Extraction of Lip Contour from Face
|
|
- Logan Pope
- 5 years ago
- Views:
Transcription
1 Internatonal Journal of Current Engneerng and Technology ISSN INPRESSCO. All Rghts Reserved. Avalable at Research Artcle Extracton of Lp Contour from Face Rt Kushwaha a, Neeta Nan a* and Promla Jangra a a Department of Computer Engneerng Malavya Natonal Insttute of Technology, Japur, Rajasthan, Inda Accepted 3June 202, Avalable onlne 8 June 202 Abstract Lp segmentaton s an essental stage n many multmeda systems such as vdeo-conferencng, lp readng, or low bt rate codng communcaton systems. It s also useful n varous mage / vdeo acquston devces encouraged the development of many computer vson applcatons, such as vson-based survellance, vson based man machne nterfaces, vson-based bometrcs, and so on. Hence extracton of lp becomes a broad feld. Ths paper presents an algorthm for extracton of lp contour. We have used two algorthms for ths. Our frst algorthm s a color based algorthm derved from a quadratc polynomal, wth the assumpton that color of lps should le n the range of blue. The accuracy of the frst proposed algorthm s 9% n case of normal skn people, and 95% n case of farer skn color people. Our second algorthm s model a based algorthm whch gves accuracy up to 9 6%. Keyword: Lp contour detecton, Lp segmentaton, Lp extracton from face.. Introducton Detecton of the lp contour s a fundamental procedure of mouth feature extracton. It forms a prelmnary stage of face mage analyss, whch s essental for numerous applcaton areas ncludng man-machne nteracton based on the observed human behavor, vdeo-telephony, face and person dentcaton, bmodal speech recognton, face and vsual speech synthess, facal expressons classcaton etc. All of these applcatons requre an effcent and fully automated mouth feature extracton method that can be acheved usng an automatc lp contour detecton technque. Observng the pxels of lps, we fnd that lp color of farer skn people ranges from dark red to purple, and for normal skn color people t s n the range of blue under normal lght condtons. From the perspectve of human vsual percepton, the lps are very easy to be dferentated from the face, cause of dferent contrasts n colors. The outer labal contour of the mouth s havng very poor color dstncton when compared aganst ts skn background; t makes extracton of lp a dfcult problem. In order to mprove the contrast between lp and the other face regons we need dferent type of lp extracton technques. But we are takng the assumpton that lp color vares from dark red to purple then ths condton s satsfed wth the people who have very far complexon. For the normal skn people we are assumng that the color of lp also vares n the range of blue. We thus used the chromatc color space (Cheng Chn et al, 2003, whch s constructed from the RGB color space (Cheng Chn et al, 2003, to exclude dark pxels because * Correspondng author: Neeta Nan chromatc color space s not sutable to dstngush between brght pxels and dark pxels. For chromatc color space, each pxel s represented by two values, denoted by (r,g. Ther relatonshp s explaned n secton IV-A. Both dark pxels and brght pxels mght have the same converted r and g values due to the normalzaton effect n brghtness n chromatc color space thus we have used both the color spaces. Our second algorthm s model based algorthm (T.F.Cootes et al, 995 hence we don t need any color constran for that. Secton II descrbes the related work, secton III descrbes the dataset taken of dferent types. Secton IV and V descrbes the proposed algorthms for lp contour extracton technques. In secton VI result analyss of the proposed methods are obtaned. Secton VII contans the whole summary of the experments. 2. Related work A number of technques are used for detecton of lp contours from a gven face mage, whch can be generally classed nto categores, whch are model based approaches lke deform-able templates (L.Yulle et al, 989, actve shape models J.Luettn et al, 996 and snakes (M.Kass et al, 987. These approaches generally use a set feature pont for approxmatng the lp contours wth splne functons and gve a model for the lp contour. Hgh robustness s acheved relable constrants on the deformaton of mouth model are ncluded n the cost functon, whch s defned on the bass of heurstcs or through generally supervsed learnng from examples. However, the mnmzaton of the cost functon nvolves computatonally expensve algorthms, and the model 265
