Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment

Size: px
Start display at page:

Download "Turkish Fingerspelling Recognition System Using Axis of Least Inertia Based Fast Alignment"

Transcription

1 Turkish Figerspellig ecogitio System Usig Axis of Least Iertia Based Fast Aligmet Oğuz Altu, Sogül Albayrak, Ali Ekici, ad Behzat Bükü Yıldız Techical Uiversity, Computer Egieerig Departmet, Yıldız, İstabul, Türkiye {oguz, Abstract. Figerspellig is used i sig laguage to spell out ames of people ad places for which there is o sig or for which the sig is ot kow. I this work we describe a Turkish figerspellig recogitio system that recogizes all 9 letters of the Turkish alphabet. A sigle represetative frame is extracted from the sig video, sice that frame is eough for recogitio purposes of the letters metioed. Processig a sigle frame, istead of the whole video, icreases speed cosiderably. The ski regios i the represetative frame are extracted by color segmetatio i YCrCb space before clearig oise regios by morphological opeig. A ovel fast aligmet method that uses the agle of orietatio betwee the axis of least iertia ad y axis is applied to had regios. This method compesates small orietatio differeces but icreases big oes. This is desirable whe differetiatig the figerspellig sigs, some of which are close i shape but differet i orietatio. Also the use of miimum boudig square is advised, which helps i resizig without breakig the aligmet. Biary values of this miimum boudig square are directly used as feature values, ad that allowed experimetig with differet classificatio schemes. Features like mea radial distace ad circularity are also used for icreasig success rate. Classifiers like knn, SVM, Naïve Bayes, ad BF Network are experimeted with, ad 1NN ad SVM are foud to be the best two of them. The video database was created by 3 differet sigers, a set of 90 traiig videos, ad a separate set of 174 testig videos are used i experimets. The best classifiers 1NN ad SVM achieved a success rate of 99.43% ad 98.83% respectively. Keywords: Turkish Figerspellig ecogitio, Fast Aligmet, Agle of orietatio, Axis of Least Iertia, Miimum Boudig Square, Classificatio. 1 Itroductio Sig Laguage is a visual meas of commuicatio usig gestures, facial expressio, ad body laguage. Sig Laguage is used maily by deaf people ad people with hearig difficulties. There are two major types of commuicatio i sig laguage. The first oe has word based sig vocabulary, where gestures, facial expressio, ad body laguage are used for the most commo words. The secod oe has letter based vocabulary, ad is called figerspellig, which is a method of spellig words usig had movemets. Figerspellig is used i sig laguage to spell out ames of people A. Sattar ad B.H. Kag (Eds.): AI 006, LNAI 4304, pp , 006. Spriger-Verlag Berli Heidelberg 006

2 474 O. Altu et al. ad places for which there is o sig ad ca also be used to spell words for sigs that the siger does ot kow the sig for, or to clarify a sig that is ot kow by the perso readig the siger [1]. Sig laguages develop specific to their commuities ad are ot uiversal. For example, ASL (America Sig Laguage) is totally differet from British Sig Laguage eve though both coutries speak Eglish []. I the automatic sig laguage recogitio, there are successful systems for America Sig Laguage (SL) [3], Australia SL [4], ad Chiese SL [5]. Previous approaches to word level sig recogitio rely heavily o statistical models such as Hidde Markov Models (HMMs). A real-time ASL recogitio system developed by Starer ad Petlad [3] used colored gloves to track ad idetify left ad right hads. They extracted global features that represet positios, agle of axis of least iertia, ad eccetricity of the boudig ellipse of two hads. Usig a HMM recogizer with a kow grammar, they achieved a 99.% accuracy at the word level for 99 test sequeces. For TSL (Turkish Sig Laguage) Haberdar ad Albayrak [6], developed a TSL recogitio system from video usig HMMs for trajectories of hads. The system achieved a word accuracy of 95.7% by cocetratig oly o the global features of the geerated sigs. The developed system is the first comprehesive study o TSL ad recogizes 50 isolated sigs. This study is improved with local features ad performs perso depedet recogitio of 17 isolated sigs i two stages with a accuracy of 93.31% [7]. For figerspellig recogitio, most successful approaches are based o istrumeted gloves, which provide iformatio about figer positios. Lamar ad Bhuiyat [8] achieved letter recogitio rates ragig from 70% to 93%, usig colored gloves ad eural etworks. More recetly, ebollar et al. [9] used a more sophisticated glove to classify 1 out of 6 letters with 100% accuracy. The worst case, letter U, achieved 78% accuracy. Isaacs ad Foo [10] developed a two layer feed-forward eural etwork that recogizes the 4 static letters i the America Sig Laguage (ASL) alphabet usig still iput images. ASL figerspellig recogitio system is with 99.9% accuracy with a SN as low as. Feris, Turk ad others [11] used a multi-flash camera with flashes strategically positioed to cast shadows alog depth discotiuities i the scee, allowig efficiet ad accurate had shape extractio. Altu et al. [1] icreased the effect of figers i Turkish figerspellig shapes by thick edge detectio ad correlatio with pealizatio. They achieved 99% accuracy out of 03 sig videos of 9 the Turkish alphabet letters. I this work, we have developed a siger idepedet figerspellig recogitio system for Turkish Sig Laguage (TSL). The represetative frames are extracted from sig videos. Had objects i these frames are segmeted out by ski color i YCrCb space. These had objects are aliged usig the ovel agle of orietatio based fast aligmet method. The, the aliged object is moved ito the ceter of a miimum boudig square, ad resized. The biary values of the miimum boudig square are used as classificatio features, i additio to the biary object features like mea radial distace ad circularity. We experimeted with differet classificatio schemes ad reported their success rate. The remaiig of this paper is orgaized as follows: I Sectio we describe the represetative frame extractio, our fast aligmet method, ad extractio of

