A Novel Fuzzy Classifier Using Fuzzy LVQ to Recognize Online Persian Handwriting

Size: px
Start display at page:

Download "A Novel Fuzzy Classifier Using Fuzzy LVQ to Recognize Online Persian Handwriting"

Transcription

1 A Novel Fuzzy Classfer Usng Fuzzy LVQ to Recognze Onlne Persan Handwrtng M. Soleyan Baghshah S. Bagher Shourak S. Kasae Departent of Coputer Engneerng, Sharf Unversty of Technology, Tehran, Iran Abstract Fuzzy logc s a powerful tool to represent precse and rregular patterns. Ths paper presents a novel fuzzy approach for recognzng onlne Persan (Fars) handwrtng. In ths approach, a fuzzy classfer s ntroduced that uses a cobnaton of the fuzzy LVQ learnng odel and the expert knowledge. Ths ethod apples an FLVQ network to dstngush between the slar tokens that appear at the end of the strokes. For other tokens, fuzzy lngustc ters are used to descrbe ther features. The purposed ethod was run on a database of Persan solated handwrtten characters and acheved a hgh recognton rate copared to other avalable approaches. Keywords: Persan Handwrtng, Fuzzy Rule-Based, FLVQ, Recognton.. Introducton The Persan character set (along wth slar character sets) are used by ore than 30% of the world's populaton and serve n the wrtng of any wdespread languages such as Arabc and Aurdo []. In contrast to the advances n the onlne Latn and Chnese handwrtng recognton, relatvely few studes have been devoted to the Persan handwrtng recognton. Ths s due, n part, to the cursve nature of the task. In the last two decades a nuber of onlne handwrtng recognton systes have been developed. Most of the eploy stochastc ethods (lke hdden Markov odels), connectve learnng-based ethods (lke neural networks), odel atchng, and structural/syntactcal technques. The ajor drawback of all prevous ethods s ther hgh-dependablty on sall wrtng perturbatons that tends to precse recognton results when workng wth very vast varety of wrtng styles. Consderng the ltaton and drawbacks of the exstng approaches, we defne two ajor characterstcs that a handwrtng recognton syste should possess: fast response and flexblty. To acheve these requreents, the knowledge base ust be sall but robust [2]. Changes n style or orentaton should be handled by the flexble prototypes that contan wdely vald descrptons of character nforaton. In ths paper, n order to overcoe the coplextes of Persan handwrtng and to acheve the above requreents, a practcal fuzzy approach s proposed. In ths approach, the onlne stroke s frst preprocessed and segented nto tokens and the features of each token are extracted. A novel fuzzy classfer s then used to recognze the characters. In ths classfer, the end token of the strokes are classfed by usng the fuzzy learnng vector quantzaton (FLVQ) algorth and the other tokens are characterzed by usng fuzzy lngustc ters that descrbe sple representatve features. The knowledge base of ths classfer s n the for of fuzzy rules that are extracted by an expert. The rest of ths paper s organzed as follows: Secton 2 presents a bref ntroducton to Persan handwrtng and prevous works. Secton 3 explans the preprocessng and segentaton processes. Secton 4 states the feature extracton process. In secton 5 a novel fuzzy classfer s ntroduced and the recognton algorth s presented. The experental results are gven n Secton 6, and the last secton presents the conclusons and future works. 2. Persan Handwrtng and Prevous Works Persan characters are n cursve scrpt. It coprses 32 an characters and s wrtten fro rght to left. Characters have up to four dfferent fors, dependng on ther poston wthn a word (the begnnng, ddle, end and solated fors). Fgure presents saples of dfferent characters and ther fors. Also, the characters ay be wrtten n dfferent fors based on personal handwrtng styles. Persan characters have one an stroke and ost of the have

2 also one to three secondary strokes. Usually the an stroke s wrtten frst and then secondary strokes are wrtten. In Fgure 2, strokes nuber, 3, and 6 are the an strokes. The secondary strokes ay be n the for of dots, "sarkesh", and "daste". There are soe works devoted to recognton of onlne Persan/Arabc handwrtng characters. Al- Ea used a structural analyss ethod for selectng features of Arabc characters and a decson tree for the classfcaton [3]. Al ntroduced a Neuro-Fuzzy approach n [4] and a teplate atchng and dynac prograng approach n [5]. In [6] cobnaton of pruned Kohonen aps and n [7] cobnaton of SOM and Perceptron s used to recognze onlne Arabc handwrtten characters. A Persan handwrtng recognton syste s also ntroduced n [8] whch s based on representng nput data and character patterns usng lngustc ters and coparsons of these ters. Recently we ntroduced a novel fuzzy approach n [9] that uses a fuzzy rule-based approach, where the rules are fored only by an expert. In ths work, we have extended that approach to use the FLVQ learnng odel to prove the recognton results. Snce none of the above approaches were appled on the sae data set, and any of the were not tested on ndependent and extensve test sets, t s not a far atch to copare how these approaches dd aganst each other. flterng steps. Soothng averages the coordnates of a pont usng ts neghborng pxels, and the flterng reduces the nuber of ponts by elnatng very close ponts. Ths flterng technque forces a nu dstance between consecutve ponts. Stroke7 Stroke6 Stroke5 Stroke3 Stroke4 Stroke2 Stroke Fgure 2. Soe saple strokes. After preprocessng our nternal segentaton ethod s appled. It as at separatng each stroke nto a set of sall parts called tokens. In Fgure 4, each star ark shows the end pont of a token. These tokens can be lnes, arcs or loops. Soe features are used to descrbe the propertes of each token. To start the task, we frst convert the lst of (x, y) coordnates of nput ponts nto a set of vectors, each startng fro one of the ponts and endng at the next pont. Fgure 3 shows vectors that lnk the nput ponts. P5 V3 V2 P4 P2 V V0 P P0 Fgure 3. Vectors between ponts. The angle between two consecutve vectors V and V + s noted as A. The sgn of A s consdered as the curvature sde at pont P. For a sequence of ponts, the total curvature sde s the sgn of the su of angles along the sequence. Fgure. Saple of Persan prnted characters and ther fors n dfferent postons wthn the word. 3. Preprocessng and Segentaton In ths secton, we present the proposed preprocessng and segentaton ethods. The nput data are acqured n the for of a lst of (x, y) coordnates. Frst, the nput data are externally separated nto strokes by the help of pen-ups. In Fgure 2, soe saple strokes are shown. Then, the nose reducton process s appled through soothng and Input : V.. V A = V V + + n V, ( V + ( V + ) <= 80 ) >= 80 otherwse () At ths stage, any pont n whch A exceeds a certan threshold, T, can be a canddate for the end of token. Also, when A exceeds another threshold T 2 (less than T ) and curvature sde at pont P s opposed to the total curvature sde, the P s a segentaton canddate. So, we save ths pont and start the process fro the next pont. To fnalze the segentaton task, a loop detecton

