Improving online handwritten mathematical expressions recognition with contextual modeling

Size: px
Start display at page:

Download "Improving online handwritten mathematical expressions recognition with contextual modeling"

Transcription

1 Improvng onlne handwrtten mathematcal expressons recognton wth contextual modelng Ahmad-Montaser Awal, Harold Mouchère, Chrstan Vard-Gaudn IRCCyN/IVC UMR CNRS 6597 Ecole polytechnque de l unversté de Nantes - Nantes France {ahmad-montaser.awal, harold.mouchere, Chrstan.Vard-Gaudn }@unv-nantes.fr Abstract We propose n ths paper a new contextual modellng method for combnng syntactc and structural nformaton for the recognton of onlne handwrtten mathematcal expressons. Those models are used to fnd the most lkely combnaton of segmentaton/recognton hypotheses proposed by a 2D segmentor. Models are based on structural nformaton concernng the layouts of symbols. They are learned from a mathematcal expressons dataset to prevent the use of heurstc rules whch are fuzzy by nature. The system s tested wth a large base of synthetc expressons and also wth a set of real complex expressons. 1. Introducton For scentsts, nothng s better than modelng a gven problem usng mathematcal notaton. Almost all felds of scence ncludng human scences use mathematcs n less or more complex ways. To understand even more the mportance of mathematcal expressons (MEs), we have extracted all MEs from web pages of the French Wkpeda. Almost expressons were found n 7000 web pages. Thus, MEs are unversal communcaton tools among scentsts. Furthermore, the tendency n scentfc communtes to use dgtal proceedngs ncreased remarkably n the last few years. There are many tools to nput MEs nto dgtal documents. However, those tools requre specal sklls to be used effcently. Latex and MathML, for example, requre knowledge of predefned sets of key words. Other tools, such as Math Type, depend on a vsual envronment to add symbols usng the mouse and though needs lot of tme. Recent advances n the doman of dgtal pens and touch screens allow to wdespread the use of handwrtng nput tools. Of course, these tools present an nterestng alternatve to nput mathematcal expressons nto dgtal documents. Hence, t s essental to develop systems able to convert expressons from the natural handwrtten way to a dgtal format. However, handwrtten MEs recognton s more challengng than text recognton [1]. Unlke handwrtten text whch s a smple left to rght sequence of characters; a ME s a complex 2D layout of mathematcal symbols. The number of these symbol (~220 symbols) s by tself another challenge that requres powerful classfyng tools. Moreover, the two dmensonal layout causes many ambgutes n symbol roles, spatal relatons, more examples can be found n [2][3]. Many researches have been done recently n ths doman wth promsng results. Most of these researches consder expresson recognton as a sequence of ndependent subtasks. Ths decomposton smplfes the problem, but errors nherted from one step cannot be easly corrected. Our research focuses on the recognton of onlne handwrtten MEs. The advantage of our proposton s to perform a smultaneous segmentaton, recognton and nterpretaton of MEs under the restrcton of a language model. Specfcally, the classfer used to recognze symbols s based on a global learnng method allowng to learn symbols drectly from MEs performng at the same tme the segmentaton, and the nterpretaton.. The contrbuton of ths paper s to propose a new method to model contextual nformaton between symbols. Contextual models are learned drectly from a ME database. These models serve not only n recognzng expresson structure, but also n boostng the capacty of the symbols classfer by consderng the n best class canddates.

