Particle Swarm Optimization Base
More informationCS 106 Winter 2016 Craig S. Kaplan. Module 01 Processing Recap. Topics
CS 106 Winter 2016 Craig S. Kaplan Moule 01 Processing Recap Topics The basic parts of speech in a Processing program Scope Review of syntax for classes an objects Reaings Your CS 105 notes Learning Processing,
More informationNew Version of Davies-Bouldin Index for Clustering Validation Based on Cylindrical Distance
New Version of Davies-Boulin Inex for lustering Valiation Base on ylinrical Distance Juan arlos Roas Thomas Faculta e Informática Universia omplutense e Mari Mari, España correoroas@gmail.com Abstract
More informationEstimating Velocity Fields on a Freeway from Low Resolution Video
Estimating Velocity Fiels on a Freeway from Low Resolution Vieo Young Cho Department of Statistics University of California, Berkeley Berkeley, CA 94720-3860 Email: young@stat.berkeley.eu John Rice Department
More informationHere are a couple of warnings to my students who may be here to get a copy of what happened on a day that you missed.
Preface Here are my online notes for my Calculus I course that I teach here at Lamar University. Despite the fact that these are my class notes, they shoul be accessible to anyone wanting to learn Calculus
More informationEvolutionary Optimisation Methods for Template Based Image Registration
Evolutionary Optimisation Methos for Template Base Image Registration Lukasz A Machowski, Tshilizi Marwala School of Electrical an Information Engineering University of Witwatersran, Johannesburg, South
More informationKinematic Analysis of a Family of 3R Manipulators
Kinematic Analysis of a Family of R Manipulators Maher Baili, Philippe Wenger an Damien Chablat Institut e Recherche en Communications et Cybernétique e Nantes, UMR C.N.R.S. 6597 1, rue e la Noë, BP 92101,
More informationResearch Article Research on Law s Mask Texture Analysis System Reliability
Research Journal of Applie Sciences, Engineering an Technology 7(19): 4002-4007, 2014 DOI:10.19026/rjaset.7.761 ISSN: 2040-7459; e-issn: 2040-7467 2014 Maxwell Scientific Publication Corp. Submitte: November
More informationMultilevel Linear Dimensionality Reduction using Hypergraphs for Data Analysis
Multilevel Linear Dimensionality Reuction using Hypergraphs for Data Analysis Haw-ren Fang Department of Computer Science an Engineering University of Minnesota; Minneapolis, MN 55455 hrfang@csumneu ABSTRACT
More informationCharacterizing Decoding Robustness under Parametric Channel Uncertainty
Characterizing Decoing Robustness uner Parametric Channel Uncertainty Jay D. Wierer, Wahee U. Bajwa, Nigel Boston, an Robert D. Nowak Abstract This paper characterizes the robustness of ecoing uner parametric
More informationResearch Article Inviscid Uniform Shear Flow past a Smooth Concave Body
International Engineering Mathematics Volume 04, Article ID 46593, 7 pages http://x.oi.org/0.55/04/46593 Research Article Invisci Uniform Shear Flow past a Smooth Concave Boy Abullah Mura Department of
More informationfiltering LETTER An Improved Neighbor Selection Algorithm in Collaborative Taek-Hun KIM a), Student Member and Sung-Bong YANG b), Nonmember
107 IEICE TRANS INF & SYST, VOLE88 D, NO5 MAY 005 LETTER An Improve Neighbor Selection Algorithm in Collaborative Filtering Taek-Hun KIM a), Stuent Member an Sung-Bong YANG b), Nonmember SUMMARY Nowaays,
More informationReconstructing the Nonlinear Filter Function of LILI-128 Stream Cipher Based on Complexity
Reconstructing the Nonlinear Filter Function of LILI-128 Stream Cipher Base on Complexity Xiangao Huang 1 Wei Huang 2 Xiaozhou Liu 3 Chao Wang 4 Zhu jing Wang 5 Tao Wang 1 1 College of Engineering, Shantou
More informationSkyline Community Search in Multi-valued Networks
Syline Community Search in Multi-value Networs Rong-Hua Li Beijing Institute of Technology Beijing, China lironghuascut@gmail.com Jeffrey Xu Yu Chinese University of Hong Kong Hong Kong, China yu@se.cuh.eu.h
More informationImage compression predicated on recurrent iterated function systems
