Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning
|
|
- Maximilian Snow
- 5 years ago
- Views:
Transcription
1 Improvig Face Recogitio Rate by Combiig Eigeface Approach ad Case-based Reasoig Haris Supic, ember, IAENG Abstract There are may approaches to the face recogitio. This paper presets a approach that combies advatage of geeralizatio ability of Pricipal Compoet Aalysis (PCA) ad specializatio ability of Case- based reasoig (CBR). CBR is expected to improve the geeralizatio ability of PCA i the recogitio process. By usig PCA the ew image is projected ito its eigeface compoets. The projected vector represets a descriptio compoet of a ew face case. The CBR module compares the similarity of the ew face case ad previously stored face cases i the face casebase ad retrieves the most similar case. The solutio compoet of the retrieved case represets the results of the recogitio process. Idex Terms case based reasoig, face recogitio, eigevalues, eigevectors, pricipal compoet aalysis. I. INTRODUCTION As oe of the most successful applicatios of image aalysis ad uderstadig, face recogitio has recetly received sigificat attetio. The problem of face recogitio ca be formulated as follows [1] : For a give image of scee, idetify or verify oe or more persos i the scee usig a stored database of faces. The iput to the face recogitio system is a ukow face, ad the system determies idetity from a database of kow idividuals. I verificatio problems, the face recogitio system eeds to cofirm or reject the claimed idetity of the iput face. I geeral, the huma face recogitio system utilizes a broad spectrum of stimuli obtaied from may of the seses: visual, auditory, olfactory, etc. I recogitio process cotextual kowledge is also used [2]. However, the huma brai has its limitatios i the total umber of persos that it ca remember. A mai advetage of a computer face recogitio system is its capacity to hadle large image databases. Some psychological studies have poited out that the iteral facial features, such as eyes, ose, ad mouth, are very importat for huma beigs to recogize familiar faces. A complete face recogitio system should iclud two stages. The first stage is detectig the locatio ad size of a face. This task is difficult because of the ukow positio ad orietatio of faces i image. The secod stage ivolves recogizig the faces obtaied i the first stage. It is very auscript received arch 21, This work was supported i part by the Cato Sarajevo, iistry of educatio ad sciece uder Grat , ad Grat /07. Haris Supic is with the Departmet of Computer Sciece, Faculty of Electrical Egieerig, Uiversity of Sarajevo, Bosia ad Herzegovia, Zmaja od Bose bb, phoe: +(387) ; fax: +(387) ; haris.supic@ etf.usa.ba. importat to emphasize that there are may problems that has to be solved for complete success of face recogitio systems. The followig two problems are the most importat: the ilumiatio problem ad the pose problem [3]. The illumiatio problem ca be described as the problem where same face appears differetly due to the chage i lightig. The chages produced by illumiatio could be larger tha the differeces betwee idividuals. The pose problem ca be described as a problem where the same face appears differetly due to chages i viewig coditio. Face recogitio approaches ca be broadly grouped ito geometric ad template matchig techiques. I the first case, geometric characteristics of faces to be matched, such as distaces betwee differet facial features, are compared. I the secod case, face images represeted as a two-dimesioal array of pixel itesity values are compared to a sigle or several templates represetig the whole face. ore successful template matchig approaches are: Pricipal Compoet Aalysis (PCA) ad Liear Discrimiat Aalysis (LDA). Template matchig approaches to face recogitio use the cocept of image space. A two-dimesioal image I(x,y) may be viewed as a poit i a very high dimesioal space, called image space, where each coordiate of the space correspods to a sample of the image. For example, a image with 32 rows ad 32 colums describes a poit i a 1024-dimesioal image space. I geeral, a image of N rows ad N colums describes a poit i N 2 -dimesioal image space. All the faces look like each other. They all have two eyes, a mouth, a ose, etc. Therefore, all the face vectors are located i a very arrow cluster i the image space [4]. II. THE EIGENFACE APPROACH Differet eigespace-based approaches have bee proposed for the face recogitio. They differ mostly i the kid of projectio method bee used ad i the similarity matchig criterio employed. Pricipal Compoet Aalysis (PCA) is a geeral method to idetify the liear directios i which a set of vectors are best represeted ad after that to make a dimesioal reductio of them. Turk ad Petlad used the PCA for dimesioality reductio to fid the vectors which best accout for the distributio of face images withi the etire image space [5], [6]. Let S deote the traiig set of face images [6]: S = {Γ 1, Γ 2, Γ 3,, Γ }. (1) The mea image of the set if defied by: Ψ = 1 (2) Γ = 1
2 NEW PROBLE RETRIEVE RETAIN PRIOR CASES REUSE SOLUTION CASEBASE REVISE Fig. 1. The CBR cycle. Adapted from [9] The set of deviatio-from-mea vectors, {Φ 1, Φ 2, Φ 3,..., Φ } cotais the idividual differece of each traiig image from the mea vector Ψ. Idividual differeces are defied as: Φ i = Γi Ψ, i=1,2, (3) To obtai the eigeface descriptio of the traiig set, the traiig images are subjected to PCA, which seeks a set of orthoormal vectors u ad their associated eigevalues λ k which best describes the distributio of the data. The vectors u k ad scalars λ k are the eigevectors ad eigevalues, respectively, of the covariace matrix. The covariace matrix is give by [6]: 1 T Φ T AA (4) =1 C = Φ = where the matrix A is A=[Φ 1 Φ 2.Φ ] The matrix C is a N 2 by N 2 matrix ad would geerate N 2 eigevectors ad eigevalues. With image sizes like 256 by 256, or eve lower tha that, such a calculatio would be = projected descriptio of ew face to be recogized (ew case) = projected descriptio of previously recogized faces (stored solved cases) = stored solutios (idetities) Problem space (face space) u 2 Ω 5 Ω 1 Ω 3 Ω 4 Ω 6 Ω 2 Ω m Solutio space (idetity space) u 1... Id 1 Id 2 Id 3 Id CB f ={(Ω 1, Id 1 ), (Ω 3,Id 1 ), (Ω 2,Id 2 ), (Ω 4,Id 2 ), (Ω 5,Id 3 ), (Ω 6,Id 3 ),...,(Ω m,id )} Fig. 2. Simplified represetatio of problem descriptio (face space) ad solutio (idetity) space