2 2. State of the art Generally, ME recognton takes place n three man steps [4]: segmentaton, recognton and nterpretaton. Consderng an onlne handwrtten sgnal, the prmtve unt, whch allows to segment t, s a stroke. A stroke beng a trace drawn between a pen down and a pen lft. However, n most cases a sngle symbol s composed of several strokes. Conversely, we wll assume that one pen lft exsts between consecutve symbols. A good segmentaton s the key pont of a good recognton and nterpretaton. Hence the segmentaton step consst n groupng strokes belongng to the same symbol. Early systems consdered symbol segmentaton as an ndependent step [5][6]. More recently, symbol segmentaton and recognton are consdered as one step. Thus, the segmentaton s lead by symbol recognton [7][8][9], where recognton scores serve to choose groupngs that are more lkely to represent symbols. In order to decrease the complexty of ths smultaneous optmzaton «best frst search» [7], or CYK [9] algorthms are used. The geometrcal structure of a ME s usually more complex than that of a normal text. Whle a text s systematcally wrtten from left to rght, math symbols can be wrtten n almost all drectons, see Fgure 1. Therefore, MEs nterpretaton conssts of analyzng geometrcal structures of the expresson and applyng syntactc analyss. The objectve of ths nterpretaton s to fnd the dervaton tree of the expresson. Fgure 1 Wrtng drectons n a normal text and a mathematcal expresson Spatal relatons between symbols are crucal for good nterpretaton. Even f all symbols are correctly segmented and recognzed, a 2D analyss s requred to correctly nterpret the expresson. A method based on a Defnte Clause Grammar s proposed n [4]. The effcency of ths DCG s ncreased by usng left factored rules. More recently, Garan [10] proposed a context free grammar. A structure s bult by dvdng the expresson recursvely nto horzontal and vertcal bands. When reachng the level of atomc elements, grammar producton rules are appled accordng to the type of spatal relatons. In [11], the authors present an approach called Fuzzy Shft-Reduce Parsng. Ths method uses a descendng analyss assurng effcent verfcaton. A probablstc grammar has been proposed n [9]. Each producton rule of the grammar s assocated to a logcal relaton n addton to the probablty of ths rule. Thus, the recognton of an expresson s transformed nto a search of rules that maxmze the probablty of obtanng the result expresson. 3. Proposed recognton system The proposed archtecture ams at handlng the recognton of MEs as a smultaneous optmzaton of segmentaton, symbol recognton and nterpretaton problems. The tranng of the system and also the recognton of expressons are done usng the global archtecture we proposed n [17], see Fgure 2. Fgure 2 Expresson recognzer archtecture The System s traned n two dstnct stages n a global learnng schema. Furthermore, the system s traned drectly from mathematcal expressons nstead of tranng t wth solated symbols or usng heurstc values for structural analyss. It takes nto account the ground truth of the gven ME (deal segmentaton and correspondng labels of symbols and spatal relatons among those symbols) and the best current nterpretaton resultng from a specfc segmentaton, and correspondng recognzed symbols. The archtecture s detaled n the followng sectons Symbol hypothess generator The number of all possble segmentatons s defned by the bell number. On a smple example shown n Fgure 3, consderng 7 strokes B 7 = 877 dfferent segmentaton. Bell numbers are calculated usng the followng recursve formula : n n n Bn+ 1 = Bk ; s a bnomal coeffcent. k = 0 k k Fgure 3 Example of groupng hypotheses

3 Hypothess generator lsts a number of possble combnatons of strokes. Each group of strokes s called a symbol hypothess (sh). From a computng perspectve, t can be consdered as a Dynamc Programmng (DP) algorthm, whch s well adapted to ths knd of decson makng problems [12]. However, the key pont s that ths s not a standard 1D-DP but we adopt an extenson to a 2D-DP. To avod the combnatory exploson of the search space, some constrants are added lmtng the maxmum number of strokes n one symbol and of hypothess Symbol recognzer The symbol recognzer provdes, n addton to the best n canddates of each hypothess, a recognton score of each canddate that wll be used to calculate the recognton cost. We used a tme delayed neural network (TDNN) [13] for ts nterestng propertes of beng nsenstve to poston shfts. However, an addtonal layer s added n order to convert the classfer outputs nto probabltes. For a gven hypothess p c j sh ) denotes the probablty of the ( hypothess sh beng the class c j ; where p( c sh ) j = 1 (1) j Some methods consders N best canddate of the symbol classfer [9]. Smlarly, others delay the decson of labelng ambguous symbols to be resolved by the global context [7]. In order to determne the number of canddates retaned for each sh. We retan k canddates wth a max number N (k <=N). k s chosen under the k 1 condton: p ( c j sh ) Thresh to keep only j= 0 canddates wth hgh confdence and avod to keep all N canddates systematcally. In the frst tranng stage, the system s traned wth the tranng expressons wthout consderng contextual nformaton. The goal of ths stage s to tran the symbol classfer. Furthermore, ths stage gves the classfer the ablty to dentfy wrong hypotheses durng the segmentaton usng an addtonal class that we call the junk class [17] Language model A mathematcal expresson s produced by a 2D language. Context free grammars are effcently used for parsng 1D languages (such as programmng languages). However, parsng 2D languages s ntractable and requres specal algorthms and constrants to reduce complexty and ambguty [3]. Graph grammar was ntroduced n [15], transferrng parsng an ME to a graph rewrtng problem. Snce two-dmensonal grammars are faced to performance ssues, we have descrbed one as a set of one-dmensonal rules on both vertcal and horzontal axes. Vertcal rules (VR) and horzontal rules (HR) are appled successvely untl elementary symbols are reached to perform a bottom up parsng algorthm. Table 1 Example of a smple grammar Rule sym x, y, 1, 2, op +, -, x, formule subexp op sym subexp subexp op sym subexp sym sym subexp sym Relaton type (operator) [HR] (operator) [HR] (superscrpt) [VR] As shown n Table 1, each producton rule of the grammar s assocated to a spatal relaton that descrbes the layout between the elements of the rule. On the other hand, each relaton s assocated to a cost functon (see sectons 3.4 and 3.5) that penalzes more or less the rule accordng to structural nformaton of ts elements. Ideal postons and szes are dffcult to be predefned because of the fuzzy nature of relatons. Therefore, we try to model these relatons nstead of predefnng them usng some heurstc rules Structural analyzer Structural analyss requres extractng spatal nformaton of each symbol hypothess to perform contextual evaluaton. In order to avod ambgutes, spatal nformaton are extracted dfferently dependng on the type of the recognzed symbol as shown n Fgure 4. Extracted nformaton s the base lne y and hypothess heght h. Furthermore, the spatal nformaton of a produced sub-expresson s calculated from ts elements consderng the spatal relaton type. Fgure 4 Structural nformaton of dfferent symbol types When a relaton R s bult, the value of y and h of the correspondng sub-expresson s computed from the N chldren components: y h y = f ( y,..., y ) ; h = f ( h,...,h ) SE R SE1 SE N SE R SE1 SEN