2 defnton often employs sem-automated user asssted procedures or a pror knowledge of some characterstcs of the mouth mage. The second category s Colour based approach lke (Yao Hongxun et al, Another category s level set based approach and rule based approach (Cheng Chn et al, We have used rule based approach. In ths approach frstly colour devaton s done by some technque then rules for extractng the lp contour s appled. 3. Database acquston For testng both the methods we have chosen dferent databases. If a person s havng very far complexon then we have appled dark red to purple color on hs lps, he s havng normal skn color then we choose blue color. A dataset of 50 persons for farer skn color people wth red color on lps s taken from nternet for testng results. For normal skn color people we construct the database by applyng blue color on lps, we are havng 20 person s face. Two types of pctures are taken n both the cases whch are enlsted below. Images when a part of face wth lps s avalable Images when whole face s avalable We have tested all the lsted type of mages for frst algorthm. And the second algorthm s tested on the mages when a part of face wth lps s avalable. 4. Proposed Method The overvew of the frst proposed method for extractng the lp contour from face s shown n Fgure converson from conventonal RGB color space to chromatc color space s defned as follows: r R R G B g G R G B ( (2 Where R, G, B denotes the ntenstes of pxels n red, green and blue channels respectvely. Accordng to the above transformaton, t s easy to see that the brghtness varaton n mages can be normalzed n chromatc color space. The color representaton n ths two-dmensonal chromatc color space enables us to vsualze and analyze very easly when buldng the color model for skn pxels. 2 lp ( r.776r.560r.223 ( r.560r.766 (4 As the objectve of our algorthm s to detect lps from face n real tme, we adopt a smple technque whch uses two quadratc polynomals to fnd out the upper and lower contour of lp regon usng equaton and 2. Ths extracts the darker regon of face wth a O(2 computaton cost. After applyng ths dscrmnate functon the pxels from darker part of face lke eyes, eyebrows, nose holes etc., are also ncluded n the extracted regon whch are removed by applyng threshold as explaned n the secton 4.2. b Applyng threshold As we know that the threshold vares for dferent skn color people hence we calculate two threshold condtons. One for those wth farer complexon and another for those who are havng normal complexon as gven below: For (FSC Farer Skn Color Threshold condton for farer skn color people s not havng lots of varaton n ther ranges, hence the ntensty value of red green and blue pxels le n approxmately same range. The threshold s calculated as: F( N 0 g lp( r & R 20 & G 20 & B 20 (6 Fg. flow chart for color based approach a Rules for extracton Ths algorthm adopts the chromatc color coordnate for color representaton. For chromatc color space, each pxel s represented by two values, denoted by (r, g. The 2 For (NSC Normal Skn Color As we all know there are lots of varaton n the normal skn color that mples varaton n the ntensty value of the pxels. Thus R, G and B values have varatons n ther range. The threshold s calculated as shown below. Where L (N = ndcates a lp regon pxel. And f(r and lp(r s taken from the equaton 3 and 4. We have used standard morphologcal operaton for mage enhancement and nose 266
3 removal, followed by edge detecton technque for fndng the edge detecton technque for fndng the edges of extracted component. Connected component labelng s also done for the better regon extracton. The algorthm s dscussed below: L( N 0 g lp( r & R 30 & 30 G 70 & 55 B 22 (7 Step. Morphologcal Operaton: After applyng threshold stray pxels as sde effects also called salt nose s left n the mage (I. Ths s removed by morphologcal Eroson operaton usng a square (sze varyng from 3-5 as the StrEl (structurng element as shown n equaton 8. I IStrEl (8 These small components from the face up to the sze of 5 pxels. The Eroson operaton also removes some part from the lp component whch s restored by Dlatng I (the lps as shown n equaton 9, usng Dsc as a StrEl2. I I SrtEl 2 (9 Ths restores the orgnal lps and also connects both upper and lower lp portons whch sometmes break due to Eroson. Both the StrEl s are shown n the table. Step2. Edge Detecton: To extract the upper and lower contour of lps whch are mostly dagonal edges we apply edge detecton technque usng Sobel edge detector as t smoothes the mage n the drecton perpendcular to edge detecton whch makes t a good