3 impractical to implemet. A computatioally feasible method was suggested to fid out the eigevectors [5]. If the umber of images i the traiig set is less tha the umber of pixels i a image (i.e < N 2), there will be oly -1, rather tha N 2, meaigful eigevectors. The remaiig eigevectors will have associated eigevalues of zero. Thus, we ca solve a by matrix istead of solvig a N 2 by N 2 matrix [5], [6]. A. Stadard Recogitio Procedure The sigificat eigevectors of the matrix L=A T A are chose as those with the largest associated eigevalues. The eigefaces spa a -dimesioal subspace of the origial N 2 image space. A ew face image Γ is trasformed ito its eigeface compoets (projected ito face space ) by a simple operatio, w k = u k T (Г - ψ), k=1,2,.. (5) The weights obtaied as above form a vector [6]: Ω T = [w 1, w 2, w 3,. w ] (6) that describes the cotributio of each eigeface i represetig the iput face image. The stadard method for determiig which face class provides the best descriptio of a iput face image is to fid the face class k that miimizes the Euclidia distace ε k 2 = Ω Ω k 2 (7) where Ω k is a vector describig the k th face class. The ew face is cosidered to belog to a class if ε k is bellow a established threshold θ ε. The the face image is cosidered to be a kow face. If the differece is above the give threshold, but bellow a secod threshold, the image ca be determied as a ukow face. If the iput image is above these two thresholds, the image is determied ot to be a face. III. THE EIGENFACE-CBR APPROACH I this sectio we will describe the eigeface-cbr approach to face recogitio. The mai purpose of eigeface-cbr approach is to take advatage of geeralizatio ability of PCA ad specializatio ability of CBR. CBR is expected to improve the geeralizatio ability i the recogitio process. CBR ability of a give approach should be maifested i the experimets as the ability to improve a recogitio rate whe icreasig the umber of retaied previously face recogitio cases. I order to evaluate this approach, we compared the approach with the stadard eigeface approach. A. Case-based reasoig Case-based reasoig (CBR) is able to utilize the specific kowledge of previously experieced, cocrete problem situatios (cases). A ew problem is solved by fidig a similar past case, ad reusig it i the ew problem situatio [7]. There are two mai ways to reuse past cases: reuse the past case solutio ad reuse the past method that costructed the solutio [8]. I CBR termiology, a case usually deotes a problem situatio. A previously experieced situatio, which has bee captured ad leared i a way that it ca be reused i the solvig of future problems, is referred to as a previous case, stored case, or retaied case. Correspodigly, a ew case or usolved case is the descriptio of a ew problem to be solved. Fig. 1 shows the model of the problem solvig cycle i CBR. Solvig a problem by CBR ivolves obtaiig a problem descriptio, measurig the similarity of the curret problem to previous problems stored i a case base with their kow solutios, retrievig oe or more similar cases, ad attemptig to reuse the solutio of oe of the retrieved cases, possibly after adaptig it to accout for differeces i problem descriptios [9]. The solutio proposed by the system is the evaluated (e.g.., by beig applied to the iitial problem or assessed by a domai expert). Followig revisio of the proposed solutio if required i light of its evaluatio, the problem descriptio ad its solutio ca the be retaied as a ew case, ad the system has leared to solve a ew problem [9]. CBR is fouded o the premise that similar problems have similar solutios. Thus, oe of the primary goals of a CBR system is to fid the most similar, or most relevat, cases for ew iput problems. The effectiveess of CBR depeds o the quality ad quatity of cases i a casebase. I some domais, eve a small umber of cases provide good solutios, but i other domais, a icreased umber of uique cases improve problem-solvig capabilities of CBR systems because there are more experieces to draw o. Case-based reasoig systems ca also be viewed as cotiuous kowledge acquisitio ad learig systems. B. Case Represetatio for Eigeface-CBR Approach I this sectio, we describe case represetatio used for the eigeface-cbr approach. Case represetatio is geerally regarded as oe of the most importat problems ad is crucial to success of case-based reasoig system. The case represetatio problem is primarily the problem of decidig what to store i a case, ad fidig a appropriate structure for describig case cotets. I geeral, a case cosists of a problem descriptio compoet ad a solutio compoet. I this work, face cases C f are represeted as two-tuples (see Fig. 2): C f =(Ω T, Id) where: Ω T is a face case descriptio compoet that represets projected image vector Γ, Id is a face case solutio compoet that represets idetity. C. CBR Recogitio Procedure Let CB f deotes the face casebase: where CB f = {C 1, C 2,...,C CB }, C i =(Ω i T,Id j ), i=1,2,... CB, j=1,2,... ID ad where ID is the set of all previously recogized persos. Fig. 3 shows the block diagram of the eigeface-cbr recogitio system. It is used PCA ad the ew image Γ is
4 Γ Ω T PCA CBR module NEW FACE C ew =(Ω T,?) same 90 images, obtaied i good illumiatio coditios. All preseted results were obtaied with oe processig for each amout of eigevectors (5, 15, ad 30). Table I presets the results obtaied with the stadard eigefaces recogitio procedure. Table II presets the results obtaied with the eigeface-cbr recogitio procedure, workig with the same 90 well illumiated images ad with the three differet casebase sizes: 60, 120, ad 180. We ca see that the experimetal results obtaied usig the eigeface-cbr approach icreases its recogitio rate. The recogitio rates icreases with icreasig umber of previously experieced face recogitio cases. Id r Result of the idetificatio Fig. 3. Block diagram of the eigeface-cbr approach Eigevectors Table I. Stadard eigeface results Errors Success Quatity Rate Quatity Rate trasformed ito its eigeface compoets. The resultig weights form the weight vector Ω T = [w 1, w 2, w 3,. w ]. Task of the CBR module is create the ew face recogitio case, fid a prior case similar to the ew oe, use that case to suggest a solutio to the curret face recogitio problem, ad update the system by learig from this experiece. The projected vector Ω T represets the descriptio compoet of the ew face case C =(Ω T,?). The symbol? deotes that the solutio compoet (idetity) is ukow. The CBR module compares the similarity of the descriptio compoet Ω T of the ew face case ad previously stored descriptio compoets Ω i, i=1,2,... CB, of face cases i the casebase CB f. The Euclidea distace betwee two descriptio compoets d(ω T,Ω i ), i=1,2,... CB, provides a measure of similarity betwee the ew case C ad previously stored cases C i,i=1,2,... CB. By usig the criterio of similarity based o Euclidia distace, CBR module determies ad retrieves the most similar case C r =(Ω r T, Id r ) i the case base. The solutio compoet Id r of the retrieved case C r represets the results of the recogitio process. The iput face is cosidered to belog to a idetity if distace d(ω T, Ω r T ) is bellow a established threshold θ r. If the distace d(ω T, Ω r T ) is above the give threshold, but bellow a secod threshold θ f, the image ca be cosidered as a ukow face. If the distace d(ω T, Ω r T ) is above these two thresholds, the ew face case is determied ot to be a face. A very importat characteristic of the eigeface-cbr approach is icremetal learig, sice a ew experiece is retaied each time a ew face has bee recogized, makig it immediately available for future face recogitio problems. IV. RECOGNITION EXPERIENTS This sectio is focused o the compariso of stadard eigespace based face recogitio usig the PCA projectio method ad the eigeface-cbr approach previously preseted i this paper. I order to compare the stadard eigeface recogitio procedure ad the eigeface-cbr recogitio procedure, we applied both procedures to the ,1% 71 78,9% ,7% 84 93,3% ,3% 87 96,7% Num. of stored cases Eige vect. Table II. Eigeface-CBR results Errors Success Quat. Rate Quat. Rate ,8% 74 82,2% ,7% 84 93,3% ,2% 88 97,8% % 77 85,6% ,4% 86 95,6% ,2% 88 97,8% 5 8 8,9% 82 91,1% ,3% 87 96,7% ,1% 89 98,9%
5 V. CONCLUSIONS AND FUTURE WORK I this paper we have preseted a approach that combies eigeface approach ad case-based reasoig. The case based approach to face recogitio was motivated by the desire to combie the advatage of geeralizatio ability of Pricipal Compoet Aalysis (PCA) ad the advatage of specializatio ability of case-based reasoig (CBR). The prelimiary experimetal results show that usig the eigeface-cbr approach icreases the recogitio rate. The recogitio rate icreases with icreasig umber of previously experieced face recogitio cases. As future work we are focusig o the extesio of the research, cosiderig other kid of eigespace-based approaches. Also, we are iterested i developmet of algorithms for more efficiet case retrieval from the casebase. ACKNOWLEDGENT The author is grateful for the support by the iistry of educatio ad sciece, Cato Sarajevo, B&H. REFERENCES [1] W. Zhao, R. Chellappa, A. Rosefeld, ad P.J. Phillips, Face recogitio: a literature survey, AC Computig Surveys, 2003, pp [2] A.. Burto, V. Bruce, ad P.J.B. Hacock, From pixels to people: a model of familiar face recogitio, Cogitive Sciece, Vol. 23, No. 1, 1999, pp [3] R. Gross, J. Shi, J. Coh, Quo vadis face recogitio? - The curret state of the art i face recogitio, Techical Report, Robotics Istitute, Caregie ello Uiversity, Pittsburgh, PA, [4] A. Schwaiger, S. Ryf, ad F. Hofer, Cofigural iformatio is processed differetly i perceptio ad recogitio of faces, Visio Research, Vol. 43, 2003, pp [5]. Turk, ad A. Petlad A, Eigefaces for recogitio, Joural of Cogitive Neurosciece, Volume 3, Number 1, arch [6]. Turk, ad A. Petlad, Face recogitio usig eigefaces, i Proc. IEEE Iteratioal Coferece o Computer Visio ad Patter Recogitio, aui, Hawaii, [7] A. Aamodt, ad E. Plaza, Case-based reasoig: Foudatioal issues, methodological variatios ad system approaches, I AICO (1994), vol 7(1), pp [8] J.L. Koloder, Case based reasoig, orga Kaufma Publishers, Ic., Sa ateo, CA, [9] L. ataras, et al. Retrieval, reuse, revisio, ad retetio i CBR. Kowledge Egieerig Review, 20(3), 2005, pp
Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1
Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces
More informationEigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1
Eigeimages Uitary trasforms Karhue-Loève trasform ad eigeimages Sirovich ad Kirby method Eigefaces for geder recogitio Fisher liear discrimat aalysis Fisherimages ad varyig illumiatio Fisherfaces vs. eigefaces
More informationNew HSL Distance Based Colour Clustering Algorithm
The 4th Midwest Artificial Itelligece ad Cogitive Scieces Coferece (MAICS 03 pp 85-9 New Albay Idiaa USA April 3-4 03 New HSL Distace Based Colour Clusterig Algorithm Vasile Patrascu Departemet of Iformatics
More informationPattern Recognition Systems Lab 1 Least Mean Squares
Patter Recogitio Systems Lab 1 Least Mea Squares 1. Objectives This laboratory work itroduces the OpeCV-based framework used throughout the course. I this assigmet a lie is fitted to a set of poits usig
More informationDimensionality Reduction PCA
Dimesioality Reductio PCA Machie Learig CSE446 David Wadde (slides provided by Carlos Guestri) Uiversity of Washigto Feb 22, 2017 Carlos Guestri 2005-2017 1 Dimesioality reductio Iput data may have thousads
More informationImage based Cats and Possums Identification for Intelligent Trapping Systems
Volume 159 No, February 017 Image based Cats ad Possums Idetificatio for Itelliget Trappig Systems T. A. S. Achala Perera School of Egieerig Aucklad Uiversity of Techology New Zealad Joh Collis School
More informationA New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method
A ew Morphological 3D Shape Decompositio: Grayscale Iterframe Iterpolatio Method D.. Vizireau Politehica Uiversity Bucharest, Romaia ae@comm.pub.ro R. M. Udrea Politehica Uiversity Bucharest, Romaia mihea@comm.pub.ro
More informationImage Segmentation EEE 508
Image Segmetatio Objective: to determie (etract) object boudaries. It is a process of partitioig a image ito distict regios by groupig together eighborig piels based o some predefied similarity criterio.