3 ethod s used to fnd the loops and deletes addtonal canddate segentaton ponts that locate on the. It also defnes new segentaton ponts. Two procedures are consdered for ths purpose; one that detects closed loops and the other that detects open loops that appear at the start of the strokes. To detect closed loops, the trajectory of the pen oveent s saved. If ths trajectory ntersects tself, and the ponts between the prevous and current vst of the pont construct a crcle lke curve, a closed loop s detected and two new segentaton ponts add at the start and end of ths loop. Open loops are always located at the start of the stroke. To fnd the, we start fro the begnnng of the stroke and for each pont of t copute the dstance between ths pont and the start pont of that stroke and save these values n an array. The frst local na n ths array, f exsts any, s selected. If ths value s sall relatve to the length of the curve up to correspondng pont, and the curve s crcle lke, ths pont s consdered as the end of the open loop. Otherwse, we contnue the process fro the next pont. As descrbed above, n ths work n contrast to the other works [2, 8, 9], a loop detecton process s used to coplete the segentaton process and to ake the resultng tokens ore eanngful. Fgure 4 shows soe segentaton saples. Fgure 4. Saples of segentaton. The end pont of each token s shown wth a ark. 4. Feature Extracton After the nput data s segented, each token s descrbed usng a set of features. These are defned below. ) Start2End_Drecton: The drecton of the straght lne that starts fro the frst pont of the token and end at the last pont. Φ = tan (( Yend Ystatrt ) /( X end X start )) (2) 2) Start2COG_Drecton: The drecton of the straght lne that starts fro the frst pont of the token and ends at the center of gravty of the token. 3) End2COG_Drecton: The drecton of the straght lne that starts fro the last pont of the token and ends at the center of gravty of the token. 4) Straghtness: A new straghtness easure that perfors uch better than the easure ntroduced n [0, ]. Ths easure s the angle between the Start2COG_Drecton and End2COG_Drecton. Value of ths easure for a drect lne s 80 and for a crcle s zero. 5) Horzontal_Moton: The relatve horzontal oton n the wrtten token profle: xax xn HM = (3) N x = + x 6) Vertcal_Moton: The relatve vertcal oton n the wrtten token profle: yax yn VM = (4) N y = + y 7) Curvature_Sde: The drecton of concavty coputed by: Curvature Sde = Sgn( N = A ) (5) where A s defned n (). If ths value s negatve, the curvature sde s assued to be clockwse, and otherwse t s counter clockwse. These two ters are referred to as CWC and CCWC through the paper. 7) Aspect Rato: Is coputed by dvdng the vertcal sze of the token by ts horzontal sze as: y ax y n Aspect Rato = (6) x x ax n 5. Fuzzy Classfer Usng FLVQ The next step after the feature extracton process s to create a classfer. Ths classfer ust contan one or several rules for each character to dentfy the an stroke of t. In ths secton we frst explan our fuzzy classfer and then the recognton algorth s ntroduced to classfy the nputs. 5.. Fuzzy Classfer Foraton In ths secton, we splt the tokens nto two groups: The end tokens and the non end tokens. The tokens that appear at the end of the strokes are end tokens and the other tokens are non end tokens. If a stroke contans only one token, t s trval that ths token s an end token. Snce the classfcaton of end tokens s a cubersoe task (as the expert has not already found

4 approprate set of rules), n ths paper, we use the FLVQ learnng odel to autoatcally classfy the end tokens. The Non end tokens are characterzed by the expert and for descrbng the, the expert uses lngustc ters. In ths subsecton, we frst ntroduce the FLVQ algorth and then we descrbe the proposed rule-based creaton ethod. 5.. FLVQ Algorth Here, we descrbe the FLVQ algorth ntroduced n U = µ k k = N, = c be the fuzzy X = xk k = N, [2]. Let { } c-partton of tranng patterns { } and V = { = c} be the neuron's paraetrc vectors. Frst, assue that the nuber of copetng neurons c s equal to the nuber of pattern classes. The goal of the FLVQ algorth s to nze the below objectve functon: Q N ( U, V ) = µ c k = = Subjected to the constrants: c = µ k = ; k and µ k [ t ] D (7) k 2 k k [0,]; k, (8) Where Dk = xk s the dstance between neuron and tranng pattern k, s a fuzzness paraeter greater than, and t k {0, } s the target class ebershp value of neuron for nput pattern k. The FLVQ learnng law s: ( t + ) = ( t) + α( t)[ t k µ k ][ xk ( t)]; And the ebershp updatng rule s: = c µ k l= D ( D k kl ) (9) (0) The extenson of above entoned learnng technque s llustrated n Fgure 5. It can be seen that by-passng the MIN layer results n the algorth descrbed above. Recall that the nuber of copetng neurons has been assued to be equal to the nuber of pattern classes. Such assupton can be relaxed by ntroducng the MIN layer to handle ultple neurons per pattern class network desgn. Consequently, the neuron underutlzaton proble n LVQ s resolved. Correspondng to the general network archtecture, the learnng algorth s odfed as follows. Frst, the dstance coputaton s redefned as: D k = n x j S k j () Where S s the ndex set of the copetng neurons for pattern class I, and j s jth copetng neuron's paraetrc vector for pattern class. Thus, the FLVQ learnng law wll be: ( t + ) = ( t) + α( t) I j [ tk µ k ][ xk Where: f xk j I j = 0 otherwse ( t)]; l S (2) k l Fgure 5.Typcal FLVQ network [2]. x (3) Here, we use ths FLVQ network to classfy the end tokens. The nput pattern to ths network s a vector of features ntroduced n Secton 4. The nuber of clusters s fxed to 0 (nuber of dfferent types of end tokens). Fgure 6 shows the ebers of dfferent clusters. By usng ths network, we fnd ebershps of the nput to the clusters. The dentfers of these clusters are used n the fnal rules Fuzzy Rule-Based Creaton The knowledge base used n ths paper, s n the for of fuzzy rules whch found by an expert. To overcoe the probles exstng n ult-wrter envronents, the defned prototypes ust antan the syntax of the rules as short as possble to descrbe a ulttude of character styles and sultaneously to process enough seantc nforaton to dstngush the sybols easly