edge detector for dagonal edges. Step3. Connected Component: As we know that the largest connected component n the face wll be lps, we have appled the 8-connected component algorthm to denty lps. Fgure 3 shows an nstance of the above steps for normal skn color people and Fgure 2 shows the result for farer skn people. Fg. 3 Result on Normal skn color people (a Input mage (b Applyng threshold condtons (c Morphologcal operaton and edge detecton (d Extracted lps. 5. Proposed method 2 Ths algorthm s desgned for specc set of frontal face mages wth open mouth, from the whole database. Ths model based algorthm uses Mean Shape Model (MSM. The database used for tranng s hand desgned. The algorthm conssts of four major steps: (a Tranng the data set, (b calculate MSM, (c normalze the MSM by algnng t wth the mn angle to prncpal axs, (d MSM deformaton. 5. Tranng Set The tranng set contans any set of 20 open mouth mages to make MSM. Open mouthed mages are selected to cater for the purpose of maxmum outer lp contour segmentaton of any nput mage n any sze database. Thus for ths experment, the tranng set contans only open mouth mages to make the large shape model whch covers up all other type of movement of lps by just nner deformaton of the model. 5.2 Mean Shape Model A SV (Shape Vector s defned manually for all mages of the tranng set. The SV conssts of 66 landmark ponts whch specy the outer lp contour as shown n Fg. 4 (b. These landmark ponts are chosen wth the constrant that these ponts exactly defne the lp contour shape. The th SV s defned as equaton 0. SV ( x, y, ( x 2, y 2,..., ( x 66, y 66 (0 After evaluatng the SV of all tranng set mages, the MSM s calculated usng equaton. Fg. 2 Result on farer skn color people (a Input mage (b Applyng threshold condtons (c Morphologcal operaton and edge detecton (d Extracted lps. SV N N SV ( Here, N s the number of landmark ponts for any tranng set mage. One nstance of MSM s shown n Fgure 4 (c. 267
4 5.3 Algnment of MSM The MSM calculated n the above step s algned wth mnmum angle wth the prncpal axs as shown n Fgure 4(d. To acheve the requred algnment we have to perform scalng, rotaton and translaton so that mage and MSM corresponds as closely as possble. 5.4 Mean Shape Model Deformaton After proper normalzaton of MSM, we start the deformaton of MSM to extract the lp contour of the nput mage. Before performng any deformaton, we threshold the RGB mage to a bnary mage (B usng equaton 2. B 0 R 20 & & G 20 & & B 70 The deformaton can be done as: (2 The MSM s dvded nto two parts- upper lp model and lower lp model. The upper lp model contans 35 landmarks ponts whereas; lower lp model contans 3 landmarks ponts of the MSM. 2 MC (model curve for these both parts s extracted usng curve fttng algorthm ( We fnd the polynomal of degree n that fts the data ponts x to. y Let suppose the mean shape ponts of upper lp contour are: X u x, x x2,..., Y u y, y y2,..., (3 (4 4 Fnd tangent normal for each pxel whch occurred n between the MSM and the lp contour of nput mage (ths s nothng but the ntensty change of the bnary mage. Normal lne s the lne perpendcular to the tangent lne to the curve. The slope of normal lne s -/(dy/dx and thus the equaton of normal lne s dy ( x x ( y y 0 dx (7 The results of model deformaton are shown n Fgure 4(e. Length of the normal vector of each tangent s bascally decded by the pont on the model curve and end pont of deformaton where ntensty change occurred between the lp and the skn. Here, we check the ntensty value at each sngle pxel ncrement of normal vector length. So, the task of pxel by pxel checkng becomes lttle bt tme consumng. To reduce ths tme, we can use the bnary search approach nstead of pxel by pxel approach. In ths approach, we can set the maxmum value of length for normal vector that s feasble under the model deformaton. For every teraton reduce the length by half and agan make a test of ntensty value at the pont. If that pont les on the lp then agan reduce the length by half ncrease the length up to half of prevous normal vector length. Repeat these tll we get a sngle pont. Ths s the end pont of the normal vector and whch defne the lp contour. A new SV s extracted that contans the landmark ponts whch defne the shape of our nput mage. An nstance of the fnal output of the deformaton of MSM s shown n Fgure 4(f. p n n ( x p. x p2. x... pn. x pn (5 Here, p, p 2 and p n+ are the polynomal coeffcent of a polynomal equaton. The degree n of the curve s chosen such that all data ponts related to * les on the polynomal equaton of the curve Where, * s ( x, y 3 Construct the tangent on the MSV curve. For example, y=p(x then slope of tangent s dy/dx. Then the tangent lne at ( x, y s defned as: y y dy.