More informationOnes Assignment Method for Solving Traveling Salesman Problem
Joural of mathematics ad computer sciece 0 (0), 58-65 Oes Assigmet Method for Solvig Travelig Salesma Problem Hadi Basirzadeh Departmet of Mathematics, Shahid Chamra Uiversity, Ahvaz, Ira Article history:
More informationNeuro Fuzzy Model for Human Face Expression Recognition
IOSR Joural of Computer Egieerig (IOSRJCE) ISSN : 2278-0661 Volume 1, Issue 2 (May-Jue 2012), PP 01-06 Neuro Fuzzy Model for Huma Face Expressio Recogitio Mr. Mayur S. Burage 1, Prof. S. V. Dhopte 2 1
More informationReal-Time Secure System for Detection and Recognition the Face of Criminals
Available Olie at www.ijcsmc.com Iteratioal Joural of Computer Sciece ad Mobile Computig A Mothly Joural of Computer Sciece ad Iformatio Techology IJCSMC, Vol. 4, Issue. 9, September 2015, pg.58 83 RESEARCH
More informationEvaluation scheme for Tracking in AMI
A M I C o m m u i c a t i o A U G M E N T E D M U L T I - P A R T Y I N T E R A C T I O N http://www.amiproject.org/ Evaluatio scheme for Trackig i AMI S. Schreiber a D. Gatica-Perez b AMI WP4 Trackig:
More informationA SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON
A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON Roberto Lopez ad Eugeio Oñate Iteratioal Ceter for Numerical Methods i Egieerig (CIMNE) Edificio C1, Gra Capitá s/, 08034 Barceloa, Spai ABSTRACT I this work
More informationImproving Template Based Spike Detection
Improvig Template Based Spike Detectio Kirk Smith, Member - IEEE Portlad State Uiversity petra@ee.pdx.edu Abstract Template matchig algorithms like SSE, Covolutio ad Maximum Likelihood are well kow for
More informationAccuracy Improvement in Camera Calibration
Accuracy Improvemet i Camera Calibratio FaJie L Qi Zag ad Reihard Klette CITR, Computer Sciece Departmet The Uiversity of Aucklad Tamaki Campus, Aucklad, New Zealad fli006, qza001@ec.aucklad.ac.z r.klette@aucklad.ac.z
More informationPrincipal Components Analysis Based Iris Recognition and Identification System
Iteratioal Joural of Soft Computig ad Egieerig (IJSCE) ISSN: 223-2307, Volume-3, Issue-2, May 203 Pricipal Compoets Aalysis Based Iris Recogitio ad Idetificatio System E. Mattar Abstract his article focuses
More informationA Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System
A Novel Feature Extractio Algorithm for Haar Local Biary Patter Texture Based o Huma Visio System Liu Tao 1,* 1 Departmet of Electroic Egieerig Shaaxi Eergy Istitute Xiayag, Shaaxi, Chia Abstract The locality
More informationLDA-based Non-negative Matrix Factorization for Supervised Face Recognition
1294 JOURNAL OF SOFTWARE, VOL. 9, NO. 5, MAY 2014 LDA-based No-egative Matrix Factorizatio for Supervised Face Recogitio Yu Xue a, Chog Sze Tog b, Jig Yu Yua c a School of Physics ad Telecommuicatio Egieerig,
More informationMATHEMATICAL METHODS OF ANALYSIS AND EXPERIMENTAL DATA PROCESSING (Or Methods of Curve Fitting)
MATHEMATICAL METHODS OF ANALYSIS AND EXPERIMENTAL DATA PROCESSING (Or Methods of Curve Fittig) I this chapter, we will eamie some methods of aalysis ad data processig; data obtaied as a result of a give
More informationSoft Computing Based Range Facial Recognition Using Eigenface
Soft Computig Based Rage Facial Recogitio Usig Eigeface Yeug-Hak Lee, Chag-Wook Ha, ad Tae-Su Kim School of Electrical Egieerig ad Computer Sciece, Yeugam Uiversity, 4- Dae-dog, Gyogsa, Gyogbuk, 7-749
More informationCarnegie Mellon University
Caregie Mello Uiversity CARNEGIE INSTITUTE OF TECHNOLOGY THESIS SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF Doctor of Philosophy TITLE Pose Robust Video-Based Face Recogitio
More informationStone Images Retrieval Based on Color Histogram
Stoe Images Retrieval Based o Color Histogram Qiag Zhao, Jie Yag, Jigyi Yag, Hogxig Liu School of Iformatio Egieerig, Wuha Uiversity of Techology Wuha, Chia Abstract Stoe images color features are chose
More informationOctahedral Graph Scaling
Octahedral Graph Scalig Peter Russell Jauary 1, 2015 Abstract There is presetly o strog iterpretatio for the otio of -vertex graph scalig. This paper presets a ew defiitio for the term i the cotext of
More informationAn Improved Shuffled Frog-Leaping Algorithm for Knapsack Problem
A Improved Shuffled Frog-Leapig Algorithm for Kapsack Problem Zhoufag Li, Ya Zhou, ad Peg Cheg School of Iformatio Sciece ad Egieerig Hea Uiversity of Techology ZhegZhou, Chia lzhf1978@126.com Abstract.