5 []. To defne a rule, at frst, soe tokens are chosen to descrbe the an stroke of the character. The end token of the stroke s dentfed only by the dentfer of the related cluster n the FLVQ network. For non end tokens, soe features are selected by the expert to descrbe the. The Expert uses Straghtness, End2COG_Drecton, and Curvature_Sde features to descrbe crcle-lke curves and uses Straghtness, Start2End_Drecton, and Curvature_Sde features, for other types of curves. Then, for each feature, an approprate lngustc ter s chosen. The ebershps of soe of these lngustc ters are shown n Fgures 7 and 8. The lngustc ters n Fgure 8 are the abbrevatons of the eght drectons: East, North East, North, North West, West, South West, South, South East, and East. ١ ٢ ٣ ٤ ٥ ٦ ٧ ٨ ٩.0 E 0 NE 45 N NW W SW S SE E Fgure 8. Fuzzy sets of the Drecton varables. Soetes ore than one lngustc ter s needed to descrbe a feature of a non end token or several ways are exst to segent a stroke nto tokens. In these cases ore than one rule s used. Table presents three saple rules whch are used to defne three characters shown n Fgure 4. Each row of ths table s related to one of the tokens of the character. Table. Saples of rule defnton. Cluster Straghtness End2COG Start2COG Curvature Drecton Drecton Sde 'Seen' Secrcle W CWC Secrcle W CWC 'Eyn' Secrcle S CCWC 'Sad' Crcle NE Arc W Ф ١٠ 5.2. Proposed Recognton Algorth Fgure 6. The ebers of dfferent clusters. The end pont of each non end token s shown wth a ark. For the characters that have ore than one token, the end token s consdered. Crcle SeCrcle Arc Straghtness Fgure 7. Fuzzy sets of the type varable. In Secton 5., we descrbed the rule-based foraton. Ths subsecton presents the purposed classfcaton algorth that deternes the correspondng class usng the extracted tokens. The aount of slarty between the nput token and a token of a rule s coputed as follows. If a rule token has a cluster nuber, we use FLVQ network and fnd the ebershp of the nput token to the correspondng cluster usng (0); If ths value s less than 0., we replace t by 0. Otherwse, we consder the fuzzy sets correspondng to the lngustc ters n the rule and fnd the nu of the ebershp values of the nput token features to the related fuzzy sets. Snce there ght be extra short tokens n the nput (whch do not atch wth any tokens), to copute the

6 slarty between an nput sequence of tokens wth a rule, we fnd, f possble, the nput tokens that are ost slar to the rule tokens. The other of these tokens ust also be correspondng to the order of the rule tokens. If ths task s not possble, the total slarty value s set to zero, otherwse t s set to the nu of the slarty of the acheved nput tokens to the correspondng rule tokens. Fnally, the total slarty value s consdered as a postve easure (PM) and the su of the relatve lengths of the unused nput tokens s consdered as a negatve easure (NM). To recognze the class of the nput, we fnd the rule that axzes ths equaton: O = PM α NM Where α s a constant coeffcent. 6. Experental Results (4) In ths work, we use the relatvely coplete database ntroduced n [3] that contans the solated characters wrtten by 28 persons. As there s no general bench ark for onlne handwrtng recognton algorth n Persan, we could not copare our result wth other works quanttatvely. The recognton rate of the purposed ethod on ths database s near 88% and proves to about 95% when tunng the paraeters for a query wrter. It ust be noted that the perforance of the proposed algorth are ore accurate when copared wth the ost recent results reported n [8, 9]. In addton, the coputatonal cost of our approach s also uch less than that of the approach ntroduced n [8]; and thus can be used n onlne envronents. The nuber of the rules used n ths test s Concluson and Future Drectons There are very few avalable approaches for recognton of onlne Persan handwrtng. In ths paper, a novel ethod whch s based on representaton of nput tokens wth very sple features, usng cobnaton of a fuzzy rule-based and the FLVQ network s presented and a fuzzy nference s also ntroduced. As opposed to other avalable ethods, an portant advantage of the purposed ethod s ts ablty to segent the strokes nto eanngful tokens. As presented n Secton 6, ths approach has been qute successful n acceptng a wde range of varatons for each letter and has shown prosng results. To follow ths research, we are now workng on recognton of the secondary strokes, to further prove the recognton results. Acknowledgeent Ths work was n part supported by a grant fro ITRC. References [] I. S. I. Abuhaba, M. J. J. Holt, S. Datta, Recognton of Off-Lne Cursve Handwrtng, Coputer Vson and Iage Processng, Vol. 7, No., pp. 9-38, 998. [2] A. Malavya, R. Klette, "A Fuzzy Syntactc Method for On-lne Handwrtng Recognton", Lecture notes n Coputer Scence 2, Sprnger, Advances n Structural and Syntactcal Pattern recognton, SSPR'96, pp , 996. [3] Al-Ea, S. and Usher, M. On-Lne Recognton of Handwrtten Arabc Characters, IEEE Transactons on Pattern Analyss and Machne Intellgence, Vol. 2, No. 7, July 990. pp [4] A. M. Al, A Neuro-Fuzzy Approach to Recognze Arabc Handwrtten Characters, IEEE Internatonal Conference on Neural Network, vol. 3, pp , 997. [5] A. Al, O. Ghorbel, The Analyss of Error n an On- Lne Recognton Syste of Arabc Handwrtten Characters, Proceedngs of ICDAR 995, pp , 4-6 August 995, Montreal, Canada. [6] N. Mezghan, M. Cheret, "Cobnaton of Pruned Kohenon Maps for On-lne Arabc Character Recognton", Proceedngs of the Seventh Internatonal Conf. on Docuent Analyss and Recognton (ICDAR'03), pp , Ednburgh, Scotland, August [7] T. Klassen, "Towards Neural Network Recognton of Handwrtten Arabc Letters", MS. Thess, Dalhouse Unversty, Halfax, Nova Scota, 200. [8] R. Halavat, S. B. Sourak, M. Soleyan, Persan Onlne Handwrtng Recognton Usng Fuzzy Modelng, to be publshed n IFSA 05, Bejng, Chna, July [9] M. Soleyan Baghshah, S. Bagher Sourak, S. Kasae, A Novel Fuzzy Approach to Recognton of Onlne Persan Handwrtng, to be publshed n ISDA 05, Wroclaw, Poland, Septeber [0] Roesh Ranawana, Vasle Palade, G.E.M.D.C. Bandara, "An Effcent Fuzzy Method for Handwrtten Character Recognton", Proceedngs of KES2004, pp , Wellngton, New Zealand, Septeber [] A. Malavya, L. Peters, R. Caposano, "A Fuzzy Onlne Handwrtng Recognton Syste : FOHRES", Second nternatonal conference on Fuzzy Theory and Technology, Durha, NC, Oct.3-6, 993. [2] F. L. Chung, T. Lee, "A Fuzzy Learnng Model for Mebershp Functon Estaton and Pattern Classfcaton", IEEE Internatonal Conference on Fuzzy Systes, :426-43, 994. [3] S. M. Razav, E. Kabr, "A Data base for Onlne Persan Handwrtten recognton", 6 th Conference on Intellgent Systes, Keran, Iran, 2004.