3 Turkish Figerspellig ecogitio System 475 additioal object features. Sectio 3 covers the video database we use. We listed the classificatio schemes we used i Sectio 4. Fially, coclusios ad future work are addressed i Sectio 5. Feature Extractio Cotrary to Turkish Sig Laguage word sigs, Turkish figerspellig sigs, because of their static structure, ca be discrimiated by shape aloe by use of a represetative frame. To take advatage of this ad to icrease processig speed, these represetative frames are extracted ad used for recogitio. Fig. 1 shows represetative frames for all 9 Turkish Alphabet letters. Fig. 1. epresetative frames for all 9 letters i Turkish Alphabet I each represetative frame, had regios are determied by ski color. From the biary images that show had ad backgroud pixels, the regios we are iterested i are extracted, aliged ad resized. I additio to aliged biary pixel values, biary object features are extracted to support maximum correlatio based matchig. Each process is summarized below:.1 epresetative Frame Extractio I a Turkish figerspellig video, represetative frames are the oes with least had movemet. Hece, the frame whose distace to its successor is miimum ca be chose as a represetative frame. Distace betwee successive frames f ad f+1 is give by the sum of the city block distace betwee correspodig pixels:

4 476 O. Altu et al. (a) (b) Fig.. (a) Origial image ad detected ski regios after pixel classificatio, (b) result of the morphological opeig. (a) (b) (c) (d) Fig. 3. (a)-(b) The 'C' sig by two differet sigers. (c)-(d) The 'U' sig by two differet sigers. D f f f f = Δ + ΔG + ΔB, (1) where f iterates over frames, iterates over pixels,, G, B are the compoets of the pixel color, f f +1 f Δ =, f f +1 f ΔG = G G, ad f f +1 f ΔB = B B.. Ski Detectio by Color For ski detectio, YCrCb color-space has bee foud to be superior to other color spaces such as GB ad HSV [13]. Hece we covert the pixel values of images from GB color space to YCrCb usig (). I order to decrease oise, each of the Y, Cr ad Cb compoets of the image are smoothed with the D Gaussia filter give by (3), where σ is its stadard deviatio Y = G B, = B Y, = Y () 1 x + y F( x, = exp( ), (3) πσ σ Chai ad Bouzerdom [14] report that pixels that belog to the ski regio have similar Cr ad Cb values, ad give a distributio of the pixel color i Cr-Cb plae. Cosequetly, we classified a pixel as ski if the Y, Cr, Cb values of it falls iside the rages 135 < Cr < 180, 85 < Cb < 135 ad Y > 80 (Fig..a). After clearig small ski colored regios by morphological opeig (Fig..b), ski detectio is completed. C r C b

5 Turkish Figerspellig ecogitio System Fast Aligmet for Maximum Correlatio Based Template Matchig Template matchig is very sesitive to size ad orietatio chages. A scheme that ca compesate size ad orietatio chages is eeded. Elimiatig orietatio iformatio totally is ot appropriate however, as depicted i Fig. 3. Fig. 3a-b show two 'C' sigs that we must be able to match each other, so we must compesate the small orietatio differece. I Fig. 3c-d we see two 'U' sigs that we eed to differetiate from 'C' sigs. 'U' sigs ad 'C' sigs are quite similar to each other i shape, luckily orietatio is a major differetiator. As a result we eed a scheme that ot oly ca compesate small orietatio differeces of had regios, but also is resposive to large oes. Fig. 4. Axis of least secod momet ad the agle of orietatio We propose a fast aligmet method that works by makig the agle of orietatio (θ ) zero. Agle of orietatio, give by (4), is the agle betwee y axis ad the axis of least momet (show i Fig. 4). M11 θ = arcta M 0 M where (I(x, = 1 for pixels o the object, 0 otherwise), M ) = xi( x, y, ad = 0 x y x M y I( x, 0 y. 0 (4) M = xyi( x, 11 x y, (a) (b) (c) (d) (e) Fig. 5. Stages of fast aligmet. (a) Origial frame. (b) Detected ski regios. (c) egio of Iterest (OI). (d) otated OI. (e) esized boudig square with the object i the ceter.

6 478 O. Altu et al. Let's defie boudig square as the smallest square that ca completely eclose all the pixels of the object. After puttig images i the ceter of a boudig square, ad tha resizig the boudig square to a fixed, smaller resolutio, the fast aligmet process eds (Fig. 5)..4 Additioal Biary Object Features Istead of usig oly pixel values i the boudig square, additioal biary object features are extracted to support decisio process. These features iclude area, ceter of area, perimeter [15], agle of orietatio (defied above), ad circularity (defied as perimeter /area). I additio, mea radial distace μ is extracted: 1 μ = ( x, y ) ( x, (5) N where iterates over all pixels, N is the umber of pixels, ( x, y ) is the ceter of area, ( x, y ) is the coordiate of the th pixel, ad. deotes the Euclidea distace betwee two pixels. Aother feature is the stadard deviatio of radial distace σ, defied as 1 1 ( [( x, y ) ( x, μ ] ) N σ =. (6) As the last biary object feature, a secod circularity measure C is computed by C = μ σ. (7) To summarize, 9 biary object features are added to the 30x30 biary values of the miimum boudary square. 3 Video Database The traiig ad test videos are acquired by a Philips PCVC840K CCD webcam. The capture resolutio is set to 30x40 with 15 frames per secod (fps). While programmig is doe i C++, the Itel OpeCV library routies are used for video capturig ad some of the image processig tasks. We have developed a Turkish Sig Laguage figerspellig recogitio system for the 9 static letters i Turkish Alphabet. The traiig set was created usig three differet sigers. For traiig, they siged a total of 10 times for each letter, which sums up to 90 traiig videos. For testig, they siged a total of 6 times for each letter, which sums up to 174 test videos. Table 1 gives a summary of the distributio of the trai ad test video umbers for each siger. Notice that traiig ad test sets are totally separated.