More informationVALIDATING DIRECTIONAL EDGE-BASED IMAGE FEATURE REPRESENTATIONS IN FACE RECOGNITION BY SPATIAL CORRELATION-BASED CLUSTERING
VALIDATING DIRECTIONAL EDGE-BASED IMAGE FEATURE REPRESENTATIONS IN FACE RECOGNITION BY SPATIAL CORRELATION-BASED CLUSTERING Yasufumi Suzuki ad Tadashi Shibata Departmet of Frotier Iformatics, School of
More information3D Model Retrieval Method Based on Sample Prediction
20 Iteratioal Coferece o Computer Commuicatio ad Maagemet Proc.of CSIT vol.5 (20) (20) IACSIT Press, Sigapore 3D Model Retrieval Method Based o Sample Predictio Qigche Zhag, Ya Tag* School of Computer
More informationFast Fourier Transform (FFT) Algorithms
Fast Fourier Trasform FFT Algorithms Relatio to the z-trasform elsewhere, ozero, z x z X x [ ] 2 ~ elsewhere,, ~ e j x X x x π j e z z X X π 2 ~ The DFS X represets evely spaced samples of the z- trasform
More informationJournal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article
Available olie www.jocpr.com Joural of Chemical ad Pharmaceutical Research, 2013, 5(12):745-749 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 K-meas algorithm i the optimal iitial cetroids based
More informationHarris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c
Iteratioal Coferece o Computatioal Sciece ad Egieerig (ICCSE 015) Harris Corer Detectio Algorithm at Sub-pixel Level ad Its Applicatio Yuafeg Ha a, Peijiag Che b * ad Tia Meg c School of Automobile, Liyi
More informationChapter 3: Introduction to Principal components analysis with MATLAB
Chapter 3: Itroductio to Pricipal compoets aalysis with MATLAB The vriety of mathematical tools are avilable ad successfully workig to i the field of image processig. The mai problem with graphical autheticatio
More informationElementary Educational Computer
Chapter 5 Elemetary Educatioal Computer. Geeral structure of the Elemetary Educatioal Computer (EEC) The EEC coforms to the 5 uits structure defied by vo Neuma's model (.) All uits are preseted i a simplified
More informationUNIT 4 Section 8 Estimating Population Parameters using Confidence Intervals
UNIT 4 Sectio 8 Estimatig Populatio Parameters usig Cofidece Itervals To make ifereces about a populatio that caot be surveyed etirely, sample statistics ca be take from a SRS of the populatio ad used
More informationFundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le
Fudametals of Media Processig Shi'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dih Le Today's topics Noparametric Methods Parze Widow k-nearest Neighbor Estimatio Clusterig Techiques k-meas Agglomerative Hierarchical
More informationAnalysis of Documents Clustering Using Sampled Agglomerative Technique
Aalysis of Documets Clusterig Usig Sampled Agglomerative Techique Omar H. Karam, Ahmed M. Hamad, ad Sheri M. Moussa Abstract I this paper a clusterig algorithm for documets is proposed that adapts a samplig-based
More informationOn-line cursive letter recognition using sequences of local minima/maxima. Robert Powalka
O-lie cursive letter recogitio usig sequeces of local miima/maxima Summary Robert Powalka 19 th August 1993 This report presets the desig ad implemetatio of a o-lie cursive letter recogizer usig sequeces
More informationThe Closest Line to a Data Set in the Plane. David Gurney Southeastern Louisiana University Hammond, Louisiana
The Closest Lie to a Data Set i the Plae David Gurey Southeaster Louisiaa Uiversity Hammod, Louisiaa ABSTRACT This paper looks at three differet measures of distace betwee a lie ad a data set i the plae:
More informationPerformance Comparisons of PSO based Clustering
Performace Comparisos of PSO based Clusterig Suresh Chadra Satapathy, 2 Guaidhi Pradha, 3 Sabyasachi Pattai, 4 JVR Murthy, 5 PVGD Prasad Reddy Ail Neeruoda Istitute of Techology ad Scieces, Sagivalas,Vishaapatam
More informationEE123 Digital Signal Processing
Last Time EE Digital Sigal Processig Lecture 7 Block Covolutio, Overlap ad Add, FFT Discrete Fourier Trasform Properties of the Liear covolutio through circular Today Liear covolutio with Overlap ad add
More informationAnalysis of Server Resource Consumption of Meteorological Satellite Application System Based on Contour Curve
Advaces i Computer, Sigals ad Systems (2018) 2: 19-25 Clausius Scietific Press, Caada Aalysis of Server Resource Cosumptio of Meteorological Satellite Applicatio System Based o Cotour Curve Xiagag Zhao
More informationAssignment Problems with fuzzy costs using Ones Assignment Method
IOSR Joural of Mathematics (IOSR-JM) e-issn: 8-8, p-issn: 9-6. Volume, Issue Ver. V (Sep. - Oct.06), PP 8-89 www.iosrjourals.org Assigmet Problems with fuzzy costs usig Oes Assigmet Method S.Vimala, S.Krisha
More information9.1. Sequences and Series. Sequences. What you should learn. Why you should learn it. Definition of Sequence
_9.qxd // : AM Page Chapter 9 Sequeces, Series, ad Probability 9. Sequeces ad Series What you should lear Use sequece otatio to write the terms of sequeces. Use factorial otatio. Use summatio otatio to
More informationWhat are we going to learn? CSC Data Structures Analysis of Algorithms. Overview. Algorithm, and Inputs
What are we goig to lear? CSC316-003 Data Structures Aalysis of Algorithms Computer Sciece North Carolia State Uiversity Need to say that some algorithms are better tha others Criteria for evaluatio Structure
More informationAn Efficient Algorithm for Graph Bisection of Triangularizations
A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045 Oe Brookigs Drive St. Louis, Missouri 63130-4899, USA jaegerg@cse.wustl.edu
More informationDimension Reduction and Manifold Learning. Xin Zhang
Dimesio Reductio ad Maifold Learig Xi Zhag eeizhag@scut.edu.c Cotet Motivatio of maifold learig Pricipal compoet aalysis ad its etesio Maifold learig Global oliear maifold learig (IsoMap) Local oliear
More informationIMP: Superposer Integrated Morphometrics Package Superposition Tool
IMP: Superposer Itegrated Morphometrics Package Superpositio Tool Programmig by: David Lieber ( 03) Caisius College 200 Mai St. Buffalo, NY 4208 Cocept by: H. David Sheets, Dept. of Physics, Caisius College