4 The number of chldren N dffers accordng to the type of the relaton R; wth N = {2, 3, 4}. For example, relatons as superscrpt and subscrpt" have two chldren. The operator relaton has three chldren, whle the ntegral relaton has four. A sub-expresson (SE) can denote three possble nterpretatons: a symbol hypothess, a sub-expresson, or the fnal result expresson. Then, we defne the normalzed poston and sze dfferences (dh, dy) of a sub-expresson (SE ) as follows: dh = ( hse hse ) / h ; SE dy = ( yse yse ) / h SE The second stage of the tranng ams at modelng spatal relatons wthout consderng the classfer. All occurrences of (dy, dh) of each sub-expressons for each knd of relatons are computed usng the ground truth of the tranng dataset of MEs. Then, two Gaussan models are constructed for each element of a relaton. The frst model reflects the pertnence of the sze of ths element for the sub-expresson produced by the producton rule assocated to ths relaton, usng dh. The second one reflects the qualty of the algnment of the consdered elements accordng to the produced sub-expresson, usng dy. Thus, for each relaton R, 2N Gaussan models are constructed usng the n occurrences of dh, dy of each sub-expresson. The mean µ and varance σ of each model are calculated as follows ( = 1..n): dx µ = ; 1 2 σ = ( dx µ ) n n 1 For example, the relaton superscrpt, whch nvolves two elements, s assocated to four models. Two models for sze dfferences (dh) of each element, and another two for the algnment dfferences (dy). Fgure 5 llustrates the structural nformaton of the superscrpt relaton and shows an example of Gaussan models of the poston dfferences (dh). Though, for a gven stuaton we defne the probablty of a sub-expresson beng correctly postoned and szed regardng the produced SE by a Gaussan functon: g ( x ) 2 µ ) 2 2σ SE, dx ( x = e (2) Hence, the probablty of a sub-expresson beng produced by the relaton R s: p( SE R ) = g ( dh ).g ( dy ) (3) SE,dh SE, dy Back to the example of N sub-expressons producng a new sub-expresson SE by the relaton R. The probablty that SE s produced by the N subexpressons s: p( SE R ) = N = 1 p( SE R ) (4) But, from the defnton of Bayes rule, the probablty of a relaton that produces a sub-expresson knowng ts Gaussan model s: p( SE R ).p( R ) p ( R SE ) = (5) p( SE ) but the term p(se) can be gnored, because t s a constant for all relatons, and by usng the equaton (4) we obtan the probablty of a relaton R: p( R SE ) N = 1 p( SE R ).p( R ) (6) where p(r) s the pror probablty of the relaton R calculated durng the learnng stage Decson maker dh (b) Fgure 5 (a) Illustraton of the relaton superscrpt, (b) Gaussan models of poston dfferences (dh) (a) As shown n the example n Fgure 6, a canddate expresson produced by the grammar s represented by a relatonal tree. Each node represents a hypothess of stroke groupng. The root of ths tree contans n addton to the orgnal nk sgnal: a proposed soluton wth ts global recognton cost and the nature of the lnk wth ts chldren. In a smlar way, each non termnal node represents a sub-expresson, whch contans the same nformaton. Fnally, termnals are symbol hypotheses proposed by the hypothess generator wth ther recognton costs computed by the symbol recognzer.