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram Shape Representaton Robust to the Sketchng Order Usng Dstance Map and Drecton Hstogram Department of Computer Scence Yonse Unversty Kwon Yun CONTENTS Revew Topc Proposed Method System Overvew Sketch Normalzaton

More information

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms

Generating Fuzzy Term Sets for Software Project Attributes using and Real Coded Genetic Algorithms Generatng Fuzzy Ter Sets for Software Proect Attrbutes usng Fuzzy C-Means C and Real Coded Genetc Algorths Al Idr, Ph.D., ENSIAS, Rabat Alan Abran, Ph.D., ETS, Montreal Azeddne Zah, FST, Fes Internatonal

More information

Handwritten English Character Recognition Using Logistic Regression and Neural Network

Handwritten English Character Recognition Using Logistic Regression and Neural Network Handwrtten Englsh Character Recognton Usng Logstc Regresson and Neural Network Tapan Kuar Hazra 1, Rajdeep Sarkar 2, Ankt Kuar 3 1 Departent of Inforaton Technology, Insttute of Engneerng and Manageent,

More information

Optimization Methods: Integer Programming Integer Linear Programming 1. Module 7 Lecture Notes 1. Integer Linear Programming

Optimization Methods: Integer Programming Integer Linear Programming 1. Module 7 Lecture Notes 1. Integer Linear Programming Optzaton Methods: Integer Prograng Integer Lnear Prograng Module Lecture Notes Integer Lnear Prograng Introducton In all the prevous lectures n lnear prograng dscussed so far, the desgn varables consdered

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Human Face Recognition Using Radial Basis Function Neural Network

Human Face Recognition Using Radial Basis Function Neural Network Huan Face Recognton Usng Radal Bass Functon eural etwor Javad Haddadna Ph.D Student Departent of Electrcal and Engneerng Arabr Unversty of Technology Hafez Avenue, Tehran, Iran, 594 E-al: H743970@cc.au.ac.r

More information

What is Object Detection? Face Detection using AdaBoost. Detection as Classification. Principle of Boosting (Schapire 90)

What is Object Detection? Face Detection using AdaBoost. Detection as Classification. Principle of Boosting (Schapire 90) CIS 5543 Coputer Vson Object Detecton What s Object Detecton? Locate an object n an nput age Habn Lng Extensons Vola & Jones, 2004 Dalal & Trggs, 2005 one or ultple objects Object segentaton Object detecton

More information

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation College of Engneerng and Coputer Scence Mechancal Engneerng Departent Mechancal Engneerng 309 Nuercal Analyss of Engneerng Systes Sprng 04 Nuber: 537 Instructor: Larry Caretto Solutons to Prograng Assgnent

More information

Comparative Study between different Eigenspace-based Approaches for Face Recognition

Comparative Study between different Eigenspace-based Approaches for Face Recognition Coparatve Study between dfferent Egenspace-based Approaches for Face Recognton Pablo Navarrete and Javer Ruz-del-Solar Departent of Electrcal Engneerng, Unversdad de Chle, CHILE Eal: {pnavarre, jruzd}@cec.uchle.cl

More information

Nighttime Motion Vehicle Detection Based on MILBoost

Nighttime Motion Vehicle Detection Based on MILBoost Sensors & Transducers 204 by IFSA Publshng, S L http://wwwsensorsportalco Nghtte Moton Vehcle Detecton Based on MILBoost Zhu Shao-Png,, 2 Fan Xao-Png Departent of Inforaton Manageent, Hunan Unversty of

More information

A Semantic Model for Video Based Face Recognition

A Semantic Model for Video Based Face Recognition Proceedng of the IEEE Internatonal Conference on Inforaton and Autoaton Ynchuan, Chna, August 2013 A Seantc Model for Vdeo Based Face Recognton Dhong Gong, Ka Zhu, Zhfeng L, and Yu Qao Shenzhen Key Lab

More information

Research on action recognition method under mobile phone visual sensor Wang Wenbin 1, Chen Ketang 2, Chen Liangliang 3

Research on action recognition method under mobile phone visual sensor Wang Wenbin 1, Chen Ketang 2, Chen Liangliang 3 Internatonal Conference on Autoaton, Mechancal Control and Coputatonal Engneerng (AMCCE 05) Research on acton recognton ethod under oble phone vsual sensor Wang Wenbn, Chen Ketang, Chen Langlang 3 Qongzhou

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

Outline. Third Programming Project Two-Dimensional Arrays. Files You Can Download. Exercise 8 Linear Regression. General Regression

Outline. Third Programming Project Two-Dimensional Arrays. Files You Can Download. Exercise 8 Linear Regression. General Regression Project 3 Two-densonal arras Ma 9, 6 Thrd Prograng Project Two-Densonal Arras Larr Caretto Coputer Scence 6 Coputng n Engneerng and Scence Ma 9, 6 Outlne Quz three on Thursda for full lab perod See saple

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

A system based on a modified version of the FCM algorithm for profiling Web users from access log

A system based on a modified version of the FCM algorithm for profiling Web users from access log A syste based on a odfed verson of the FCM algorth for proflng Web users fro access log Paolo Corsn, Laura De Dosso, Beatrce Lazzern, Francesco Marcellon Dpartento d Ingegnera dell Inforazone va Dotsalv,

More information

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges

More information

Performance Analysis of Coiflet Wavelet and Moment Invariant Feature Extraction for CT Image Classification using SVM

Performance Analysis of Coiflet Wavelet and Moment Invariant Feature Extraction for CT Image Classification using SVM Perforance Analyss of Coflet Wavelet and Moent Invarant Feature Extracton for CT Iage Classfcaton usng SVM N. T. Renukadev, Assstant Professor, Dept. of CT-UG, Kongu Engneerng College, Perundura Dr. P.