More informationCriterion in selecting the clustering algorithm in Radial Basis Functional Link Nets
WSEAS TRANSACTIONS o SYSTEMS Ag Sau Loog, Og Hog Choo, Low Heg Chi Criterio i selectig the clusterig algorithm i Radial Basis Fuctioal Lik Nets ANG SAU LOONG 1, ONG HONG CHOON 2 & LOW HENG CHIN 3 Departmet
More informationLoad balanced Parallel Prime Number Generator with Sieve of Eratosthenes on Cluster Computers *
Load balaced Parallel Prime umber Geerator with Sieve of Eratosthees o luster omputers * Soowook Hwag*, Kyusik hug**, ad Dogseug Kim* *Departmet of Electrical Egieerig Korea Uiversity Seoul, -, Rep. of
More informationBayesian approach to reliability modelling for a probability of failure on demand parameter
Bayesia approach to reliability modellig for a probability of failure o demad parameter BÖRCSÖK J., SCHAEFER S. Departmet of Computer Architecture ad System Programmig Uiversity Kassel, Wilhelmshöher Allee
More informationRedundancy Allocation for Series Parallel Systems with Multiple Constraints and Sensitivity Analysis
IOSR Joural of Egieerig Redudacy Allocatio for Series Parallel Systems with Multiple Costraits ad Sesitivity Aalysis S. V. Suresh Babu, D.Maheswar 2, G. Ragaath 3 Y.Viaya Kumar d G.Sakaraiah e (Mechaical
More informationDynamic Programming and Curve Fitting Based Road Boundary Detection
Dyamic Programmig ad Curve Fittig Based Road Boudary Detectio SHYAM PRASAD ADHIKARI, HYONGSUK KIM, Divisio of Electroics ad Iformatio Egieerig Chobuk Natioal Uiversity 664-4 Ga Deokji-Dog Jeoju-City Jeobuk
More informationCubic Polynomial Curves with a Shape Parameter
roceedigs of the th WSEAS Iteratioal Coferece o Robotics Cotrol ad Maufacturig Techology Hagzhou Chia April -8 00 (pp5-70) Cubic olyomial Curves with a Shape arameter MO GUOLIANG ZHAO YANAN Iformatio ad
More informationPerformance Plus Software Parameter Definitions
Performace Plus+ Software Parameter Defiitios/ Performace Plus Software Parameter Defiitios Chapma Techical Note-TG-5 paramete.doc ev-0-03 Performace Plus+ Software Parameter Defiitios/2 Backgroud ad Defiitios
More informationCS 683: Advanced Design and Analysis of Algorithms
CS 683: Advaced Desig ad Aalysis of Algorithms Lecture 6, February 1, 2008 Lecturer: Joh Hopcroft Scribes: Shaomei Wu, Etha Feldma February 7, 2008 1 Threshold for k CNF Satisfiability I the previous lecture,
More informationCOMP 558 lecture 6 Sept. 27, 2010
Radiometry We have discussed how light travels i straight lies through space. We would like to be able to talk about how bright differet light rays are. Imagie a thi cylidrical tube ad cosider the amout
More informationON THE QUALITY OF AUTOMATIC RELATIVE ORIENTATION PROCEDURES
ON THE QUALITY OF AUTOMATIC RELATIVE ORIENTATION PROCEDURES Thomas Läbe, Timo Dickscheid ad Wolfgag Förster Istitute of Geodesy ad Geoiformatio, Departmet of Photogrammetry, Uiversity of Bo laebe@ipb.ui-bo.de,
More informationChapter 1. Introduction to Computers and C++ Programming. Copyright 2015 Pearson Education, Ltd.. All rights reserved.
Chapter 1 Itroductio to Computers ad C++ Programmig Copyright 2015 Pearso Educatio, Ltd.. All rights reserved. Overview 1.1 Computer Systems 1.2 Programmig ad Problem Solvig 1.3 Itroductio to C++ 1.4 Testig
More informationOutline. Research Definition. Motivation. Foundation of Reverse Engineering. Dynamic Analysis and Design Pattern Detection in Java Programs
Dyamic Aalysis ad Desig Patter Detectio i Java Programs Outlie Lei Hu Kamra Sartipi {hul4, sartipi}@mcmasterca Departmet of Computig ad Software McMaster Uiversity Caada Motivatio Research Problem Defiitio
More informationAn Efficient Algorithm for Graph Bisection of Triangularizations
Applied Mathematical Scieces, Vol. 1, 2007, o. 25, 1203-1215 A Efficiet Algorithm for Graph Bisectio of Triagularizatios Gerold Jäger Departmet of Computer Sciece Washigto Uiversity Campus Box 1045, Oe
More informationLecture Notes 6 Introduction to algorithm analysis CSS 501 Data Structures and Object-Oriented Programming
Lecture Notes 6 Itroductio to algorithm aalysis CSS 501 Data Structures ad Object-Orieted Programmig Readig for this lecture: Carrao, Chapter 10 To be covered i this lecture: Itroductio to algorithm aalysis
More informationAnnouncements. Recognition III. A Rough Recognition Spectrum. Projection, and reconstruction. Face detection using distance to face space
Aoucemets Assigmet 5: Due Friday, 4:00 III Itroductio to Computer Visio CSE 52 Lecture 20 Fial Exam: ed, 6/9/04, :30-2:30, LH 2207 (here I ll discuss briefly today, ad will be at discussio sectio tomorrow
More informationFEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING
FEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING Christoph Busch, Ralf Dörer, Christia Freytag, Heike Ziegler Frauhofer Istitute for Computer Graphics, Computer Graphics Ceter
More informationEfficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme
828 Iteratioal Joural of Cotrol, Automatio, ad Systems, vol. 6, o. 6, pp. 828-835, December 2008 Efficiet Eye Locatio for Biomedical Imagig usig Two-level Classifier Scheme Mi Youg Nam, Xi Wag, ad Phill
More information1.8 What Comes Next? What Comes Later?
35 1.8 What Comes Next? What Comes Later? A Practice Uderstadig Task For each of the followig tables, CC BY Hiroaki Maeda https://flic.kr/p/6r8odk describe how to fid the ext term i the sequece, write
More informationMath 10C Long Range Plans
Math 10C Log Rage Plas Uits: Evaluatio: Homework, projects ad assigmets 10% Uit Tests. 70% Fial Examiatio.. 20% Ay Uit Test may be rewritte for a higher mark. If the retest mark is higher, that mark will
More informationImprovement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation
Improvemet of the Orthogoal Code Covolutio Capabilities Usig FPGA Implemetatio Naima Kaabouch, Member, IEEE, Apara Dhirde, Member, IEEE, Saleh Faruque, Member, IEEE Departmet of Electrical Egieerig, Uiversity
More informationOCR Statistics 1. Working with data. Section 3: Measures of spread
Notes ad Eamples OCR Statistics 1 Workig with data Sectio 3: Measures of spread Just as there are several differet measures of cetral tedec (averages), there are a variet of statistical measures of spread.