7 Turkish Figerspellig ecogitio System 479 Table 1. Distributio of trai ad test video umbers for each siger Siger 1 Siger Siger 3 Total Trai Test Trai Test Trai Test Trai Test A Z Total Table. Success rates of most successful classifiers o figerspellig data Classifier Success ate (%) 1NN [16] SVM [17] adom Forest [18] BF Network [19] Multiomial Naive Bayes [0] Naive Bayes [1] J48 [] Classificatio Compariso A set of differet classificatio algorithms are applied to the features extracted as explaied i Sectio ad obtaied results are sorted accordig to their success rates. These classificatio results are summarized i Table. The most successful classifiers are oe earest eighbor (1NN) ad support vector machie (SVM). These methods classified more tha 98% successfully, as see i Table. The biggest problem is i the classificatio of the letter 'S', which is cofused by ' '. A secod problem letter was 'G', which is cofused by ' '. The cofused characters are very similar to each other i shape, as see i Fig. 6. Fig. 6. Two difficult cases where our methods may fail. Left to right: 'S' ad ' ', 'G' ad ' '. 5 Coclusios ad Future Work A Turkish figerspellig recogitio system is tested ad foud to have more tha 99% accuracy. Testig ad traiig sets is created by multiple sigers, as a cosequece the developed system is siger idepedet. Accuracy is the result of the

8 480 O. Altu et al. fast aligmet process we applied. This process brigs objects with similar orietatio ito same aligmet, while brigig objects with high orietatio differece ito differet aligmet. This is a desired result, because for figerspellig recogitio, shapes that belog to differet letters ca be very similar, ad the orietatio ca be the mai differetiator. After the aligmet, to resize without breakig the aligmet, the object is moved ito the ceter of a miimum boudig square. The biary values i miimum boudig square are used as the features. I additio, we used biary object features like circularity ad mea radial distace, which helped icreasig success rate. Our method is robust to the problem of occlusio of the hads, because the fast aligmet method allows us to process a esemble of oe or more coected compoets i the same way. The system is fast due to represetig the sig video by a sigle frame, the speed of fast aligmet process, ad resizig the boudig square to a smaller resolutio. The amout of resizig ca be arraged for differet applicatios. Sice we used biary pixel values as ordiary features, we are able to experimet with differet classificatio algorithms, amogst which are knn, SVM, BF Network, Naïve Bayes, adom Forest, ad J48 tree. The 1NN ad SVM give the best success rates, 99.43% ad 98.85% respectively. Not all letters i Turkish alphabet are represetable by oe sigle frame, ' ' beig a example. The sig of letter ivolves some movemet that differetiates it from 'S'. I fact, this letter is the oe that preveted us achievig a 100% success rate. Still, represetig the whole sig by oe sigle frame is acceptable sice this work is actually a step towards makig a full blow Turkish Sig Laguage recogitio system that ca also recogize word sigs. That system will icorporate ot oly shape but also the movemet, ad the research o it is cotiuig. The importace of successful segmetatio of the ski ad backgroud regios ca ot be overstated. I this work we assumed that there is o ski colored backgroud regios ad used color based segmetatio i YCrCb space. The systems' success depeds o that assumptio, ad research o better ski segmetatio is ivaluable. The fast aligmet ad classificatio schemes preseted would work equally well i the existece of a face i the frame, eve though i this study we used oly had regios whe creatig the figerspellig video database. Although we demostrated the fast aligmet method i the cotext of had shape recogitio, it is equally applicable to other problems where shape recogitio is required, for example to the problem of shape retrieval. efereces Starer, T., Weaver, J., Petlad, A.: eal-time America sig laguage recogitio usig desk ad wearable computer based video. Ieee Trasactios o Patter Aalysis ad Machie Itelligece 0 (1998) Holde, E.J., Lee, G., Owes,.: Australia sig laguage recogitio. Machie Visio ad Applicatios 16 (005) 31-30