More information

On-line Scheduling Algorithm with Precedence Constraint in Embeded Real-time System

On-line Scheduling Algorithm with Precedence Constraint in Embeded Real-time System 00 rd Internatonal Conference on Coputer and Electrcal Engneerng (ICCEE 00 IPCSIT vol (0 (0 IACSIT Press, Sngapore DOI: 077/IPCSIT0VNo80 On-lne Schedulng Algorth wth Precedence Constrant n Ebeded Real-te

More information

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data Malaysan Journal of Mathematcal Scences 11(S) Aprl : 35 46 (2017) Specal Issue: The 2nd Internatonal Conference and Workshop on Mathematcal Analyss (ICWOMA 2016) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES

More information

A Cluster Tree Method For Text Categorization

A Cluster Tree Method For Text Categorization Avalable onlne at www.scencedrect.co Proceda Engneerng 5 (20) 3785 3790 Advanced n Control Engneerngand Inforaton Scence A Cluster Tree Meod For Text Categorzaton Zhaoca Sun *, Yunng Ye, Weru Deng, Zhexue

More information

Aircraft Engine Gas Path Fault Diagnosis Based on Fuzzy Inference

Aircraft Engine Gas Path Fault Diagnosis Based on Fuzzy Inference 202 Internatonal Conference on Industral and Intellgent Inforaton (ICIII 202) IPCSIT vol.3 (202) (202) IACSIT Press, Sngapore Arcraft Engne Gas Path Fault Dagnoss Based on Fuzzy Inference Changzheng L,

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

Face Detection and Tracking in Video Sequence using Fuzzy Geometric Face Model and Mean Shift

Face Detection and Tracking in Video Sequence using Fuzzy Geometric Face Model and Mean Shift Internatonal Journal of Advanced Trends n Coputer Scence and Engneerng, Vol., No.1, Pages : 41-46 (013) Specal Issue of ICACSE 013 - Held on 7-8 January, 013 n Lords Insttute of Engneerng and Technology,

More information

Prediction of Dumping a Product in Textile Industry

Prediction of Dumping a Product in Textile Industry Int. J. Advanced Networkng and Applcatons Volue: 05 Issue: 03 Pages:957-96 (03) IN : 0975-090 957 Predcton of upng a Product n Textle Industry.V.. GANGA EVI Professor n MCA K..R.M. College of Engneerng

More information

Pattern Classification of Back-Propagation Algorithm Using Exclusive Connecting Network

Pattern Classification of Back-Propagation Algorithm Using Exclusive Connecting Network World Acade of Scence, Engneerng and Technolog 36 7 Pattern Classfcaton of Bac-Propagaton Algorth Usng Eclusve Connectng Networ Insung Jung, and G-Na Wang Abstract The obectve of ths paper s to a desgn

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Introduction. Leslie Lamports Time, Clocks & the Ordering of Events in a Distributed System. Overview. Introduction Concepts: Time

Introduction. Leslie Lamports Time, Clocks & the Ordering of Events in a Distributed System. Overview. Introduction Concepts: Time Lesle Laports e, locks & the Orderng of Events n a Dstrbuted Syste Joseph Sprng Departent of oputer Scence Dstrbuted Systes and Securty Overvew Introducton he artal Orderng Logcal locks Orderng the Events

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information

User Behavior Recognition based on Clustering for the Smart Home

User Behavior Recognition based on Clustering for the Smart Home 3rd WSEAS Internatonal Conference on REMOTE SENSING, Vence, Italy, Noveber 2-23, 2007 52 User Behavor Recognton based on Clusterng for the Sart Hoe WOOYONG CHUNG, JAEHUN LEE, SUKHYUN YUN, SOOHAN KIM* AND

More information

3D vector computer graphics

3D vector computer graphics 3D vector computer graphcs Paolo Varagnolo: freelance engneer Padova Aprl 2016 Prvate Practce ----------------------------------- 1. Introducton Vector 3D model representaton n computer graphcs requres

More information

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

A Novel System for Document Classification Using Genetic Programming

A Novel System for Document Classification Using Genetic Programming Journal of Advances n Inforaton Technology Vol. 6, No. 4, Noveber 2015 A Novel Syste for Docuent Classfcaton Usng Genetc Prograng Saad M. Darwsh, Adel A. EL-Zoghab, and Doaa B. Ebad Insttute of Graduate

More information

Color Image Segmentation Based on Adaptive Local Thresholds

Color Image Segmentation Based on Adaptive Local Thresholds Color Iage Segentaton Based on Adaptve Local Thresholds ETY NAVON, OFE MILLE *, AMI AVEBUCH School of Coputer Scence Tel-Avv Unversty, Tel-Avv, 69978, Israel E-Mal * : llero@post.tau.ac.l Fax nuber: 97-3-916084

More information

Joint Registration and Active Contour Segmentation for Object Tracking

Joint Registration and Active Contour Segmentation for Object Tracking Jont Regstraton and Actve Contour Segentaton for Object Trackng Jfeng Nng a,b, Le Zhang b,1, Meber, IEEE, Davd Zhang b, Fellow, IEEE and We Yu a a College of Inforaton Engneerng, Northwest A&F Unversty,

More information

Generalized Spatial Kernel based Fuzzy C-Means Clustering Algorithm for Image Segmentation

Generalized Spatial Kernel based Fuzzy C-Means Clustering Algorithm for Image Segmentation Internatonal Journal of Scence and Research (IJSR, Inda Onlne ISSN: 39-7064 Generalzed Spatal Kernel based Fuzzy -Means lusterng Algorth for Iage Segentaton Pallav Thakur, helpa Lnga Departent of Inforaton

More information

Lecture 5: Multilayer Perceptrons

Lecture 5: Multilayer Perceptrons Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented

More information

Optimally Combining Positive and Negative Features for Text Categorization

Optimally Combining Positive and Negative Features for Text Categorization Optally Cobnng Postve and Negatve Features for Text Categorzaton Zhaohu Zheng ZZHENG3@CEDAR.BUFFALO.EDU Rohn Srhar ROHINI@CEDAR.BUFFALO.EDU CEDAR, Dept. of Coputer Scence and Engneerng, State Unversty

More information

Realistic 3D Face Modeling by Fusing Multiple 2D Images

Realistic 3D Face Modeling by Fusing Multiple 2D Images Realstc 3D Face Modelng by Fusng Multple D ages Changhu Wang EES Departent, Unversty of Scence and echnology of Chna, wch@ustc.edu Shucheng Yan, Hongjang Zhang, Weyng Ma Mcrosoft Research Asa, Bejng,.R.