More informationStereo matching approach based on wavelet analysis for 3D reconstruction in neurovision system 1
Stereo matchig approach based o wavelet aalysis or 3D recostructio i eurovisio system Yige Xiog Visio Iteraces & Sys. Lab. (VISLab) CSE Dept.Wright State U. OH 45435 ABSTRACT I this paper a stereo matchig
More informationSouth Slave Divisional Education Council. Math 10C
South Slave Divisioal Educatio Coucil Math 10C Curriculum Package February 2012 12 Strad: Measuremet Geeral Outcome: Develop spatial sese ad proportioal reasoig It is expected that studets will: 1. Solve
More informationCSCI 5090/7090- Machine Learning. Spring Mehdi Allahyari Georgia Southern University
CSCI 5090/7090- Machie Learig Sprig 018 Mehdi Allahyari Georgia Souther Uiversity Clusterig (slides borrowed from Tom Mitchell, Maria Floria Balca, Ali Borji, Ke Che) 1 Clusterig, Iformal Goals Goal: Automatically
More informationHand Gesture Recognition for Human-Machine Interaction
Had Gesture Recogitio for Huma-Machie Iteractio Elea Sáchez-Nielse Departmet of Statistic, O.R. ad Computer Sciece, Uiversity of La Lagua Edificio de Física y Matemáticas 38271, La Lagua, Spai eielse@ull.es
More informationLecture 1: Introduction and Strassen s Algorithm
5-750: Graduate Algorithms Jauary 7, 08 Lecture : Itroductio ad Strasse s Algorithm Lecturer: Gary Miller Scribe: Robert Parker Itroductio Machie models I this class, we will primarily use the Radom Access
More informationSectio 4, a prototype project of settig field weight with AHP method is developed ad the experimetal results are aalyzed. Fially, we coclude our work
200 2d Iteratioal Coferece o Iformatio ad Multimedia Techology (ICIMT 200) IPCSIT vol. 42 (202) (202) IACSIT Press, Sigapore DOI: 0.7763/IPCSIT.202.V42.0 Idex Weight Decisio Based o AHP for Iformatio Retrieval
More informationCopyright 2016 Ramez Elmasri and Shamkant B. Navathe
Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe CHAPTER 18 Strategies for Query Processig Copyright 2016 Ramez Elmasri ad Shamkat B. Navathe Itroductio DBMS techiques to process a query Scaer idetifies
More informationDATA MINING II - 1DL460
DATA MINING II - 1DL460 Sprig 2017 A secod course i data miig http://www.it.uu.se/edu/course/homepage/ifoutv2/vt17/ Kjell Orsbor Uppsala Database Laboratory Departmet of Iformatio Techology, Uppsala Uiversity,
More informationShape Completion and Modeling of 3D Foot Shape While Walking Using Homologous Model Fitting
Shape Completio ad Modelig of 3D Foot Shape While Walkig Usig Homologous Model Fittig Yuji YOSHIDA* a, Shuta SAITO a, Yoshimitsu AOKI a, Makiko KOUCHI b, Masaaki MOCHIMARU b a Faculty of Sciece ad Techology,
More informationEE 584 MACHINE VISION
METU EE 584 Lecture Notes by A.Aydi ALATAN 0 EE 584 MACHINE VISION Itroductio elatio with other areas Image Formatio & Sesig Projectios Brightess Leses Image Sesig METU EE 584 Lecture Notes by A.Aydi ALATAN
More informationRegularized Orthogonal Local Fisher Discriminant Analysis
Regularized Orthogoal Local Fisher Discrimiat Aalysis Shuhua Xu Departmet of Maths Uiversity of Shaoxig City South Road, Shaoxig P.R Chia webqmm974@63.com Joural of Digital Iformatio Maagemet ABSRAC: Aimig
More informationEffect of control points distribution on the orthorectification accuracy of an Ikonos II image through rational polynomial functions
Effect of cotrol poits distributio o the orthorectificatio accuracy of a Ikoos II image through ratioal polyomial fuctios Marcela do Valle Machado 1, Mauro Homem Atues 1 ad Paula Debiasi 1 1 Federal Rural
More informationANN WHICH COVERS MLP AND RBF
ANN WHICH COVERS MLP AND RBF Josef Boští, Jaromír Kual Faculty of Nuclear Scieces ad Physical Egieerig, CTU i Prague Departmet of Software Egieerig Abstract Two basic types of artificial eural etwors Multi
More informationConsider the following population data for the state of California. Year Population
Assigmets for Bradie Fall 2016 for Chapter 5 Assigmet sheet for Sectios 5.1, 5.3, 5.5, 5.6, 5.7, 5.8 Read Pages 341-349 Exercises for Sectio 5.1 Lagrage Iterpolatio #1, #4, #7, #13, #14 For #1 use MATLAB
More informationNew Fuzzy Color Clustering Algorithm Based on hsl Similarity
IFSA-EUSFLAT 009 New Fuzzy Color Clusterig Algorithm Based o hsl Similarity Vasile Ptracu Departmet of Iformatics Techology Tarom Compay Bucharest Romaia Email: patrascu.v@gmail.com Abstract I this paper
More informationForce Network Analysis using Complementary Energy
orce Network Aalysis usig Complemetary Eergy Adrew BORGART Assistat Professor Delft Uiversity of Techology Delft, The Netherlads A.Borgart@tudelft.l Yaick LIEM Studet Delft Uiversity of Techology Delft,
More informationData-Driven Nonlinear Hebbian Learning Method for Fuzzy Cognitive Maps
Data-Drive Noliear Hebbia Learig Method for Fuzzy Cogitive Maps Wociech Stach, Lukasz Kurga, ad Witold Pedrycz Abstract Fuzzy Cogitive Maps (FCMs) are a coveiet tool for modelig of dyamic systems by meas
More informationFREQUENCY ESTIMATION OF INTERNET PACKET STREAMS WITH LIMITED SPACE: UPPER AND LOWER BOUNDS
FREQUENCY ESTIMATION OF INTERNET PACKET STREAMS WITH LIMITED SPACE: UPPER AND LOWER BOUNDS Prosejit Bose Evagelos Kraakis Pat Mori Yihui Tag School of Computer Sciece, Carleto Uiversity {jit,kraakis,mori,y
More informationAlgorithms for Disk Covering Problems with the Most Points
Algorithms for Disk Coverig Problems with the Most Poits Bi Xiao Departmet of Computig Hog Kog Polytechic Uiversity Hug Hom, Kowloo, Hog Kog csbxiao@comp.polyu.edu.hk Qigfeg Zhuge, Yi He, Zili Shao, Edwi
More informationLearning to Shoot a Goal Lecture 8: Learning Models and Skills
Learig to Shoot a Goal Lecture 8: Learig Models ad Skills How do we acquire skill at shootig goals? CS 344R/393R: Robotics Bejami Kuipers Learig to Shoot a Goal The robot eeds to shoot the ball i the goal.