5 Fgure 7 Examples of real and synthetc expressons Fgure 6 Relatonal trees of two canddates of a mathematcal expresson Snce recognton and structural scores are n form of probablty (p), we use a logarthmc functon to transform those scores nto costs: cost = log( p) The decson maker organzes all resultng relatonal trees, and selects the one that mnmzes a global cost functon. The cost of non-termnal nodes n the relatonal tree s defned by the recursve formula: Costreco ( sh );f SE s a termnal (7) Cost( SE ) = α.cost struct( RSE SE ) + Cost( SE );Otherwse where: Cost ( R SE ) = log( p( R SE ) s the struct SE probablty that the sub-expresson SE s produced by the relaton R. The cost of termnals s the recognton cost of the hypothess sh : Cost ( sh ) = log( p( c sh )) reco j Fnally, the global cost of a canddate expresson wth n symbols hypotheses lnked by r relatons s: Cost (exp) = Cost ( SE root ) Where α s a weghtng factor between recognton and structural costs. The choce of alpha value n the equaton (7) s very mportant to balance the dfferences between structural and recognton costs, t has been set expermentally to α = Experments The expressons corpus s extracted from the base Aster [14]. A set of 36 expressons s chosen coverng a majorty of mathematcal domans. Each expresson contans n average 11 symbols, where the total number of dstnct symbols s 34 classes. Each expresson s artfcally generated from a base of solated symbols collected from 280 wrters [16], therefore ths dataset contans 10,080 mathematcal expressons. In addton, each of those 36 expressons s wrtten twce resultng a total of 72 expressons wrtten by 10 wrters, examples shown n Fgure 7. Further detals about databases can be found n [17]. SE It s napproprate to evaluate the system only at a global level, especally when dealng wth long and complex expressons. In consequence, we have chosen three measures smlar to those used recently n [7] and [9] n order to be more precse and to allow comparng our results. Denotng total number of symbols: N total, we used the followng measures: SegRate=(correctly segmented symbols)/n total RecoRate=(correctly recognzed symbols)/n total ExpRate= (correctly recognzed expressons)/exp total 4.1. Results The number of canddates consdered as a result of symbol hypotheses classfyng s an mportant factor. The curve Fgure 8 shows expresson recognton rate evoluton on the synthetc DB when varyng the average of consdered canddates per symbol hypothess. Fgure 8 Evoluton of test expressons recognton rate Vs average canddates number per symbol Ths curve s obtaned by fxng the max number of canddates to 5, and varyng the threshold (see secton 3.2). Consderng only one recognton result for a hypothess lmts the classfer capacty. On the other hand, retanng a large number of canddates gves more freedom to the structure analyzer. Ths freedom allows to ncrease segmentaton rate wth a rsk to overlap correct expresson nterpretaton. Thus, results n Table 2 are obtaned by consderng at maxmum the frst 5 canddates wth the sum of ther