More information

Merging Results by Using Predicted Retrieval Effectiveness

Merging Results by Using Predicted Retrieval Effectiveness Mergng Results by Usng Predcted Retreval Effectveness Introducton Wen-Cheng Ln and Hsn-Hs Chen Departent of Coputer Scence and Inforaton Engneerng Natonal Tawan Unversty Tape, TAIWAN densln@nlg.cse.ntu.edu.tw;

More information

A new Fuzzy Noise-rejection Data Partitioning Algorithm with Revised Mahalanobis Distance

A new Fuzzy Noise-rejection Data Partitioning Algorithm with Revised Mahalanobis Distance A new Fuzzy ose-reecton Data Parttonng Algorth wth Revsed Mahalanobs Dstance M.H. Fazel Zarand, Mlad Avazbeg I.B. Tursen Departent of Industral Engneerng, Arabr Unversty of Technology Tehran, Iran Departent

More information

Relevance Feedback in Content-based 3D Object Retrieval A Comparative Study

Relevance Feedback in Content-based 3D Object Retrieval A Comparative Study 753 Coputer-Aded Desgn and Applcatons 008 CAD Solutons, LLC http://www.cadanda.co Relevance Feedback n Content-based 3D Object Retreval A Coparatve Study Panagots Papadaks,, Ioanns Pratkaks, Theodore Trafals

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Key-Words: - Under sear Hydrothermal vent image; grey; blue chroma; OTSU; FCM

Key-Words: - Under sear Hydrothermal vent image; grey; blue chroma; OTSU; FCM A Fast and Effectve Segentaton Algorth for Undersea Hydrotheral Vent Iage FUYUAN PENG 1 QIAN XIA 1 GUOHUA XU 2 XI YU 1 LIN LUO 1 Electronc Inforaton Engneerng Departent of Huazhong Unversty of Scence and

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

A Bayesian Mixture Model for Multi-view Face Alignment

A Bayesian Mixture Model for Multi-view Face Alignment A Bayesan Mxture Model for Mult-vew Face Algnent Y Zhou, We Zhang, Xaoou Tang, and Harry Shu Mcrosoft Research Asa Bejng, P. R. Chna {t-yzhou, xtang, hshu}@crosoft.co DCST, Tsnghua Unversty Bejng, P. R.

More information

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

More information

Machine Learning 9. week

Machine Learning 9. week Machne Learnng 9. week Mappng Concept Radal Bass Functons (RBF) RBF Networks 1 Mappng It s probably the best scenaro for the classfcaton of two dataset s to separate them lnearly. As you see n the below

More information

Multiple Instance Learning via Multiple Kernel Learning *

Multiple Instance Learning via Multiple Kernel Learning * The Nnth nternatonal Syposu on Operatons Research and ts Applcatons (SORA 10) Chengdu-Juzhagou, Chna, August 19 23, 2010 Copyrght 2010 ORSC & APORC, pp. 160 167 ultple nstance Learnng va ultple Kernel

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

The Research of Support Vector Machine in Agricultural Data Classification

The Research of Support Vector Machine in Agricultural Data Classification The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou

More information

A New Scheduling Algorithm for Servers

A New Scheduling Algorithm for Servers A New Schedulng Algorth for Servers Nann Yao, Wenbn Yao, Shaobn Ca, and Jun N College of Coputer Scence and Technology, Harbn Engneerng Unversty, Harbn, Chna {yaonann, yaowenbn, cashaobn, nun}@hrbeu.edu.cn

More information

CLASSIFICATION OF ULTRASONIC SIGNALS

CLASSIFICATION OF ULTRASONIC SIGNALS The 8 th Internatonal Conference of the Slovenan Socety for Non-Destructve Testng»Applcaton of Contemporary Non-Destructve Testng n Engneerng«September -3, 5, Portorož, Slovena, pp. 7-33 CLASSIFICATION

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

Using Gini-Index for Feature Selection in Text Categorization

Using Gini-Index for Feature Selection in Text Categorization 3rd Internatonal Conference on Inforaton, Busness and Educaton Technology (ICIBET 014) Usng Gn-Index for Feature Selecton n Text Categorzaton Zhu Wedong 1, Feng Jngyu 1 and Ln Yongn 1 School of Coputer

More information

Large Margin Nearest Neighbor Classifiers

Large Margin Nearest Neighbor Classifiers Large Margn earest eghbor Classfers Sergo Bereo and Joan Cabestany Departent of Electronc Engneerng, Unverstat Poltècnca de Catalunya (UPC, Gran Captà s/n, C4 buldng, 08034 Barcelona, Span e-al: sbereo@eel.upc.es

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

LOOP ANALYSIS. The second systematic technique to determine all currents and voltages in a circuit

LOOP ANALYSIS. The second systematic technique to determine all currents and voltages in a circuit LOOP ANALYSS The second systematic technique to determine all currents and voltages in a circuit T S DUAL TO NODE ANALYSS - T FRST DETERMNES ALL CURRENTS N A CRCUT AND THEN T USES OHM S LAW TO COMPUTE

More information

AN ADAPTIVE APPROACH TO THE SEGMENTATION OF DCE-MR IMAGES OF THE BREAST: COMPARISON WITH CLASSICAL THRESHOLDING ALGORITHMS