2n International Conference on Mathematics & Statistics 16-19 June, 2008, Athens, Greece Image compression preicate on recurrent iterate function systems Chol-Hui Yun *, Metzler W. a an Barski M. a * Faculty
More informationPreamble. Singly linked lists. Collaboration policy and academic integrity. Getting help
CS2110 Spring 2016 Assignment A. Linke Lists Due on the CMS by: See the CMS 1 Preamble Linke Lists This assignment begins our iscussions of structures. In this assignment, you will implement a structure
More informationA new fuzzy visual servoing with application to robot manipulator
2005 American Control Conference June 8-10, 2005. Portlan, OR, USA FrA09.4 A new fuzzy visual servoing with application to robot manipulator Marco A. Moreno-Armenariz, Wen Yu Abstract Many stereo vision
More informationNon-homogeneous Generalization in Privacy Preserving Data Publishing
Non-homogeneous Generalization in Privacy Preserving Data Publishing W. K. Wong, Nios Mamoulis an Davi W. Cheung Department of Computer Science, The University of Hong Kong Pofulam Roa, Hong Kong {wwong2,nios,cheung}@cs.hu.h
More informationOn the Role of Multiply Sectioned Bayesian Networks to Cooperative Multiagent Systems
On the Role of Multiply Sectione Bayesian Networks to Cooperative Multiagent Systems Y. Xiang University of Guelph, Canaa, yxiang@cis.uoguelph.ca V. Lesser University of Massachusetts at Amherst, USA,
More informationCLASS BASED RATIOING EFFECT ON SUB-PIXEL SINGLE LAND COVER AUTOMATIC MAPPING
CLSS BSED RTIOIG EFFECT O SUB-PIXEL SIGLE LD COVER UTOMTIC MPPIG nil Kumar *a, Suresh Saggar b, a Inian Institute of Remote Sensing, Dehraun, anil@iirs.gov.in b Birla Institute of Technology & Science,
More informationA Plane Tracker for AEC-automation Applications
A Plane Tracker for AEC-automation Applications Chen Feng *, an Vineet R. Kamat Department of Civil an Environmental Engineering, University of Michigan, Ann Arbor, USA * Corresponing author (cforrest@umich.eu)
More information1 Surprises in high dimensions
1 Surprises in high imensions Our intuition about space is base on two an three imensions an can often be misleaing in high imensions. It is instructive to analyze the shape an properties of some basic
More informationUsing Vector and Raster-Based Techniques in Categorical Map Generalization
Thir ICA Workshop on Progress in Automate Map Generalization, Ottawa, 12-14 August 1999 1 Using Vector an Raster-Base Techniques in Categorical Map Generalization Beat Peter an Robert Weibel Department
More information3D CITY REGISTRATION AND ENRICHMENT
3D CITY REGISTRATION AND ENRICHMENT J. A. Quinn, P. D. Smart an C. B. Jones School of Computer Science, Cariff University {j.a.quinn, p.smart, c.b.jones}@cs.cf.ac.uk KEY WORDS: City moels, registration,
More informationLearning Subproblem Complexities in Distributed Branch and Bound
Learning Subproblem Complexities in Distribute Branch an Boun Lars Otten Department of Computer Science University of California, Irvine lotten@ics.uci.eu Rina Dechter Department of Computer Science University
More informationRobust Camera Calibration for an Autonomous Underwater Vehicle
obust Camera Calibration for an Autonomous Unerwater Vehicle Matthew Bryant, Davi Wettergreen *, Samer Aballah, Alexaner Zelinsky obotic Systems Laboratory Department of Engineering, FEIT Department of
More informationComparative Study of Projection/Back-projection Schemes in Cryo-EM Tomography
Comparative Stuy of Projection/Back-projection Schemes in Cryo-EM Tomography Yu Liu an Jong Chul Ye Department of BioSystems Korea Avance Institute of Science an Technology, Daejeon, Korea ABSTRACT In
More informationTight Wavelet Frame Decomposition and Its Application in Image Processing
ITB J. Sci. Vol. 40 A, No., 008, 151-165 151 Tight Wavelet Frame Decomposition an Its Application in Image Processing Mahmu Yunus 1, & Henra Gunawan 1 1 Analysis an Geometry Group, FMIPA ITB, Banung Department