6 recognton probabltes beng below We compare obtaned results usng ths confguraton and the contextual modelng proposed n ths paper wth those of the system proposed n [17] based on geometrc modelng of spatal relatons. Table 2 Test Expresson recognton rates Synthetc DB SegRate RecoRate ExpRate Geometrc modelng [17] Gaussan modelng Real DB SegRate RecoRate ExpRate Geometrc modelng [17] Gaussan modelng Table 2 shows the nterest of usng Gaussan models for the contextual modelng. Ths latter ncreases expressons recognton rate on the synthetc DB from 64.2% to 64.9%. Ths mprovement s not generalzed on real expressons. ExpRate decreases from (28.6% to 27.9%) compared to 29.2% n the system proposed by Ha et al. [6], notcng that they use a dfferent database and t s not possble to do a drect comparson of results. Ths general fall n performance compared to the geometrc model comes prncpally from the strong dependence of learned models wth the tran database, whch s synthetc. Thus, we assume that t s ndspensable to use large database of real expressons n order to ncrease the generalzaton capacty of usng Gaussan models. 5. Concluson and perspectve We presented n ths paper a new method for contextual modelng n a system for onlne handwrtten mathematcal expressons recognton. Contextual models are learned drectly from ME database. Learned models partcpate n penalzng wrong locatons of hypotheses. Another mprovement comes from consderng the best n canddates of the symbols classfer. We beleve that the performance can be mproved by ntegratng models of smlar relatons and gnore some others that cause ambgutes at relaton level. The system has been tested wth a large set of synthetc expressons and also on a set of real complex expressons wth promsng results. References [1] D. Blosten, A. Grbavec. Recognton of mathematcal notaton. Handbook on Optcal Character Recognton and Document Image Analyss, Queen's unversty, World Scentfc Publshng Company: , [2] W. Martn. Computer nput/output of mathematcal expressons. 2 nd Symp. on Symbolc and Algebrac Manpulatons, New York: [3] E.G. Mller, P. A. Vola. Ambguty and Constrant n Mathematcal Expresson Recognton. 15 th Natonal Conference on Artfcal Intellgence: [4] K-F. Chan, D-Y. Yeung. An effcent syntactc approach to structural analyss of on-lne handwrtten mathematcal expressons. Pattern Recognton 33: [5] C. Faure, Z.X. Wang. Automatc percepton of the structure of handwrtten mathematcal expressons. Computer Processng of Handwrtng, World scentfc, Sngapore: , [6] J. Ha, R.M. Haralck, I.T. Phllps. Understandng mathematcal expressons from document mages. 3 rd ICDAR: , [7] T-H Rhee, J-H Km. Effcent search strategy n structural analyss for handwrtten mathematcal expresson recognton. Pattern Recognton 42(12): , [8] S. Smthes, K. Novns, J. Arvo. A Handwrtng-Based Equaton Edtor. the Graphcs Interface: 84-91, [9] R. Yamamoto, S. Sako, T. Nshmoto, S. Sagayama. On- Lne Recognton of Handwrtten Mathematcal Expressons Based on Stroke-Based Stochastc Context-Free Grammar. 10 th IWFHR, La Baule, France: , [10] U. Garan, B. Chaudhur. Recognton of Onlne Handwrtten Mathematcal Expressons. IEEE Transactons on Systems, Man and Cybernetcs 34: , [11] J.A. Ftzgerald, F. G., T. K. Structural Analyss of Handwrtten Mathematcal Expressons Through Fuzzy parsng. 4 th IASTED: , [12] M. Held, R.M.K., The constructon of dscrete dynamc programmng algorthms, IBM Syst. J. 4(2): , [13] M. Schenkel, I. Guyon, D. Henderson. Onlne cursve scrpt recognton usng tme delay neural networks and hdden Markov models. Mach. Vs. Appl., Specal Issue on Cursve Scrpt Recognton 8: , [14] T.V. Raman. Audo system for techncal readngs. Cornell Unversty, [15] A Kosmala, G Rgoll, S Lavrotte, L Potter. On-Lne Handwrtten Formula Recognton Usng Hdden Markov Models and Context Dependent Graph Grammars. 5 th ICDAR: , [16] A.M. Awal, R. Cousseau, C. Vard-Gaudn. Convertsseur d'équatons LATEX2Ink. 10 th CIFED, Rouen, France: , [17] A.M. Awal, H. Mouchère, C. Vard-Gaudn. Towards handwrtten mathematcal expresson recognton. 10 th ICDAR, Barcelona, Span: , 2009.

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 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

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

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

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

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

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

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

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

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

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

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

Analysis of Continuous Beams in General

Analysis of Continuous Beams in General Analyss of Contnuous Beams n General Contnuous beams consdered here are prsmatc, rgdly connected to each beam segment and supported at varous ponts along the beam. onts are selected at ponts of support,

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

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

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

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan

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

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

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

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

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

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

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1)

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1) Secton 1.2 Subsets and the Boolean operatons on sets If every element of the set A s an element of the set B, we say that A s a subset of B, or that A s contaned n B, or that B contans A, and we wrte A

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

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Decson surface s a hyperplane (lne n 2D) n feature space (smlar to the Perceptron) Arguably, the most mportant recent dscovery n machne learnng In a nutshell: map the data to a predetermned