9 Turkish Figerspellig ecogitio System Gao, W., Fag, G.L., Zhao, D.B., Che, Y.Q.: A Chiese sig laguage recogitio system based o SOFM/SN/HMM. Patter ecogitio 37 (004) Haberdar, H., Albayrak, S.: eal Time Isolated Turkish Sig Laguage ecogitio From Video Usig Hidde Markov Models With Global Features. Lecture Notes i Computer Sciece LNCS 3733 (005) Haberdar, H., Albayrak, S.: Visio Based eal Time Isolated Turkish Sig Laguage ecogitio. Iteratioal Symposium o Methodologies for Itelliget Systems, Bari, Italy (006) 8. Lamar, M., Bhuiyat, M.: Had Alphabet ecogitio Usig Morphological PCA ad Neural Networks. Iteratioal Joit Coferece o Neural Networks, Washigto, USA (1999) ebollar, J., Lidema,., Kyriakopoulos, N.: A Multi-Class Patter ecogitio System for Practical Figerspellig Traslatio. Iteratioal Coferece o Multimodel Iterfaces, Pittsburgh, USA (00) 10. Isaacs, J., Foo, S.: Had Pose Estimatio for America Sig Laguage ecogitio. Thirty-Sixth Southeaster Symposium o, IEEE System Theory (004) Feris,., Turk, M., askar,., Ta, K.: Exploitig Depth Discotiuities for Visio- Based Figerspellig ecogitio. 004 IEEE Computer Society Coferece o Computer Visio ad Patter ecogitio Workshops(CVPW'04) (004) 1. Altu, O., Albayrak, S., Ekici, A., Bükü, B.: Icreasig the Effect of Figers i Figerspellig Had Shapes by Thick Edge Detectio ad Correlatio with Pealizatio. PSIVT 006 (006) 13. Sazoov, V., Vezhevetsi, V., Adreeva, A.: A survey o pixel vased ski color detectio techiques. Graphico-003 (003) Chai, D., Bouzerdom, A.: A Bayesia Approach To Ski Colour Classificatio. TENCON- 000 (000) 15. Umbaugh, S.E.: Computer Visio ad Image Processig: A Practical Approach Usig CVIPtools. Pretice Hall (1998) 16. Aha, D.W., Kibler, D., Albert, M.K.: Istace-Based Learig Algorithms. Machie Learig 6 (1991) Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K..K.: Improvemets to Platt's SMO algorithm for SVM classifier desig. Neural Computatio 13 (001) Breima, L.: adom forests. Machie Learig 45 (001) Fritzke, B.: Fast Learig with Icremetal bf Networks. Neural Processig Letters 1 (1994) McCallum, A., Nigam, K.: A Compariso of Evet Models for Naive Bayes Text Classificatio. AAAI-98, Workshop o Learig for Text Categorizatio (1998) 1. Joh, G.H., Lagley, P.: Estimatig Cotiuous Distributios i Bayesia Classifiers. Eleveth Coferece o Ucertaity i Artificial Itelligece. Morga Kaufma, Sa Mateo (1995) Quila,.: C4.5: Programs for Machie Learig. Morga Kaufma Publishers, Sa Mateo, CA (1993)

Neuro Fuzzy Model for Human Face Expression Recognition

Neuro 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 information

3D Model Retrieval Method Based on Sample Prediction

3D 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 information

New HSL Distance Based Colour Clustering Algorithm

New 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 information

Lip Contour Extraction Based on Support Vector Machine

Lip Contour Extraction Based on Support Vector Machine Lip Cotour Extractio Based o Support Vector Machie Author Pa, Xiaosheg, Kog, Jiagpig, Liew, Ala Wee-Chug Published 008 Coferece Title CISP 008 : Proceedigs, First Iteratioal Cogress o Image ad Sigal Processig

More information

Image Segmentation EEE 508

Image 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 information

Application of Decision Tree and Support Vector Machine for Inspecting Bubble Defects on LED Sealing Glue Images

Application of Decision Tree and Support Vector Machine for Inspecting Bubble Defects on LED Sealing Glue Images 66 Applicatio of Decisio Tree ad Support Vector Machie for Ispectig Bubble Defects o LED Sealig Glue Images * Chua-Yu Chag ad Yi-Feg Li Abstract Bubble defect ispectio is a importat step i light-emittig

More information

A New Morphological 3D Shape Decomposition: Grayscale Interframe Interpolation Method

A 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 information

Investigating methods for improving Bagged k-nn classifiers

Investigating 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 information

The Closest Line to a Data Set in the Plane. David Gurney Southeastern Louisiana University Hammond, Louisiana

The 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 information

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process

Euclidean Distance Based Feature Selection for Fault Detection Prediction Model in Semiconductor Manufacturing Process Vol.133 (Iformatio Techology ad Computer Sciece 016), pp.85-89 http://dx.doi.org/10.1457/astl.016. Euclidea Distace Based Feature Selectio for Fault Detectio Predictio Model i Semicoductor Maufacturig

More information

A Novel Feature Extraction Algorithm for Haar Local Binary Pattern Texture Based on Human Vision System

A 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 information

Dynamic Programming and Curve Fitting Based Road Boundary Detection

Dynamic 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 information

Pattern Recognition Systems Lab 1 Least Mean Squares

Pattern 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 information

Detection and Classification of Apple Fruit Diseases using Complete Local Binary Patterns

Detection and Classification of Apple Fruit Diseases using Complete Local Binary Patterns 2012 Third Iteratioal Coferece o Computer ad Commuicatio Techology Detectio ad Classificatio of Apple Fruit Diseases usig Complete Local Biary Patters Shiv Ram Dubey Departmet of Computer Egieerig ad Applicatios

More information

Fundamentals of Media Processing. Shin'ichi Satoh Kazuya Kodama Hiroshi Mo Duy-Dinh Le

Fundamentals 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 information

ANN WHICH COVERS MLP AND RBF

ANN 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 information

Improvement of the Orthogonal Code Convolution Capabilities Using FPGA Implementation

Improvement 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 information

Improving Template Based Spike Detection

Improving 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 information

RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE

RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE RESEARCH ON AUTOMATIC INSPECTION TECHNIQUE OF REAL-TIME RADIOGRAPHY FOR TURBINE-BLADE Z.G. Zhou, S. Zhao, ad Z.G. A School of Mechaical Egieerig ad Automatio, Beijig Uiversity of Aeroautics ad Astroautics,