More informationEFFICIENT STEREO MATCHING BASED ON A NEW CONFIDENCE METRIC. Won-Hee Lee, Yumi Kim, and Jong Beom Ra
th European Signal Processing Conference (EUSIPCO ) Bucharest, omania, August 7-3, EFFICIENT STEEO MATCHING BASED ON A NEW CONFIDENCE METIC Won-Hee Lee, Yumi Kim, an Jong Beom a Department of Electrical
More informationDEVELOPMENT OF DamageCALC APPLICATION FOR AUTOMATIC CALCULATION OF THE DAMAGE INDICATOR
Mechanical Testing an Diagnosis ISSN 2247 9635, 2012 (II), Volume 4, 28-36 DEVELOPMENT OF DamageCALC APPLICATION FOR AUTOMATIC CALCULATION OF THE DAMAGE INDICATOR Valentina GOLUBOVIĆ-BUGARSKI, Branislav
More informationInvestigation into a new incremental forming process using an adjustable punch set for the manufacture of a doubly curved sheet metal
991 Investigation into a new incremental forming process using an ajustable punch set for the manufacture of a oubly curve sheet metal S J Yoon an D Y Yang* Department of Mechanical Engineering, Korea
More informationComparison of Methods for Increasing the Performance of a DUA Computation
Comparison of Methos for Increasing the Performance of a DUA Computation Michael Behrisch, Daniel Krajzewicz, Peter Wagner an Yun-Pang Wang Institute of Transportation Systems, German Aerospace Center,
More informationMEASURING THE PERFORMANCE OF SIMILARITY PROPAGATION IN AN SEMANTIC SEARCH ENGINE
ISSN: 9-6956 (ONLINE) DOI: 10.1917/isc.013.0096 ICTACT JOURNAL ON SOFT COMPUTING, OCTOBER 013, VOLUME: 04, ISSUE: 01 MEASURING THE PERFORMANCE OF SIMILARITY PROPAGATION IN AN SEMANTIC SEARCH ENGINE S.
More informationFast Window Based Stereo Matching for 3D Scene Reconstruction
The International Arab Journal of Information Technology, Vol. 0, No. 3, May 203 209 Fast Winow Base Stereo Matching for 3D Scene Reconstruction Mohamma Mozammel Chowhury an Mohamma AL-Amin Bhuiyan Department
More informationConsidering bounds for approximation of 2 M to 3 N
Consiering bouns for approximation of to (version. Abstract: Estimating bouns of best approximations of to is iscusse. In the first part I evelop a powerseries, which shoul give practicable limits for
More informationPolitehnica University of Timisoara Mobile Computing, Sensors Network and Embedded Systems Laboratory. Testing Techniques
Politehnica University of Timisoara Mobile Computing, Sensors Network an Embee Systems Laboratory ing Techniques What is testing? ing is the process of emonstrating that errors are not present. The purpose
More information1/5/2014. Bedrich Benes Purdue University Dec 12 th 2013 INRIA Imagine. Modeling is an open problem in CG
Berich Benes Purue University Dec 12 th 213 INRIA Imagine Inverse Proceural Moeling (IPM) Motivation IPM Classification Case stuies IPM of volumetric builings IPM of stochastic trees Urban reparameterization
More informationCONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen
Proceeings of ACIVS 2002 (Avance Concepts for Intelligent Vision Systems), Ghent, Belgium, September 9-11, 2002 CONTENT-BASED RETRIEVAL OF DEFECT IMAGES Jukka Iivarinen an Jussi Pakkanen jukka.iivarinen@hut.fi,
More informationClustering using Particle Swarm Optimization. Nuria Gómez Blas, Octavio López Tolic
24 International Journal Information Theories an Applications, Vol. 23, Number 1, (c) 2016 Clustering using Particle Swarm Optimization Nuria Gómez Blas, Octavio López Tolic Abstract: Data clustering has
More informationA Cost Model For Nearest Neighbor Search. High-Dimensional Data Space
A Cost Moel For Nearest Neighbor Search in High-Dimensional Data Space Stefan Berchtol University of Munich Germany berchtol@informatikuni-muenchene Daniel A Keim University of Munich Germany keim@informatikuni-muenchene
More informationAdjacency Matrix Based Full-Text Indexing Models
1000-9825/2002/13(10)1933-10 2002 Journal of Software Vol.13, No.10 Ajacency Matrix Base Full-Text Inexing Moels ZHOU Shui-geng 1, HU Yun-fa 2, GUAN Ji-hong 3 1 (Department of Computer Science an Engineering,
More informationEstimation of large-amplitude motion and disparity fields: Application to intermediate view reconstruction