More information

PRÉSENTATIONS DE PROJETS

PRÉSENTATIONS DE PROJETS PRÉSENTATIONS DE PROJETS Rex Onlne (V. Atanasu) What s Rex? Rex s an onlne browser for collectons of wrtten documents [1]. Asde ths core functon t has however many other applcatons that make t nterestng

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

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

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

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

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

Circuit Analysis I (ENGR 2405) Chapter 3 Method of Analysis Nodal(KCL) and Mesh(KVL)

Circuit Analysis I (ENGR 2405) Chapter 3 Method of Analysis Nodal(KCL) and Mesh(KVL) Crcut Analyss I (ENG 405) Chapter Method of Analyss Nodal(KCL) and Mesh(KVL) Nodal Analyss If nstead of focusng on the oltages of the crcut elements, one looks at the oltages at the nodes of the crcut,

More information

COMPARISON OF SUPPORT VECTOR MACHINE AND NEURAL NETWORK IN CHARACTER LEVEL DISCRIMINANT TRAINING FOR ONLINE WORD RECOGNITION

COMPARISON OF SUPPORT VECTOR MACHINE AND NEURAL NETWORK IN CHARACTER LEVEL DISCRIMINANT TRAINING FOR ONLINE WORD RECOGNITION COMPARISON OF SUPPORT VECTOR MACHINE AND NEURAL NETWORK IN CHARACTER LEVEL DISCRIMINANT TRAINING FOR ONLINE WORD RECOGNITION Abdul Rahm Ahmad 1 Chrstan Vard-Gaudn 3 Marzuk Khald 2 Emle Posson 3 1 Unverst

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

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

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng, Natonal Unversty of Sngapore {shva, phanquyt, tancl }@comp.nus.edu.sg

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

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection 2009 10th Internatonal Conference on Document Analyss and Recognton A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng,

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

Comparison Study of Textural Descriptors for Training Neural Network Classifiers

Comparison Study of Textural Descriptors for Training Neural Network Classifiers Comparson Study of Textural Descrptors for Tranng Neural Network Classfers G.D. MAGOULAS (1) S.A. KARKANIS (1) D.A. KARRAS () and M.N. VRAHATIS (3) (1) Department of Informatcs Unversty of Athens GR-157.84

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

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z.

TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS. Muradaliyev A.Z. TECHNIQUE OF FORMATION HOMOGENEOUS SAMPLE SAME OBJECTS Muradalyev AZ Azerbajan Scentfc-Research and Desgn-Prospectng Insttute of Energetc AZ1012, Ave HZardab-94 E-mal:aydn_murad@yahoocom Importance of

More information

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input Real-tme Jont Tracng of a Hand Manpulatng an Object from RGB-D Input Srnath Srdhar 1 Franzsa Mueller 1 Mchael Zollhöfer 1 Dan Casas 1 Antt Oulasvrta 2 Chrstan Theobalt 1 1 Max Planc Insttute for Informatcs

More information

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent

More information

An Approach in Coloring Semi-Regular Tilings on the Hyperbolic Plane

An Approach in Coloring Semi-Regular Tilings on the Hyperbolic Plane An Approach n Colorng Sem-Regular Tlngs on the Hyperbolc Plane Ma Louse Antonette N De Las Peñas, mlp@mathscmathadmueduph Glenn R Lago, glago@yahoocom Math Department, Ateneo de Manla Unversty, Loyola

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming

Kent State University CS 4/ Design and Analysis of Algorithms. Dept. of Math & Computer Science LECT-16. Dynamic Programming CS 4/560 Desgn and Analyss of Algorthms Kent State Unversty Dept. of Math & Computer Scence LECT-6 Dynamc Programmng 2 Dynamc Programmng Dynamc Programmng, lke the dvde-and-conquer method, solves problems

More information

Dynamic wetting property investigation of AFM tips in micro/nanoscale

Dynamic wetting property investigation of AFM tips in micro/nanoscale Dynamc wettng property nvestgaton of AFM tps n mcro/nanoscale The wettng propertes of AFM probe tps are of concern n AFM tp related force measurement, fabrcaton, and manpulaton technques, such as dp-pen

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Programming in Fortran 90 : 2017/2018

Programming in Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values

More information

Foreground and Background Information in an HMM-based Method for Recognition of Isolated Characters and Numeral Strings