More information

Handwriting Stroke Extraction Using a New XYTC Transform

Handwriting Stroke Extraction Using a New XYTC Transform Hadwritig Stroke Etractio Usig a New XYTC Trasform Gilles F. Houle 1, Kateria Bliova 1 ad M. Shridhar 1 Computer Scieces Corporatio Uiversity Michiga-Dearbor Abstract: The fudametal represetatio of hadwritig

More information

x x 2 x Iput layer = quatity of classificatio mode X T = traspositio matrix The core of such coditioal probability estimatig method is calculatig the

x x 2 x Iput layer = quatity of classificatio mode X T = traspositio matrix The core of such coditioal probability estimatig method is calculatig the COMPARATIVE RESEARCHES ON PROBABILISTIC NEURAL NETWORKS AND MULTI-LAYER PERCEPTRON NETWORKS FOR REMOTE SENSING IMAGE SEGMENTATION Liu Gag a, b, * a School of Electroic Iformatio, Wuha Uiversity, 430079,

More information

BASED ON ITERATIVE ERROR-CORRECTION

BASED ON ITERATIVE ERROR-CORRECTION A COHPARISO OF CRYPTAALYTIC PRICIPLES BASED O ITERATIVE ERROR-CORRECTIO Miodrag J. MihaljeviC ad Jova Dj. GoliC Istitute of Applied Mathematics ad Electroics. Belgrade School of Electrical Egieerig. Uiversity

More information

Accuracy Improvement in Camera Calibration

Accuracy 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 information

Chapter 1. Introduction to Computers and C++ Programming. Copyright 2015 Pearson Education, Ltd.. All rights reserved.

Chapter 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 information

Ones Assignment Method for Solving Traveling Salesman Problem

Ones 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 information

Improving Information Retrieval System Security via an Optimal Maximal Coding Scheme

Improving Information Retrieval System Security via an Optimal Maximal Coding Scheme Improvig Iformatio Retrieval System Security via a Optimal Maximal Codig Scheme Dogyag Log Departmet of Computer Sciece, City Uiversity of Hog Kog, 8 Tat Chee Aveue Kowloo, Hog Kog SAR, PRC dylog@cs.cityu.edu.hk

More information

Image based Cats and Possums Identification for Intelligent Trapping Systems

Image 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 information

Hand Gesture Recognition for Human-Machine Interaction

Hand 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 information

Stone Images Retrieval Based on Color Histogram

Stone 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 information

Evaluation scheme for Tracking in AMI

Evaluation 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 information

Bayesian approach to reliability modelling for a probability of failure on demand parameter

Bayesian 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 information

IMP: Superposer Integrated Morphometrics Package Superposition Tool

IMP: 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 information

An Efficient Image Rectification Method for Parallel Multi-Camera Arrangement

An 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 information

IMAGE-BASED MODELING AND RENDERING 1. HISTOGRAM AND GMM. I-Chen Lin, Dept. of CS, National Chiao Tung University

IMAGE-BASED MODELING AND RENDERING 1. HISTOGRAM AND GMM. I-Chen Lin, Dept. of CS, National Chiao Tung University IMAGE-BASED MODELING AND RENDERING. HISTOGRAM AND GMM I-Che Li, Dept. of CS, Natioal Chiao Tug Uiversity Outlie What s the itesity/color histogram? What s the Gaussia Mixture Model (GMM? Their applicatios

More information

A SOFTWARE MODEL FOR THE MULTILAYER PERCEPTRON

A 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 information

Random Graphs and Complex Networks T

Random Graphs and Complex Networks T Radom Graphs ad Complex Networks T-79.7003 Charalampos E. Tsourakakis Aalto Uiversity Lecture 3 7 September 013 Aoucemet Homework 1 is out, due i two weeks from ow. Exercises: Probabilistic iequalities

More information

Harris Corner Detection Algorithm at Sub-pixel Level and Its Application Yuanfeng Han a, Peijiang Chen b * and Tian Meng c

Harris 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 information

are two specific neighboring points, F( x, y)

are two specific neighboring points, F( x, y) $33/,&$7,212)7+(6(/)$92,',1* 5$1'20:$/.12,6(5('8&7,21$/*25,7+0,17+(&2/285,0$*(6(*0(17$7,21 %RJGDQ602/.$+HQU\N3$/86'DPLDQ%(5(6.$ 6LOHVLDQ7HFKQLFDO8QLYHUVLW\'HSDUWPHQWRI&RPSXWHU6FLHQFH $NDGHPLFND*OLZLFH32/$1'

More information

CSCI 5090/7090- Machine Learning. Spring Mehdi Allahyari Georgia Southern University

CSCI 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 information

Administrative UNSUPERVISED LEARNING. Unsupervised learning. Supervised learning 11/25/13. Final project. No office hours today

Administrative UNSUPERVISED LEARNING. Unsupervised learning. Supervised learning 11/25/13. Final project. No office hours today Admiistrative Fial project No office hours today UNSUPERVISED LEARNING David Kauchak CS 451 Fall 2013 Supervised learig Usupervised learig label label 1 label 3 model/ predictor label 4 label 5 Supervised

More information

FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER

FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER GAURI AGRAWAL AND SANJAY KUMAR MAURYA: FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT USING SOM AND ENSEMBLE BASED CLASSIFIER DOI: 0.297/ijivp.206.082 FACE RECOGNITION BY EMBEDDING OF DT-CWT COEFFICIENT