c 2000 SPIE. Personal use of this material is permitte. However, permission to reprint/republish this material for avertising or promotional purposes or for creating new collective works for resale or
More informationSynthesis Distortion Estimation in 3D Video Using Frequency and Spatial Analysis
MITSUBISHI EECTRIC RESEARCH ABORATORIES http://www.merl.com Synthesis Distortion Estimation in 3D Vieo Using Frequency an Spatial Analysis Fang,.; Cheung, N-M; Tian, D.; Vetro, A.; Sun, H.; Yu,. TR2013-087
More informationAnimated Surface Pasting
Animate Surface Pasting Clara Tsang an Stephen Mann Computing Science Department University of Waterloo 200 University Ave W. Waterloo, Ontario Canaa N2L 3G1 e-mail: clftsang@cgl.uwaterloo.ca, smann@cgl.uwaterloo.ca
More informationAn Adaptive Routing Algorithm for Communication Networks using Back Pressure Technique
International OPEN ACCESS Journal Of Moern Engineering Research (IJMER) An Aaptive Routing Algorithm for Communication Networks using Back Pressure Technique Khasimpeera Mohamme 1, K. Kalpana 2 1 M. Tech
More informationSolution Representation for Job Shop Scheduling Problems in Ant Colony Optimisation
Solution Representation for Job Shop Scheuling Problems in Ant Colony Optimisation James Montgomery, Carole Faya 2, an Sana Petrovic 2 Faculty of Information & Communication Technologies, Swinburne University
More informationA shortest path algorithm in multimodal networks: a case study with time varying costs
A shortest path algorithm in multimoal networks: a case stuy with time varying costs Daniela Ambrosino*, Anna Sciomachen* * Department of Economics an Quantitative Methos (DIEM), University of Genoa Via
More informationCalculation on diffraction aperture of cube corner retroreflector
November 10, 008 / Vol., No. 11 / CHINESE OPTICS LETTERS 8 Calculation on iffraction aperture of cube corner retroreflector Song Li (Ó Ø, Bei Tang (», an Hui Zhou ( ï School of Electronic Information,
More informationSuper-resolution Frame Reconstruction Using Subpixel Motion Estimation
Super-resolution Frame Reconstruction Using Subpixel Motion Estimation ABSTRACT When vieo ata is use for forensic analysis, it may transpire that the level of etail available is insufficient. This is particularly
More informationA Classification of 3R Orthogonal Manipulators by the Topology of their Workspace
A Classification of R Orthogonal Manipulators by the Topology of their Workspace Maher aili, Philippe Wenger an Damien Chablat Institut e Recherche en Communications et Cybernétique e Nantes, UMR C.N.R.S.
More informationData Mining: Concepts and Techniques. Chapter 7. Cluster Analysis. Examples of Clustering Applications. What is Cluster Analysis?
Data Mining: Concepts an Techniques Chapter Jiawei Han Department of Computer Science University of Illinois at Urbana-Champaign www.cs.uiuc.eu/~hanj Jiawei Han an Micheline Kamber, All rights reserve
More informationMulti-camera tracking algorithm study based on information fusion
International Conference on Avance Electronic Science an Technolog (AEST 016) Multi-camera tracking algorithm stu base on information fusion a Guoqiang Wang, Shangfu Li an Xue Wen School of Electronic
More information1/5/2014. Bedrich Benes Purdue University Dec 6 th 2013 Prague. Modeling is an open problem in CG
Berich Benes Purue University Dec 6 th 213 Prague Inverse Proceural Moeling (IPM) Motivation IPM Classification Case stuies IPM of volumetric builings IPM of stochastic trees Urban reparameterization IPM
More informationDivide-and-Conquer Algorithms
Supplment to A Practical Guie to Data Structures an Algorithms Using Java Divie-an-Conquer Algorithms Sally A Golman an Kenneth J Golman Hanout Divie-an-conquer algorithms use the following three phases:
More informationTransient analysis of wave propagation in 3D soil by using the scaled boundary finite element method
Southern Cross University epublications@scu 23r Australasian Conference on the Mechanics of Structures an Materials 214 Transient analysis of wave propagation in 3D soil by using the scale bounary finite