AN ADAPTIVE APPROACH TO THE SEGMENTATION OF DCE-MR IMAGES OF THE BREAST: COMPARISON WITH CLASSICAL THRESHOLDING ALGORITHMS A ADAPTIVE APPROACH TO THE SEGMETATIO OF DCE-MR IMAGES OF THE BREAST: COMPARISO WITH CLASSICAL THRESHOLDIG ALGORITHMS Fath Kalel a zaettn Aydn a Gohan Ertas H.Ozcan Gulcur a Bahcesehr Unversty Engneerng

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

Signature and Lexicon Pruning Techniques

Signature and Lexicon Pruning Techniques Sgnature and Lexcon Prunng Technques Srnvas Palla, Hansheng Le, Venu Govndaraju Centre for Unfed Bometrcs and Sensors Unversty at Buffalo {spalla2, hle, govnd}@cedar.buffalo.edu Abstract Handwrtten word

More information

Writer Identification using a Deep Neural Network

Writer Identification using a Deep Neural Network Wrter Identfcaton usng a Deep Neural Network Jun Chu and Sargur Srhar Department of Computer Scence and Engneerng Unversty at Buffalo, The State Unversty of New York Buffalo, NY 1469, USA {jchu6, srhar}@buffalo.edu

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

MULTI LOCAL FEATURE SELECTION USING GENETIC ALGORITHM FOR FACE IDENTIFICATION

MULTI LOCAL FEATURE SELECTION USING GENETIC ALGORITHM FOR FACE IDENTIFICATION ULTI LOCAL FEATURE SELECTION USING GENETIC ALGORITH FOR FACE IDENTIFICATION Dzulkfl ohaad Falkut Sans Koputer dan Sste akluat Unverst Teknolog alasa, 83 UT Skuda, Johor, alasa Tel: 7-553 3333 334, E-al:

More information

An Approach to Real-Time Recognition of Chinese Handwritten Sentences

An Approach to Real-Time Recognition of Chinese Handwritten Sentences An Approach to Real-Tme Recognton of Chnese Handwrtten Sentences Da-Han Wang, Cheng-Ln Lu Natonal Laboratory of Pattern Recognton, Insttute of Automaton of Chnese Academy of Scences, Bejng 100190, P.R.

More information

Local Quaternary Patterns and Feature Local Quaternary Patterns

Local Quaternary Patterns and Feature Local Quaternary Patterns Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents

More information

STATIC MAPPING FOR OPENCL WORKLOADS IN HETEROGENEOUS COMPUTER SYSTEMS

STATIC MAPPING FOR OPENCL WORKLOADS IN HETEROGENEOUS COMPUTER SYSTEMS STATIC MAPPING FOR OPENCL WORKLOADS IN HETEROGENEOUS COMPUTER SYSTEMS 1 HENDRA RAHMAWAN, 2 KUSPRIYANTO, 3 YUDI SATRIA GONDOKARYONO School of Electrcal Engneerng and Inforatcs, Insttut Teknolog Bandung,

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

Classifying Acoustic Transient Signals Using Artificial Intelligence

Classifying Acoustic Transient Signals Using Artificial Intelligence Classfyng Acoustc Transent Sgnals Usng Artfcal Intellgence Steve Sutton, Unversty of North Carolna At Wlmngton (suttons@charter.net) Greg Huff, Unversty of North Carolna At Wlmngton (jgh7476@uncwl.edu)

More information

Multimodal Biometric System Using Face-Iris Fusion Feature

Multimodal Biometric System Using Face-Iris Fusion Feature JOURNAL OF COMPUERS, VOL. 6, NO. 5, MAY 2011 931 Multodal Boetrc Syste Usng Face-Irs Fuson Feature Zhfang Wang, Erfu Wang, Shuangshuang Wang and Qun Dng Key Laboratory of Electroncs Engneerng, College

More information

Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features

Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features Recognton of Handwrtten Numerals Usng a Combned Classfer wth Hybrd Features Kyoung Mn Km 1,4, Joong Jo Park 2, Young G Song 3, In Cheol Km 1, and Chng Y. Suen 1 1 Centre for Pattern Recognton and Machne

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

Low training strength high capacity classifiers for accurate ensembles using Walsh Coefficients

Low training strength high capacity classifiers for accurate ensembles using Walsh Coefficients Low tranng strength hgh capacty classfers for accurate ensebles usng Walsh Coeffcents Terry Wndeatt, Cere Zor Unv Surrey, Guldford, Surrey, Gu2 7H t.wndeatt surrey.ac.uk Abstract. If a bnary decson s taken

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

Detection of hand grasping an object from complex background based on machine learning co-occurrence of local image feature

Detection of hand grasping an object from complex background based on machine learning co-occurrence of local image feature Detecton of hand graspng an object from complex background based on machne learnng co-occurrence of local mage feature Shnya Moroka, Yasuhro Hramoto, Nobutaka Shmada, Tadash Matsuo, Yoshak Shra Rtsumekan

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

Keyword Spotting Based on Phoneme Confusion Matrix

Keyword Spotting Based on Phoneme Confusion Matrix Keyword Spottng Based on Phonee Confuson Matrx Pengyuan Zhang, Jan Shao, Jang Han, Zhaoje Lu, Yonghong Yan ThnkIT Speech Lab, Insttute of Acoustcs, Chnese Acadey of Scences Bejng 00080 {pzhang, jshao,

More information

Scheduling Workflow Applications on the Heterogeneous Cloud Resources

Scheduling Workflow Applications on the Heterogeneous Cloud Resources Indan Journal of Scence and Technology, Vol 8(2, DOI: 0.7485/jst/205/v82/57984, June 205 ISSN (rnt : 0974-6846 ISSN (Onlne : 0974-5645 Schedulng Workflow Applcatons on the Heterogeneous Cloud Resources

More information

Accumulated-Recognition-Rate Normalization for Combining Multiple On/Off-Line Japanese Character Classifiers Tested on a Large Database

Accumulated-Recognition-Rate Normalization for Combining Multiple On/Off-Line Japanese Character Classifiers Tested on a Large Database 4 th Internatonal Workshop on Multple Classfer Systems (MCS23) Guldford, UK Accumulated-Recognton-Rate Normalzaton for Combnng Multple On/Off-Lne Japanese Character Classfers Tested on a Large Database

More information

Incremental MQDF Learning for Writer Adaptive Handwriting Recognition 1

Incremental MQDF Learning for Writer Adaptive Handwriting Recognition 1 200 2th Internatonal Conference on Fronters n Handwrtng Recognton Incremental MQDF Learnng for Wrter Adaptve Handwrtng Recognton Ka Dng, Lanwen Jn * School of Electronc and Informaton Engneerng, South