( x x dx (6 These tangents drawn on the model curve are equal to the number of landmark ponts whch defne the MSM. Fg. Lp contour extracton processng: (a Tranng set Image, (b Landmark pont represented n blue color (c MSM, red color defne the mean pont (d Algnment of MSM on nput/test mage (e Deformaton of MSM: green lne represents the normal vector (f Output after deformaton 6. Result analyss Algorthm s tested on 270 mages. 50 mages of farer skn color people wth dark red to purple color lps, and 20 mages of normal skn color people where, the test 268
5 mages contans both full face and part of face. The accuracy of the proposed algorthm s 9% for the normal skn, and 95% for the farer skn people, where the test mages contans full face, as 42 mages among 50 gves correct result for farer skn color people. And 0 among 20 gves correct result for normal skn color people. Algorthm 2 s tested on 50 mages of normal skn people database contanng frontal face mages havng mouth only. Out of 50 mages, 48 mages successfully fulflled the crtera for the acceptance of lp contour. Fgure 5 shows the results n detal. Both the algorthms work well even for low-resoluton mages, but performance degrades wth poor llumnaton. Conclusons Proposed algorthm gves good results for both skn color people, and works n dferent well-constraned condtons of database. It has an accuracy of 9% for normal skn color and 95% for far skn color. The accuracy s consstent across databases provded the lp color s red and mage qualty s good. Fg. 2 Hstrogram depcts the correctly classed mages The performance degrades the lp color s neutral and any other face feature s smlar to lp color. Ths s proposed as future enhancement of the algorthm. In algorthm 2 the lp contour segmentaton s performed by usng MSM deformaton approach whch gves good results for outer landmarks. Ths work can be further extended for nner landmark ponts of the mouth, whch defnes the poston of mouth. Ths could also denty how much lps are open whch s hghly requred n the vsual speech recognton systems. Both the algorthms work well for good qualty mages. Small degradaton s observed n poorly llumnated mages. References L.Yulle, D.S.Kohen, and P.W.Hallnan (989, Feature Extracton from Faces Usng Deformable Templates, In: Proceednds of IEEE Internatonal Conference Computer Vson and Pattern Recog., pp , (San Dego,CA. J.Luettn, N.A.Thacker, and S.W.Beet (996, Vsual Speech Recognton Usng Actve Shape Models and Hdden Markov Models, In Proc. IEEE Intl. Conf. on Acoustcs, Speech, and Sgnal. Vol. 2, pp , Atlanta, GA. M.Kass, A.Wtkn, and D.Terzopulos (987, Snakes: Actve Contour Models. In Intl. J. Computer Vson, Vol., No. 4, pp Yao Hongxun, L Yajuan, GaoWen (2002, Lp- Movement Features Extracton and Recognton Based on Chroma Analyss. In Acta Electronca Snca, pp H.Mehrotra, G.Agrawal, M.C.Srvastava (2009, Automatc Lp Contour Trackng and Vsual Character Recognton for Computerzed Lp Readng, Internatonal Journal of Computer Scence,pp.627. Cheng Chn Chang, Wen Ka Ta, Mau Tsuen Yang, Y Tng Huang, Ch Jaung Huang (2003, Novel method for detectng lps, eyes and faces n real tme (Elsever Ltd. Abu Sayeed, Md.Sohal and Prabr Bhattacharya (2007, Automated Lp Contour Detecton Usng the Level Set Segmentaton Method. In Proceedngs 4th Internatonal Conference on Image Analyss and Processng. M.Sadegh, J.Kttler and K.Messer (2002,. Modellng and segmentaton of lp area n face mages. In Proceedng of onlne confrence on Image sgnal processng, Vol. 49, No.3, June. Fahmeh Salm, Mohammad T Sadegh (2009, Decson Level Fuson of Colour Hstogram Based Classers for Clusterng of Mouth Area Images. In Proceedngs of Internatonal Conference on Dgtal Image Processng. Pham The Bao and Huynh Nguyen Duy Nhan (2009, A New Approach to Mouth Detecton Usng Neural Network In Proceedngs Internatonal Conference on Control, Automaton and Systems Engneerng. Jagdsh Lal Raheja, Radhey Shyam, Jatn Gupta, Umesh Kumar, P Bhanu Prasad (200, Facal Gesture Identcaton usng Lp Contours, In Proceedng of Second Internatonal Conference on Machne Learnng and Computng. Qang Wang, Hazhou A, Guangyou Xu (2002, A Probablstc Dynamc Contour Model for Accurate and Robust Lp Trackng, Proceedngs of the Fourth IEEE Internatonal Conference on Multmodal Interfaces (ICMI02. Y.P.Guan (2008, Automatc extracton of lps based on mult-scale wavelet edge detecton, In Proceedngs of IET Comput. Vs, Vol. 2, No., pp Lan.Matthews, T.F.Cootes, J.Andrew Bangham, Stephen Cox, Rchard Harvey (2002, Extracton of Vsual Features for Lpreadng In Proceedngs of IEEE Transactons on Pattern Analyss and Machne Intellgence, Vol. 24, No. 2 T.F.Cootes, C.J.Taylor, D.H.Cooper, J.Graham (995, Actve Shape Models- Ther Tranng and Applcaton In Proceedngs of Computer Vson And Image Understandng, Vol. 6, No., pp