More informationIntensive Hypercube Communication: Prearranged Communication in Link-Bound Machines 1 2
This paper appears in J. of Parallel an Distribute Computing 10 (1990), pp. 167 181. Intensive Hypercube Communication: Prearrange Communication in Link-Boun Machines 1 2 Quentin F. Stout an Bruce Wagar
More informationData Mining: Clustering
Bi-Clustering COMP 790-90 Seminar Spring 011 Data Mining: Clustering k t 1 K-means clustering minimizes Where ist ( x, c i t i c t ) ist ( x m j 1 ( x ij i, c c t ) tj ) Clustering by Pattern Similarity
More informationCoordinating Distributed Algorithms for Feature Extraction Offloading in Multi-Camera Visual Sensor Networks
Coorinating Distribute Algorithms for Feature Extraction Offloaing in Multi-Camera Visual Sensor Networks Emil Eriksson, György Dán, Viktoria Foor School of Electrical Engineering, KTH Royal Institute
More informationWLAN Indoor Positioning Based on Euclidean Distances and Fuzzy Logic
WLAN Inoor Positioning Base on Eucliean Distances an Fuzzy Logic Anreas TEUBER, Bern EISSFELLER Institute of Geoesy an Navigation, University FAF, Munich, Germany, e-mail: (anreas.teuber, bern.eissfeller)@unibw.e
More informationCAMERAS AND GRAVITY: ESTIMATING PLANAR OBJECT ORIENTATION. Zhaoyin Jia, Andrew Gallagher, Tsuhan Chen
CAMERAS AND GRAVITY: ESTIMATING PLANAR OBJECT ORIENTATION Zhaoyin Jia, Anrew Gallagher, Tsuhan Chen School of Electrical an Computer Engineering, Cornell University ABSTRACT Photography on a mobile camera
More informationADAPTIVE WINDOWING FOR OPTIMAL VISUALIZATION OF MEDICAL IMAGES BASED ON NORMALIZED INFORMATION DISTANCE
ADAPTIVE WINDOWING FOR OPTIMAL VISUALIZATION OF MEDICAL IMAGES BASED ON NORMALIZED INFORMATION DISTANCE Nima Nikvand, Hojatollah Yeganeh and Zhou Wang Dept. of Electrical & Computer Engineering, University
More informationCompression of RADARSAT Data with Block Adaptive Wavelets Abstract: 1. Introduction
Compression of RADARSAT Data with Block Adaptive Wavelets Ian Cumming and Jing Wang Department of Electrical and Computer Engineering The University of British Columbia 2356 Main Mall, Vancouver, BC, Canada
More informationOpen Access Adaptive Image Enhancement Algorithm with Complex Background
Sen Orers for Reprints to reprints@benthamscience.ae 594 The Open Cybernetics & Systemics Journal, 205, 9, 594-600 Open Access Aaptive Image Enhancement Algorithm with Complex Bacgroun Zhang Pai * epartment
More informationLab work #8. Congestion control
TEORÍA DE REDES DE TELECOMUNICACIONES Grao en Ingeniería Telemática Grao en Ingeniería en Sistemas e Telecomunicación Curso 2015-2016 Lab work #8. Congestion control (1 session) Author: Pablo Pavón Mariño
More informationPHOTOGRAMMETRIC MEASUREMENT OF LINEAR OBJECTS WITH CCD CAMERAS SUPER-ELASTIC WIRES IN ORTHODONTICS AS AN EXAMPLE
PHOTOGRAMMETRIC MEASUREMENT OF LINEAR OBJECTS WITH CCD CAMERAS SUPER-ELASTIC WIRES IN ORTHODONTICS AS AN EAMPLE Tim SUTHAU, Matthias HEMMLEB, Dietmar URAN, Paul-Georg JOST-BRINKMANN Technical Universit
More informationGeneralized Edge Coloring for Channel Assignment in Wireless Networks
TR-IIS-05-021 Generalize Ege Coloring for Channel Assignment in Wireless Networks Chun-Chen Hsu, Pangfeng Liu, Da-Wei Wang, Jan-Jan Wu December 2005 Technical Report No. TR-IIS-05-021 http://www.iis.sinica.eu.tw/lib/techreport/tr2005/tr05.html
More informationRandom Clustering for Multiple Sampling Units to Speed Up Run-time Sample Generation
DEIM Forum 2018 I4-4 Abstract Ranom Clustering for Multiple Sampling Units to Spee Up Run-time Sample Generation uzuru OKAJIMA an Koichi MARUAMA NEC Solution Innovators, Lt. 1-18-7 Shinkiba, Koto-ku, Tokyo,
More informationClustering Expression Data. Clustering Expression Data
www.cs.washington.eu/ Subscribe if you Din t get msg last night Clustering Exression Data Why cluster gene exression ata? Tissue classification Fin biologically relate genes First ste in inferring regulatory
More information