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour 6.854 Advanced Algorthms Petar Maymounkov Problem Set 11 (November 23, 2005) Wth: Benjamn Rossman, Oren Wemann, and Pouya Kheradpour Problem 1. We reduce vertex cover to MAX-SAT wth weghts, such that the

More information

RESEARCH ON CLOSE-RANGE PHOTOGRAMMETRY WITH BIG ROTATION ANGLE

RESEARCH ON CLOSE-RANGE PHOTOGRAMMETRY WITH BIG ROTATION ANGLE RESEARCH ON CLOSE-RANGE PHOOGRAMMERY WIH BIG ROAION ANGLE Lu Jue a a he Departent of Surveyng and Geo-nforatcs Engneerng, ongj Unversty, Shangha, 9. - lujue985@6.co KEY WORDS: Bg Rotaton Angle; Colnearty

More information

Pose Invariant Face Recognition using Hybrid DWT-DCT Frequency Features with Support Vector Machines

Pose Invariant Face Recognition using Hybrid DWT-DCT Frequency Features with Support Vector Machines Proceedngs of the 4 th Internatonal Conference on 7 th 9 th Noveber 008 Inforaton Technology and Multeda at UNITEN (ICIMU 008), Malaysa Pose Invarant Face Recognton usng Hybrd DWT-DCT Frequency Features

More information

Measuring Cohesion of Packages in Ada95

Measuring Cohesion of Packages in Ada95 Measurng Coheson of Packages n Ada95 Baowen Xu Zhenqang Chen Departent of Coputer Scence & Departent of Coputer Scence & Engneerng, Southeast Unversty Engneerng, Southeast Unversty Nanjng, Chna, 20096

More information

CMPS 10 Introduction to Computer Science Lecture Notes

CMPS 10 Introduction to Computer Science Lecture Notes CPS 0 Introducton to Computer Scence Lecture Notes Chapter : Algorthm Desgn How should we present algorthms? Natural languages lke Englsh, Spansh, or French whch are rch n nterpretaton and meanng are not

More information

Introduction to Geometrical Optics - a 2D ray tracing Excel model for spherical mirrors - Part 2

Introduction to Geometrical Optics - a 2D ray tracing Excel model for spherical mirrors - Part 2 Introducton to Geometrcal Optcs - a D ra tracng Ecel model for sphercal mrrors - Part b George ungu - Ths s a tutoral eplanng the creaton of an eact D ra tracng model for both sphercal concave and sphercal

More information

th International Conference on Document Analysis and Recognition

th International Conference on Document Analysis and Recognition 2013 12th Internatonal Conference on Document Analyss and Recognton Onlne Handwrtten Cursve Word Recognton Usng Segmentaton-free n Combnaton wth P2DBM-MQDF Blan Zhu 1, Art Shvram 2, Srrangaraj Setlur 2,

More information

COLOR IMAGE SEGMENTATION USING SOFT ROUGH FUZZY-C-MEANS CLUSTERING AND SMO SUPPORT VECTOR MACHINE

COLOR IMAGE SEGMENTATION USING SOFT ROUGH FUZZY-C-MEANS CLUSTERING AND SMO SUPPORT VECTOR MACHINE Sgnal & Iage Processng : An Internatonal Journal (SIPIJ) Vol.6, No.5, October 205 COLOR IMAGE SEGMENTATION USING SOFT ROUGH FUZZY-C-MEANS CLUSTERING AND SMO SUPPORT VECTOR MACHINE R.V.V.Krshna and S.Srnvas

More information

SCIENTIFIC PROCEEDINGS OF RIGA TECHNICAL UNIVERSITY Information Technology and Management Science 2002

SCIENTIFIC PROCEEDINGS OF RIGA TECHNICAL UNIVERSITY Information Technology and Management Science 2002 SCIENTIFIC ROCEEDINGS OF RIGA TECHNICAL UNIVERSITY Coputer Scence Inforaton Technology and Manageent Scence METHODS OF FUZZY ATTERN RECOGNITION R Grekovs Keywords: pattern recognton, fuzzy sets, coposton

More information

Support Vector Machines. CS534 - Machine Learning

Support Vector Machines. CS534 - Machine Learning Support Vector Machnes CS534 - Machne Learnng Perceptron Revsted: Lnear Separators Bnar classfcaton can be veed as the task of separatng classes n feature space: b > 0 b 0 b < 0 f() sgn( b) Lnear Separators

More information

Vol. 5, No. 3 March 2014 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved.

Vol. 5, No. 3 March 2014 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved. Journal of Emergng Trends n Computng and Informaton Scences 009-03 CIS Journal. All rghts reserved. http://www.csjournal.org Unhealthy Detecton n Lvestock Texture Images usng Subsampled Contourlet Transform

More information

An Efficient Fault-Tolerant Multi-Bus Data Scheduling Algorithm Based on Replication and Deallocation

An Efficient Fault-Tolerant Multi-Bus Data Scheduling Algorithm Based on Replication and Deallocation BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volue 16, No Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-001 An Effcent Fault-Tolerant Mult-Bus Data

More information

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.

More information

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1 4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:

More information

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks

GA-Based Learning Algorithms to Identify Fuzzy Rules for Fuzzy Neural Networks Seventh Internatonal Conference on Intellgent Systems Desgn and Applcatons GA-Based Learnng Algorthms to Identfy Fuzzy Rules for Fuzzy Neural Networks K Almejall, K Dahal, Member IEEE, and A Hossan, Member

More information

An Empirical Evaluation of Off-line Arabic Handwriting And Printed Characters Recognition System

An Empirical Evaluation of Off-line Arabic Handwriting And Printed Characters Recognition System www.ijcsi.org 29 An Emprcal Evaluaton of Off-lne Arabc Handwrtng And Prnted Characters Recognton System Dr. Fro Parwe Department of Computer Scence & Informaton System Jazan Unversty, Jazan, Kngdom of

More information

A new paradigm of fuzzy control point in space curve

A new paradigm of fuzzy control point in space curve MATEMATIKA, 2016, Volume 32, Number 2, 153 159 c Penerbt UTM Press All rghts reserved A new paradgm of fuzzy control pont n space curve 1 Abd Fatah Wahab, 2 Mohd Sallehuddn Husan and 3 Mohammad Izat Emr

More information