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 informationSkew 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 informationA 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 informationContent 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 informationDetection 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 informationParallelism 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 informationFEATURE 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 informationA B-Snake Model Using Statistical and Geometric Information - Applications to Medical Images
A B-Snake Model Usng Statstcal and Geometrc Informaton - Applcatons to Medcal Images Yue Wang, Eam Khwang Teoh and Dnggang Shen 2 School of Electrcal and Electronc Engneerng, Nanyang Technologcal Unversty
More informationComputer Animation and Visualisation. Lecture 4. Rigging / Skinning
Computer Anmaton and Vsualsaton Lecture 4. Rggng / Sknnng Taku Komura Overvew Sknnng / Rggng Background knowledge Lnear Blendng How to decde weghts? Example-based Method Anatomcal models Sknnng Assume
More informationCorner-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 informationA 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 informationFace Recognition using 3D Directional Corner Points
2014 22nd Internatonal Conference on Pattern Recognton Face Recognton usng 3D Drectonal Corner Ponts Xun Yu, Yongsheng Gao School of Engneerng Grffth Unversty Nathan, QLD, Australa xun.yu@grffthun.edu.au,
More information2x 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 informationAn efficient method to build panoramic image mosaics
An effcent method to buld panoramc mage mosacs Pattern Recognton Letters vol. 4 003 Dae-Hyun Km Yong-In Yoon Jong-Soo Cho School of Electrcal Engneerng and Computer Scence Kyungpook Natonal Unv. Abstract
More informationImprovement 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 informationSupport 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 informationCluster 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 informationLocal 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 informationVectorization of Image Outlines Using Rational Spline and Genetic Algorithm
01 Internatonal Conference on Image, Vson and Computng (ICIVC 01) IPCSIT vol. 50 (01) (01) IACSIT Press, Sngapore DOI: 10.776/IPCSIT.01.V50.4 Vectorzaton of Image Outlnes Usng Ratonal Splne and Genetc
More informationLearning a Class-Specific Dictionary for Facial Expression Recognition
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 4 Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-0067 Learnng a Class-Specfc Dctonary for
More informationAnalysis 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 informationEdge 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 informationSLAM 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 informationAn 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 informationShape 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 informationLecture 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 informationPalmprint Feature Extraction Using 2-D Gabor Filters
Palmprnt Feature Extracton Usng 2-D Gabor Flters Wa Kn Kong Davd Zhang and Wenxn L Bometrcs Research Centre Department of Computng The Hong Kong Polytechnc Unversty Kowloon Hong Kong Correspondng author:
More informationEYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS
P.G. Demdov Yaroslavl State Unversty Anatoly Ntn, Vladmr Khryashchev, Olga Stepanova, Igor Kostern EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS Yaroslavl, 2015 Eye
More informationTsinghua 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 informationOutline. 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 informationVideo Object Tracking Based On Extended Active Shape Models With Color Information
CGIV'2002: he Frst Frst European Conference Colour on Colour n Graphcs, Imagng, and Vson Vdeo Object rackng Based On Extended Actve Shape Models Wth Color Informaton A. Koschan, S.K. Kang, J.K. Pak, B.