More information

New Fuzzy Color Clustering Algorithm Based on hsl Similarity

New 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 information

GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT

GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT 6th Iteratioal DAAAM Baltic Coferece INDUSTRIAL ENGINEERING 24-26 April 2008, Talli, Estoia GEOMETRIC REVERSE ENGINEERING USING A LASER PROFILE SCANNER MOUNTED ON AN INDUSTRIAL ROBOT Rahayem, M.; Kjellader,

More information

A New Network-based Algorithm for Human Activity Recognition in Videos

A New Network-based Algorithm for Human Activity Recognition in Videos IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, A New Network-based Algorithm for Huma Activity Recogitio i Videos Weiyao Li, Yuazhe Che, Jiaxi Wu, Hali Wag, Bi Sheg, ad Hogxiag Li Abstract

More information

USING PHASE AND MAGNITUDE INFORMATION OF THE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION

USING PHASE AND MAGNITUDE INFORMATION OF THE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION 6th Europea Sigal Processig Coferece EUSIPCO 008, Lausae, Switzerlad, August 5-9, 008, copyright by EURASIP USING PASE AND MAGNITUDE INFORMATION OF TE COMPLEX DIRECTIONAL FILTER BANK FOR TEXTURE SEGMENTATION

More information

Automatic Road Extraction from Satellite Image

Automatic Road Extraction from Satellite Image Automatic Road Extractio from Satellite Image B.Sowmya Dept. of Electroics & Cotrol Egg., Sathyabama Istitute of Sciece & Techology, Deemed Uiversity, Cheai bsowya@yahoo.com Abstract This paper explais

More information

The isoperimetric problem on the hypercube

The isoperimetric problem on the hypercube The isoperimetric problem o the hypercube Prepared by: Steve Butler November 2, 2005 1 The isoperimetric problem We will cosider the -dimesioal hypercube Q Recall that the hypercube Q is a graph whose

More information

An Image Retrieval Method Based on Hu Invariant Moment and Improved Annular Histogram

An 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 information

Algorithms for Disk Covering Problems with the Most Points

Algorithms 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 information

Unsupervised Discretization Using Kernel Density Estimation

Unsupervised Discretization Using Kernel Density Estimation Usupervised Discretizatio Usig Kerel Desity Estimatio Maregle Biba, Floriaa Esposito, Stefao Ferilli, Nicola Di Mauro, Teresa M.A Basile Departmet of Computer Sciece, Uiversity of Bari Via Oraboa 4, 7025

More information

Auto-recognition Method for Pointer-type Meter Based on Binocular Vision

Auto-recognition Method for Pointer-type Meter Based on Binocular Vision JOURNAL OF COMPUTERS, VOL. 9, NO. 4, APRIL 204 787 Auto-recogitio Method for Poiter-type Meter Based o Biocular Visio Biao Yag School of Istrumet Sciece ad Egieerig, Southeast Uiversity, Najig 20096, Chia

More information

Automated Extraction of Urban Trees from Mobile LiDAR Point Clouds

Automated Extraction of Urban Trees from Mobile LiDAR Point Clouds Automated Extractio of Urba Trees from Mobile LiDAR Poit Clouds Fa W. a, Cheglu W. a*, ad Joatha L. ab a Fujia Key Laboratory of Sesig ad Computig for Smart City ad the School of Iformatio Sciece ad Egieerig,

More information

CIS 121 Data Structures and Algorithms with Java Spring Stacks, Queues, and Heaps Monday, February 18 / Tuesday, February 19

CIS 121 Data Structures and Algorithms with Java Spring Stacks, Queues, and Heaps Monday, February 18 / Tuesday, February 19 CIS Data Structures ad Algorithms with Java Sprig 09 Stacks, Queues, ad Heaps Moday, February 8 / Tuesday, February 9 Stacks ad Queues Recall the stack ad queue ADTs (abstract data types from lecture.

More information

What are we going to learn? CSC Data Structures Analysis of Algorithms. Overview. Algorithm, and Inputs

What 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 information

On the Accuracy of Vector Metrics for Quality Assessment in Image Filtering

On the Accuracy of Vector Metrics for Quality Assessment in Image Filtering 0th IMEKO TC4 Iteratioal Symposium ad 8th Iteratioal Workshop o ADC Modellig ad Testig Research o Electric ad Electroic Measuremet for the Ecoomic Uptur Beeveto, Italy, September 5-7, 04 O the Accuracy

More information

A Comparative Study of Color Edge Detection Techniques

A Comparative Study of Color Edge Detection Techniques CS31A WINTER-1314 PROJECT REPORT 1 A Comparative Study of Color Edge Detectio Techiques Masood Shaikh, Departmet of Electrical Egieerig, Staford Uiversity Abstract Edge detectio has attracted the attetio

More information

A new algorithm to build feed forward neural networks.