Foreground and Background Information in an HMM-based Method for Recognition of Isolated Characters and Numeral Strings Foreground and Background Informaton n an HMM-based Method for Recognton of Isolated Characters and Numeral Strngs Alceu de S. Brtto Jr a,b, Robert Sabourn c,d, Flavo Bortolozz a,chng Y. Suen d a Pontfíca

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

Accounting for the Use of Different Length Scale Factors in x, y and z Directions

Accounting for the Use of Different Length Scale Factors in x, y and z Directions 1 Accountng for the Use of Dfferent Length Scale Factors n x, y and z Drectons Taha Soch (taha.soch@kcl.ac.uk) Imagng Scences & Bomedcal Engneerng, Kng s College London, The Rayne Insttute, St Thomas Hosptal,

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

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

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices Internatonal Mathematcal Forum, Vol 7, 2012, no 52, 2549-2554 An Applcaton of the Dulmage-Mendelsohn Decomposton to Sparse Null Space Bases of Full Row Rank Matrces Mostafa Khorramzadeh Department of Mathematcal

More information

A fault tree analysis strategy using binary decision diagrams

A fault tree analysis strategy using binary decision diagrams Loughborough Unversty Insttutonal Repostory A fault tree analyss strategy usng bnary decson dagrams Ths tem was submtted to Loughborough Unversty's Insttutonal Repostory by the/an author. Addtonal Informaton:

More information

Lecture 4: Principal components

Lecture 4: Principal components /3/6 Lecture 4: Prncpal components 3..6 Multvarate lnear regresson MLR s optmal for the estmaton data...but poor for handlng collnear data Covarance matrx s not nvertble (large condton number) Robustness

More information

Human Face Recognition Using Generalized. Kernel Fisher Discriminant

Human Face Recognition Using Generalized. Kernel Fisher Discriminant Human Face Recognton Usng Generalzed Kernel Fsher Dscrmnant ng-yu Sun,2 De-Shuang Huang Ln Guo. Insttute of Intellgent Machnes, Chnese Academy of Scences, P.O.ox 30, Hefe, Anhu, Chna. 2. Department of

More information

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique //00 :0 AM Outlne and Readng The Greedy Method The Greedy Method Technque (secton.) Fractonal Knapsack Problem (secton..) Task Schedulng (secton..) Mnmum Spannng Trees (secton.) Change Money Problem Greedy

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

More information

Recognizing Faces. Outline

Recognizing Faces. Outline Recognzng Faces Drk Colbry Outlne Introducton and Motvaton Defnng a feature vector Prncpal Component Analyss Lnear Dscrmnate Analyss !"" #$""% http://www.nfotech.oulu.f/annual/2004 + &'()*) '+)* 2 ! &

More information

3. CR parameters and Multi-Objective Fitness Function

3. CR parameters and Multi-Objective Fitness Function 3 CR parameters and Mult-objectve Ftness Functon 41 3. CR parameters and Mult-Objectve Ftness Functon 3.1. Introducton Cogntve rados dynamcally confgure the wreless communcaton system, whch takes beneft

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

Segmentation Based Online Word Recognition: A Conditional Random Field Driven Beam Search Strategy

Segmentation Based Online Word Recognition: A Conditional Random Field Driven Beam Search Strategy 2013 12th Internatonal Conference on Document Analyss and Recognton Segmentaton Based Onlne Word Recognton: A Condtonal Random Feld Drven Beam Search Strategy Art Shvram 1, Blan Zhu 2, Srrangaraj Setlur

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

Meta-heuristics for Multidimensional Knapsack Problems

Meta-heuristics for Multidimensional Knapsack Problems 2012 4th Internatonal Conference on Computer Research and Development IPCSIT vol.39 (2012) (2012) IACSIT Press, Sngapore Meta-heurstcs for Multdmensonal Knapsack Problems Zhbao Man + Computer Scence Department,

More information

SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE

SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE SHAPE RECOGNITION METHOD BASED ON THE k-nearest NEIGHBOR RULE Dorna Purcaru Faculty of Automaton, Computers and Electroncs Unersty of Craoa 13 Al. I. Cuza Street, Craoa RO-1100 ROMANIA E-mal: dpurcaru@electroncs.uc.ro

More information

A Statistical Model Selection Strategy Applied to Neural Networks

A Statistical Model Selection Strategy Applied to Neural Networks A Statstcal Model Selecton Strategy Appled to Neural Networks Joaquín Pzarro Elsa Guerrero Pedro L. Galndo joaqun.pzarro@uca.es elsa.guerrero@uca.es pedro.galndo@uca.es Dpto Lenguajes y Sstemas Informátcos