More informationPython Programming: An Introduction to Computer Science
Pytho Programmig: A Itroductio to Computer Sciece Chapter 6 Defiig Fuctios Pytho Programmig, 2/e 1 Objectives To uderstad why programmers divide programs up ito sets of cooperatig fuctios. To be able to
More informationA Study on the Performance of Cholesky-Factorization using MPI
A Study o the Performace of Cholesky-Factorizatio usig MPI Ha S. Kim Scott B. Bade Departmet of Computer Sciece ad Egieerig Uiversity of Califoria Sa Diego {hskim, bade}@cs.ucsd.edu Abstract Cholesky-factorizatio
More informationCreating Exact Bezier Representations of CST Shapes. David D. Marshall. California Polytechnic State University, San Luis Obispo, CA , USA
Creatig Exact Bezier Represetatios of CST Shapes David D. Marshall Califoria Polytechic State Uiversity, Sa Luis Obispo, CA 93407-035, USA The paper presets a method of expressig CST shapes pioeered by
More informationInvestigating methods for improving Bagged k-nn classifiers
Ivestigatig methods for improvig Bagged k-nn classifiers Fuad M. Alkoot Telecommuicatio & Navigatio Istitute, P.A.A.E.T. P.O.Box 4575, Alsalmia, 22046 Kuwait Abstract- We experimet with baggig knn classifiers
More informationarxiv: v2 [cs.ds] 24 Mar 2018
Similar Elemets ad Metric Labelig o Complete Graphs arxiv:1803.08037v [cs.ds] 4 Mar 018 Pedro F. Felzeszwalb Brow Uiversity Providece, RI, USA pff@brow.edu March 8, 018 We cosider a problem that ivolves
More informationComputers and Scientific Thinking
Computers ad Scietific Thikig David Reed, Creighto Uiversity Chapter 15 JavaScript Strigs 1 Strigs as Objects so far, your iteractive Web pages have maipulated strigs i simple ways use text box to iput
More informationA Novel Approach for Coin Identification using Eigenvalues of Covariance Matrix, Hough Transform and Raster Scan Algorithms
Iteratioal Joural of Computer, Electrical, Automatio, Cotrol ad Iformatio Egieerig Vol:, No:8, 008 A Novel Approach for Coi Idetificatio usig Eigevalues of Covariace Matrix, Hough Trasform ad Raster Sca
More informationDescriptive Statistics Summary Lists
Chapter 209 Descriptive Statistics Summary Lists Itroductio This procedure is used to summarize cotiuous data. Large volumes of such data may be easily summarized i statistical lists of meas, couts, stadard
More informationAn Efficient Image Rectification Method for Parallel Multi-Camera Arrangement
Y.-S. Kag ad Y.-S. Ho: A Efficiet Image Rectificatio Method for Parallel Multi-Camera Arragemet 141 A Efficiet Image Rectificatio Method for Parallel Multi-Camera Arragemet Yu-Suk Kag ad Yo-Sug Ho, Seior
More informationHADOOP: A NEW APPROACH FOR DOCUMENT CLUSTERING
Y.K. Patil* Iteratioal Joural of Advaced Research i ISSN: 2278-6244 IT ad Egieerig Impact Factor: 4.54 HADOOP: A NEW APPROACH FOR DOCUMENT CLUSTERING Prof. V.S. Nadedkar** Abstract: Documet clusterig is
More informationAn Image Retrieval Method Based on Hu Invariant Moment and Improved Annular Histogram
http://dx.doi.org/10.5755/j01.eee.0.4.6888 ELEKTROIKA IR ELEKTROTECHIKA ISS 139 115 VOL. 0 O. 4 014 A Image Retrieval Method Based o Hu Ivariat Momet ad Improved Aular Histogram F. Xiag 1 H. Yog 1 S. Dada
More informationIntroduction. Nature-Inspired Computing. Terminology. Problem Types. Constraint Satisfaction Problems - CSP. Free Optimization Problem - FOP
Nature-Ispired Computig Hadlig Costraits Dr. Şima Uyar September 2006 Itroductio may practical problems are costraied ot all combiatios of variable values represet valid solutios feasible solutios ifeasible
More informationText Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree
Available olie at www.ijpe-olie.com vol. 13, o. 7, November 017, pp. 1159-1164 DOI: 10.3940/ijpe.17.07.p19.11591164 Text Feature Selectio based o Feature Dispersio Degree ad Feature Cocetratio Degree Zhifeg
More informationVariance as a Stopping Criterion for Genetic Algorithms with Elitist Model
Fudameta Iformaticae 120 (2012) 145 164 145 DOI 10.3233/FI-2012-754 IOS Press Variace as a Stoppig Criterio for Geetic Algorithms with Elitist Model Diabadhu Bhadari, C. A. Murthy, Sakar K. Pal Ceter for
More information