More informationPictures at an Exhibition
1 Pctures at an Exhbton Stephane Kwan and Karen Zhu Department of Electrcal Engneerng Stanford Unversty, Stanford, CA 9405 Emal: {skwan1, kyzhu}@stanford.edu Abstract An mage processng algorthm s desgned
More information12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification
Introducton to Artfcal Intellgence V22.0472-001 Fall 2009 Lecture 24: Nearest-Neghbors & Support Vector Machnes Rob Fergus Dept of Computer Scence, Courant Insttute, NYU Sldes from Danel Yeung, John DeNero
More informationMULTISPECTRAL 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 informationFast 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 informationRobust Face Alignment for Illumination and Pose Invariant Face Recognition
Robust Face Algnment for Illumnaton and Pose Invarant Face Recognton Fath Kahraman 1, Bnnur Kurt 2, Muhttn Gökmen 2 Istanbul Techncal Unversty, 1 Informatcs Insttute, 2 Computer Engneerng Department 34469
More informationDevelopment of an Active Shape Model. Using the Discrete Cosine Transform
Development of an Actve Shape Model Usng the Dscrete Cosne Transform Kotaro Yasuda A Thess n The Department of Electrcal and Computer Engneerng Presented n Partal Fulfllment of the Requrements for the
More informationDetection 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 informationFeature 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 informationA 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 information3D Face Reconstruction With Local Feature Refinement. Abstract
, pp.6-74 http://dx.do.org/0.457/jmue.04.9.8.06 3D Face Reconstructon Wth Local Feature Refnement Rudy Adpranata, Kartka Gunad and Wendy Gunawan 3, formatcs Department, Petra Chrstan Unversty, Surabaya,
More informationThe Research of Ellipse Parameter Fitting Algorithm of Ultrasonic Imaging Logging in the Casing Hole
Appled Mathematcs, 04, 5, 37-3 Publshed Onlne May 04 n ScRes. http://www.scrp.org/journal/am http://dx.do.org/0.436/am.04.584 The Research of Ellpse Parameter Fttng Algorthm of Ultrasonc Imagng Loggng
More informationClassification of Face Images Based on Gender using Dimensionality Reduction Techniques and SVM
Classfcaton of Face Images Based on Gender usng Dmensonalty Reducton Technques and SVM Fahm Mannan 260 266 294 School of Computer Scence McGll Unversty Abstract Ths report presents gender classfcaton based
More informationA Background Subtraction for a Vision-based User Interface *
A Background Subtracton for a Vson-based User Interface * Dongpyo Hong and Woontack Woo KJIST U-VR Lab. {dhon wwoo}@kjst.ac.kr Abstract In ths paper, we propose a robust and effcent background subtracton
More information3D Face Reconstruction With Local Feature Refinement
ternatonal Journal of Multmeda and Ubqutous Engneerng Vol.9, No.8 (014), pp.59-7 http://dx.do.org/10.1457/jmue.014.9.8.06 3D Face Reconstructon Wth Local Feature Refnement Rudy Adpranata 1, Kartka Gunad
More informationA Clustering Algorithm for Key Frame Extraction Based on Density Peak
Journal of Computer and Communcatons, 2018, 6, 118-128 http://www.scrp.org/ournal/cc ISSN Onlne: 2327-5227 ISSN Prnt: 2327-5219 A Clusterng Algorthm for Key Frame Extracton Based on Densty Peak Hong Zhao
More informationAlgorithm for Human Skin Detection Using Fuzzy Logic
Algorthm for Human Skn Detecton Usng Fuzzy Logc Mrtunjay Ra, R. K. Yadav, Gaurav Snha Department of Electroncs & Communcaton Engneerng JRE Group of Insttutons, Greater Noda, Inda er.mrtunjayra@gmal.com
More informationR 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 informationObject Tracking Based on PISC Image and Template Matching
ect Trackng Based on PISC Image and Template Matchng Bud Sugand Electrcal Engneerng Department Batam State Polytechnc Batam Indonesa ud_sugand@polatam.ac.d Astract Ths paper proposed a method for oect
More informationFace Recognition University at Buffalo CSE666 Lecture Slides Resources:
Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural
More informationUser 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 informationReducing Frame Rate for Object Tracking
Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg
More informationLearning Ensemble of Local PDM-based Regressions. Yen Le Computational Biomedicine Lab Advisor: Prof. Ioannis A. Kakadiaris
Learnng Ensemble of Local PDM-based Regressons Yen Le Computatonal Bomedcne Lab Advsor: Prof. Ioanns A. Kakadars 1 Problem statement Fttng a statstcal shape model (PDM) for mage segmentaton Callosum segmentaton
More informationLearning 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 informationClassification / Regression Support Vector Machines
Classfcaton / Regresson Support Vector Machnes Jeff Howbert Introducton to Machne Learnng Wnter 04 Topcs SVM classfers for lnearly separable classes SVM classfers for non-lnearly separable classes SVM
More informationFitting: Deformable contours April 26 th, 2018
4/6/08 Fttng: Deformable contours Aprl 6 th, 08 Yong Jae Lee UC Davs Recap so far: Groupng and Fttng Goal: move from array of pxel values (or flter outputs) to a collecton of regons, objects, and shapes.