A new algorithm to build feed forward neural networks. A ew algorithm to build feed forward eural etworks. Amit Thombre Cetre of Excellece, Software Techologies ad Kowledge Maagemet, Tech Mahidra, Pue, Idia Abstract The paper presets a ew algorithm to build

More information

Using a Dynamic Interval Type-2 Fuzzy Interpolation Method to Improve Modeless Robots Calibrations

Using a Dynamic Interval Type-2 Fuzzy Interpolation Method to Improve Modeless Robots Calibrations Joural of Cotrol Sciece ad Egieerig 3 (25) 9-7 doi:.7265/2328-223/25.3. D DAVID PUBLISHING Usig a Dyamic Iterval Type-2 Fuzzy Iterpolatio Method to Improve Modeless Robots Calibratios Yig Bai ad Dali Wag

More information

Position and Velocity Estimation by Ultrasonic Sensor

Position and Velocity Estimation by Ultrasonic Sensor Positio ad Velocity Estimatio by Ultrasoic Sesor N Ramarao 1, A R Subramayam 2, J Chara Raj 2, Lalith B V 2, Varu K R 2 1 (Faculty of EEE, BMSIT & M, INDIA) 2 (Studets of EEE, BMSIT & M, INDIA) Abstract:

More information

CS 683: Advanced Design and Analysis of Algorithms

CS 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 information

Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning

Improving Face Recognition Rate by Combining Eigenface Approach and Case-based Reasoning 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

More information

Effect of control points distribution on the orthorectification accuracy of an Ikonos II image through rational polynomial functions

Effect 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 information

Our Learning Problem, Again

Our Learning Problem, Again Noparametric Desity Estimatio Matthew Stoe CS 520, Sprig 2000 Lecture 6 Our Learig Problem, Agai Use traiig data to estimate ukow probabilities ad probability desity fuctios So far, we have depeded o describig

More information

Evaluation of Support Vector Machine Kernels for Detecting Network Anomalies

Evaluation of Support Vector Machine Kernels for Detecting Network Anomalies Evaluatio of Support Vector Machie Kerels for Detectig Network Aomalies Prera Batta, Maider Sigh, Zhida Li, Qigye Dig, ad Ljiljaa Trajković Commuicatio Networks Laboratory http://www.esc.sfu.ca/~ljilja/cl/

More information

Soft Computing Based Range Facial Recognition Using Eigenface

Soft 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 information

CSC 220: Computer Organization Unit 11 Basic Computer Organization and Design

CSC 220: Computer Organization Unit 11 Basic Computer Organization and Design College of Computer ad Iformatio Scieces Departmet of Computer Sciece CSC 220: Computer Orgaizatio Uit 11 Basic Computer Orgaizatio ad Desig 1 For the rest of the semester, we ll focus o computer architecture:

More information

. Written in factored form it is easy to see that the roots are 2, 2, i,

. Written in factored form it is easy to see that the roots are 2, 2, i, CMPS A Itroductio to Programmig Programmig Assigmet 4 I this assigmet you will write a java program that determies the real roots of a polyomial that lie withi a specified rage. Recall that the roots (or

More information

Eigenimages. Digital Image Processing: Bernd Girod, 2013 Stanford University -- Eigenimages 1

Eigenimages. 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 information

Sorting in Linear Time. Data Structures and Algorithms Andrei Bulatov

Sorting in Linear Time. Data Structures and Algorithms Andrei Bulatov Sortig i Liear Time Data Structures ad Algorithms Adrei Bulatov Algorithms Sortig i Liear Time 7-2 Compariso Sorts The oly test that all the algorithms we have cosidered so far is compariso The oly iformatio

More information

On (K t e)-saturated Graphs

On (K t e)-saturated Graphs Noame mauscript No. (will be iserted by the editor O (K t e-saturated Graphs Jessica Fuller Roald J. Gould the date of receipt ad acceptace should be iserted later Abstract Give a graph H, we say a graph

More information

Lecture 5. Counting Sort / Radix Sort

Lecture 5. Counting Sort / Radix Sort Lecture 5. Coutig Sort / Radix Sort T. H. Corme, C. E. Leiserso ad R. L. Rivest Itroductio to Algorithms, 3rd Editio, MIT Press, 2009 Sugkyukwa Uiversity Hyuseug Choo choo@skku.edu Copyright 2000-2018

More information

Description of some supervised learning algorithms

Description of some supervised learning algorithms Descriptio of some supervised learig algorithms Patrick Keekayoro patrick.keekayoro@outlook.com Statistical Cybermetrics Research Group Uiversity of Wolverhampto 1. Supervised learig Supervised machie

More information

Creating Exact Bezier Representations of CST Shapes. David D. Marshall. California Polytechnic State University, San Luis Obispo, CA , USA

Creating 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 information

FEATURE BASED RECOGNITION OF TRAFFIC VIDEO STREAMS FOR ONLINE ROUTE TRACING

FEATURE 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 information

Eigenimages. Digital Image Processing: Bernd Girod, Stanford University -- Eigenimages 1

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 information

FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE

FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE FEATURES VECTOR FOR PERSONAL IDENTIFICATION BASED ON IRIS TEXTURE R. P. Moreo Departameto de Egeharia Elétrica EESC - USP Av. Trabalhador Sãocarlese, 400 São Carlos / SP Brasil raphael@digmotor.com.br

More information

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb

( n+1 2 ) , position=(7+1)/2 =4,(median is observation #4) Median=10lb Chapter 3 Descriptive Measures Measures of Ceter (Cetral Tedecy) These measures will tell us where is the ceter of our data or where most typical value of a data set lies Mode the value that occurs most

More information

Performance Comparisons of PSO based Clustering

Performance 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 information

Fast algorithm for skew detection. Adnan Amin, Stephen Fischer, Tony Parkinson, and Ricky Shiu