More information

Data Representation in Digital Design, a Single Conversion Equation and a Formal Languages Approach

Data Representation in Digital Design, a Single Conversion Equation and a Formal Languages Approach Data Representaton n Dgtal Desgn, a Sngle Converson Equaton and a Formal Languages Approach Hassan Farhat Unversty of Nebraska at Omaha Abstract- In the study of data representaton n dgtal desgn and computer

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

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

Fast Feature Value Searching for Face Detection

Fast Feature Value Searching for Face Detection Vol., No. 2 Computer and Informaton Scence Fast Feature Value Searchng for Face Detecton Yunyang Yan Department of Computer Engneerng Huayn Insttute of Technology Hua an 22300, Chna E-mal: areyyyke@63.com

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

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

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

More information

Hermite Splines in Lie Groups as Products of Geodesics

Hermite Splines in Lie Groups as Products of Geodesics Hermte Splnes n Le Groups as Products of Geodescs Ethan Eade Updated May 28, 2017 1 Introducton 1.1 Goal Ths document defnes a curve n the Le group G parametrzed by tme and by structural parameters n the

More information

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster

More information

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated.

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated. Some Advanced SP Tools 1. umulatve Sum ontrol (usum) hart For the data shown n Table 9-1, the x chart can be generated. However, the shft taken place at sample #21 s not apparent. 92 For ths set samples,

More information

PHYSICS-ENHANCED L-SYSTEMS

PHYSICS-ENHANCED L-SYSTEMS PHYSICS-ENHANCED L-SYSTEMS Hansrud Noser 1, Stephan Rudolph 2, Peter Stuck 1 1 Department of Informatcs Unversty of Zurch, Wnterthurerstr. 190 CH-8057 Zurch Swtzerland noser(stuck)@f.unzh.ch, http://www.f.unzh.ch/~noser(~stuck)

More information

Conditional Speculative Decimal Addition*

Conditional Speculative Decimal Addition* Condtonal Speculatve Decmal Addton Alvaro Vazquez and Elsardo Antelo Dep. of Electronc and Computer Engneerng Unv. of Santago de Compostela, Span Ths work was supported n part by Xunta de Galca under grant

More information

Module Management Tool in Software Development Organizations

Module Management Tool in Software Development Organizations Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES UbCC 2011, Volume 6, 5002981-x manuscrpts OPEN ACCES UbCC Journal ISSN 1992-8424 www.ubcc.org VISUAL SELECTION OF SURFACE FEATURES DURING THEIR GEOMETRIC SIMULATION WITH THE HELP OF COMPUTER TECHNOLOGIES

More information

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

y and the total sum of

y and the total sum of Lnear regresson Testng for non-lnearty In analytcal chemstry, lnear regresson s commonly used n the constructon of calbraton functons requred for analytcal technques such as gas chromatography, atomc absorpton

More information

Unsupervised Learning

Unsupervised Learning Pattern Recognton Lecture 8 Outlne Introducton Unsupervsed Learnng Parametrc VS Non-Parametrc Approach Mxture of Denstes Maxmum-Lkelhood Estmates Clusterng Prof. Danel Yeung School of Computer Scence and

More information

Hybrid Non-Blind Color Image Watermarking

Hybrid Non-Blind Color Image Watermarking Hybrd Non-Blnd Color Image Watermarkng Ms C.N.Sujatha 1, Dr. P. Satyanarayana 2 1 Assocate Professor, Dept. of ECE, SNIST, Yamnampet, Ghatkesar Hyderabad-501301, Telangana 2 Professor, Dept. of ECE, AITS,

More information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

More information

Query Clustering Using a Hybrid Query Similarity Measure

Query Clustering Using a Hybrid Query Similarity Measure Query clusterng usng a hybrd query smlarty measure Fu. L., Goh, D.H., & Foo, S. (2004). WSEAS Transacton on Computers, 3(3), 700-705. Query Clusterng Usng a Hybrd Query Smlarty Measure Ln Fu, Don Hoe-Lan

More information

USING GRAPHING SKILLS

USING GRAPHING SKILLS Name: BOLOGY: Date: _ Class: USNG GRAPHNG SKLLS NTRODUCTON: Recorded data can be plotted on a graph. A graph s a pctoral representaton of nformaton recorded n a data table. t s used to show a relatonshp

More information