More informationThe Shortest Path of Touring Lines given in the Plane
Send Orders for Reprnts to reprnts@benthamscence.ae 262 The Open Cybernetcs & Systemcs Journal, 2015, 9, 262-267 The Shortest Path of Tourng Lnes gven n the Plane Open Access Ljuan Wang 1,2, Dandan He
More informationA 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 informationTN348: Openlab Module - Colocalization
TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages
More informationA Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures
A Novel Adaptve Descrptor Algorthm for Ternary Pattern Textures Fahuan Hu 1,2, Guopng Lu 1 *, Zengwen Dong 1 1.School of Mechancal & Electrcal Engneerng, Nanchang Unversty, Nanchang, 330031, Chna; 2. School
More informationA high precision collaborative vision measurement of gear chamfering profile
Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) A hgh precson collaboratve vson measurement of gear chamferng profle Conglng Zhou, a, Zengpu Xu, b, Chunmng
More informationVol. 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 informationSmoothing 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 information3D 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 informationNovel Fuzzy logic Based Edge Detection Technique
Novel Fuzzy logc Based Edge Detecton Technque Aborsade, D.O Department of Electroncs Engneerng, adoke Akntola Unversty of Tech., Ogbomoso. Oyo-state. doaborsade@yahoo.com Abstract Ths paper s based on
More informationImage Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline
mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and
More informationAn 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 informationThe 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 informationSum 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 informationImage Alignment CSC 767
Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances
More informationRange images. Range image registration. Examples of sampling patterns. Range images and range surfaces
Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples
More informationA 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 informationA robust, low-cost approach to Face Detection and Face Recognition
CT Internatonal Journal of Dgtal Image Processng, ISSN 0974 9691 (Prnt) & ISSN 0974 9586 (Onlne) A robust, low-cost approach to Face Detecton and Face Recognton Dvya Jyot 1, Aman Chadha 2, Pallav Vadya
More informationObject-Based Techniques for Image Retrieval
54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the
More informationMulti-stable Perception. Necker Cube
Mult-stable Percepton Necker Cube Spnnng dancer lluson, Nobuuk Kaahara Fttng and Algnment Computer Vson Szelsk 6.1 James Has Acknowledgment: Man sldes from Derek Hoem, Lana Lazebnk, and Grauman&Lebe 2008
More informationScale Selective Extended Local Binary Pattern For Texture Classification
Scale Selectve Extended Local Bnary Pattern For Texture Classfcaton Yutng Hu, Zhlng Long, and Ghassan AlRegb Multmeda & Sensors Lab (MSL) Georga Insttute of Technology 03/09/017 Outlne Texture Representaton
More informationReal-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution
Real-tme Moton Capture System Usng One Vdeo Camera Based on Color and Edge Dstrbuton YOSHIAKI AKAZAWA, YOSHIHIRO OKADA, AND KOICHI NIIJIMA Graduate School of Informaton Scence and Electrcal Engneerng,
More informationUsing Fuzzy Logic to Enhance the Large Size Remote Sensing Images
Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract
More informationActive Contours/Snakes
Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng
More informationDiscriminative classifiers for object classification. Last time
Dscrmnatve classfers for object classfcaton Thursday, Nov 12 Krsten Grauman UT Austn Last tme Supervsed classfcaton Loss and rsk, kbayes rule Skn color detecton example Sldng ndo detecton Classfers, boostng
More information12. Segmentation. Computer Engineering, i Sejong University. Dongil Han
Computer Vson 1. Segmentaton Computer Engneerng, Sejong Unversty Dongl Han Image Segmentaton t Image segmentaton Subdvdes an mage nto ts consttuent regons or objects - After an mage has been segmented,
More informationDesign of Structure Optimization with APDL