Fast algorithm for skew detection. Adnan Amin, Stephen Fischer, Tony Parkinson, and Ricky Shiu Fast algorithm for skew detectio Ada Ami, Stephe Fischer, Toy Parkiso, ad Ricky Shiu School of Computer Sciece ad Egieerig Uiversity of New South Wales, Sydey NSW, 2052 Australia ABSTRACT Documet image

More information

Descriptive Statistics Summary Lists

Descriptive 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 information

Real-Time Capable System for Hand Gesture Recognition Using Hidden Markov Models in Stereo Color Image Sequences

Real-Time Capable System for Hand Gesture Recognition Using Hidden Markov Models in Stereo Color Image Sequences Real-Time Capable System for Had Gesture Recogitio Usig Hidde Markov Models i Stereo Color Image Sequeces Mahmoud Elmezai, Ayoub Al-Hamadi, Berd Michaelis Istitute for Electroics, Sigal Processig ad Commuicatios

More information

A Study on the Performance of Cholesky-Factorization using MPI

A 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 information

Journal of Chemical and Pharmaceutical Research, 2013, 5(12): Research Article

Journal 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 information

SAML-QC: a Stochastic Assessment and Machine Learning based QC technique for Industrial Printing

SAML-QC: a Stochastic Assessment and Machine Learning based QC technique for Industrial Printing SAML-QC: a Stochastic Assessmet ad Machie Learig based QC techique for Idustrial Pritig Azhar ussai College of Iformatio ad Commuicatio Egieerig, arbi Egieerig Uiversity, 5000, arbi, Chia egrazr@hrbeu.edu.c

More information

Performance Plus Software Parameter Definitions

Performance 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 information

VALIDATING 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 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 information

Heuristic Approaches for Solving the Multidimensional Knapsack Problem (MKP)

Heuristic Approaches for Solving the Multidimensional Knapsack Problem (MKP) Heuristic Approaches for Solvig the Multidimesioal Kapsack Problem (MKP) R. PARRA-HERNANDEZ N. DIMOPOULOS Departmet of Electrical ad Computer Eg. Uiversity of Victoria Victoria, B.C. CANADA Abstract: -

More information

DATA MINING II - 1DL460

DATA 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 information

Alpha Individual Solutions MAΘ National Convention 2013

Alpha Individual Solutions MAΘ National Convention 2013 Alpha Idividual Solutios MAΘ Natioal Covetio 0 Aswers:. D. A. C 4. D 5. C 6. B 7. A 8. C 9. D 0. B. B. A. D 4. C 5. A 6. C 7. B 8. A 9. A 0. C. E. B. D 4. C 5. A 6. D 7. B 8. C 9. D 0. B TB. 570 TB. 5

More information

EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL

EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL Iteratioal Joural of Iformatio Techology ad Kowledge Maagemet July-December 2012, Volume 5, No. 2, pp. 371-375 EMPIRICAL ANALYSIS OF FAULT PREDICATION TECHNIQUES FOR IMPROVING SOFTWARE PROCESS CONTROL

More information

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c

Pruning and Summarizing the Discovered Time Series Association Rules from Mechanical Sensor Data Qing YANG1,a,*, Shao-Yu WANG1,b, Ting-Ting ZHANG2,c Advaces i Egieerig Research (AER), volume 131 3rd Aual Iteratioal Coferece o Electroics, Electrical Egieerig ad Iformatio Sciece (EEEIS 2017) Pruig ad Summarizig the Discovered Time Series Associatio Rules

More information

ON THE QUALITY OF AUTOMATIC RELATIVE ORIENTATION PROCEDURES

ON 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 information

Python Programming: An Introduction to Computer Science

Python 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 information

Neural Networks A Model of Boolean Functions

Neural Networks A Model of Boolean Functions Neural Networks A Model of Boolea Fuctios Berd Steibach, Roma Kohut Freiberg Uiversity of Miig ad Techology Istitute of Computer Sciece D-09596 Freiberg, Germay e-mails: steib@iformatik.tu-freiberg.de

More information

Text Feature Selection based on Feature Dispersion Degree and Feature Concentration Degree

Text 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 information

Real-time Path Prediction and Grid-based Path Modeling Method Using GPS

Real-time Path Prediction and Grid-based Path Modeling Method Using GPS Iteratioal Joural of Applied Egieerig Research ISSN 0973-4562 Volume 12, Number 20 (2017) pp. 9997-10001 Research Idia Publicatios. http://www.ripublicatio.com Real-time Path Predictio ad Grid-based Path

More information

Hashing Functions Performance in Packet Classification

Hashing Functions Performance in Packet Classification Hashig Fuctios Performace i Packet Classificatio Mahmood Ahmadi ad Stepha Wog Computer Egieerig Laboratory Faculty of Electrical Egieerig, Mathematics ad Computer Sciece Delft Uiversity of Techology {mahmadi,

More information

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base

Comparison of classification algorithms in the task of object recognition on radar images of the MSTAR base Compariso of classificatio algorithms i the task of object recogitio o radar images of the MSTAR base A.A. Borodiov 1, V.V. Myasikov 1,2 1 Samara Natioal Research Uiversity, 34 Moskovskoe Shosse, 443086,

More information

c-dominating Sets for Families of Graphs

c-dominating Sets for Families of Graphs c-domiatig Sets for Families of Graphs Kelsie Syder Mathematics Uiversity of Mary Washigto April 6, 011 1 Abstract The topic of domiatio i graphs has a rich history, begiig with chess ethusiasts i the

More information

Efficient Eye Location for Biomedical Imaging using Two-level Classifier Scheme

Efficient 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 information