Desgn of Structure Optmzaton wth APDL Yanyun School of Cvl Engneerng and Archtecture, East Chna Jaotong Unversty Nanchang 330013 Chna Abstract In ths paper, the desgn process of structure optmzaton wth
More informationFace Recognition Based on SVM and 2DPCA
Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty
More informationMETRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES
METRIC ALIGNMENT OF LASER RANGE SCANS AND CALIBRATED IMAGES USING LINEAR STRUCTURES Lorenzo Sorg CIRA the Italan Aerospace Research Centre Computer Vson and Vrtual Realty Lab. Outlne Work goal Work motvaton
More informationMulti-view 3D Position Estimation of Sports Players
Mult-vew 3D Poston Estmaton of Sports Players Robbe Vos and Wlle Brnk Appled Mathematcs Department of Mathematcal Scences Unversty of Stellenbosch, South Afrca Emal: vosrobbe@gmal.com Abstract The problem
More informationPCA Based Gait Segmentation
Honggu L, Cupng Sh & Xngguo L PCA Based Gat Segmentaton PCA Based Gat Segmentaton Honggu L, Cupng Sh, and Xngguo L 2 Electronc Department, Physcs College, Yangzhou Unversty, 225002 Yangzhou, Chna 2 Department
More informationHybrid 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 informationAttributed Relational Graph Based Feature Extraction of Body Poses In Indian Classical Dance Bharathanatyam
Athra.Sugathan et al Int. Journal of Engneerng Research and Applcatons ISSN : 2248-9622, Vol. 4, Issue 5( Verson 7), May 2014, pp.11-17 RESEARCH ARTICLE OPEN ACCESS Attrbuted Relatonal Graph Based Feature
More informationIntegrated Expression-Invariant Face Recognition with Constrained Optical Flow
Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow Chao-Kue Hseh, Shang-Hong La 2, and Yung-Chang Chen Department of Electrcal Engneerng, Natonal Tsng Hua Unversty, Tawan 2 Department
More informationCompiler 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 informationClassifying 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 informationDevelopment of Face Tracking and Recognition Algorithm for DVR (Digital Video Recorder)
IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.6 No.3A, March 2006 7 Development of Face Trackng and Recognton Algorthm for DVR (Dgtal Vdeo Recorder) Jang-Seon Ryu and Eung-Tae
More informationStructure from Motion
Structure from Moton Structure from Moton For now, statc scene and movng camera Equvalentl, rgdl movng scene and statc camera Lmtng case of stereo wth man cameras Lmtng case of multvew camera calbraton
More informationFuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches
Proceedngs of the Internatonal Conference on Cognton and Recognton Fuzzy Flterng Algorthms for Image Processng: Performance Evaluaton of Varous Approaches Rajoo Pandey and Umesh Ghanekar Department of
More informationA NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION
A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION Mhaela Gordan *, Constantne Kotropoulos **, Apostolos Georgaks **, Ioanns Ptas ** * Bass of Electroncs Department,
More informationAn Image Compression Algorithm based on Wavelet Transform and LZW
An Image Compresson Algorthm based on Wavelet Transform and LZW Png Luo a, Janyong Yu b School of Chongqng Unversty of Posts and Telecommuncatons, Chongqng, 400065, Chna Abstract a cylpng@63.com, b y27769864@sna.cn
More informationMOTION BLUR ESTIMATION AT CORNERS
Gacomo Boracch and Vncenzo Caglot Dpartmento d Elettronca e Informazone, Poltecnco d Mlano, Va Ponzo, 34/5-20133 MILANO boracch@elet.polm.t, caglot@elet.polm.t Keywords: Abstract: Pont Spread Functon Parameter
More informationContours Planning and Visual Servo Control of XXY Positioning System Using NURBS Interpolation Approach
Inventon Journal of Research Technology n Engneerng & Management (IJRTEM) ISSN: 2455-3689 www.jrtem.com olume 1 Issue 4 ǁ June. 2016 ǁ PP 16-23 Contours Plannng and sual Servo Control of XXY Postonng System
More informationS1 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 informationFace Tracking Using Motion-Guided Dynamic Template Matching
ACCV2002: The 5th Asan Conference on Computer Vson, 23--25 January 2002, Melbourne, Australa. Face Trackng Usng Moton-Guded Dynamc Template Matchng Lang Wang, Tenu Tan, Wemng Hu atonal Laboratory of Pattern
More information