Retrieval and Clustering from a 3D Human Database based on Body and Head Shape

Size: px
Start display at page:

Download "Retrieval and Clustering from a 3D Human Database based on Body and Head Shape"

Transcription

1 SAE 06DHM 57 Retreval and Clusterng from a 3D Human Database based on Body and Head Shape Afzal Godl, Sandy Ressler Natonal Insttute of Standards and Technology ABSTRACT In ths paper, we descrbe a framework for smlarty based retreval and clusterng from a 3D human database. Our technque s based on both body and head shape representaton and the retreval s based on smlarty of both of them. The 3D human database used n our study s the CAESAR anthropometrc database whch contans approxmately 5000 bodes. We have developed a web based nterface for specfyng the queres to nteract wth the retreval system. Our approach performs the smlarty based retreval n a reasonable amount of tme and s a practcal approach. INTRODUCTION Wth the wde avalablty of 3D scannng technologes, 3D geometry s becomng an mportant type of meda. Large numbers of 3D models are created every day and many are stored n publcly avalable databases. Understandng the 3D shape and structure of these models s essental to many scentfc actvtes. These 3D scentfc databases requre methods for storage, ndexng, searchng, clusterng, retreval and recognton of the content under study. Searchng a database for 3D obects whch are smlar to a gven 3D obect s an mportant and challengng problem. Ths doman of research s also called query by example (QBE). We have developed technques for searchng a human database and have used the CAESAR anthropometrc database whch conssts of a database of approxmately 5000 human subects. In our study we have mplemented methods for smlarty based retreval from the CAESAR human database based on both human body and head shape. Prevous work on human body retreval based on body shape was performed by [Paquet and Roux 2003]. They performed content based anthropometrc data mnng of three dmensonal scanned human by representng them wth compact support feature vectors. They showed a vrtual envronment to perform vsual data mnng on the clusters and to characterze the populaton by defnng archetypes. [Paquet 2004] ntroduced cluster analyss as a method to explore 3D body scans together wth the relatonal anthropometrc data as contaned n the CAESAR anthropometrc database. [Azouz 2002, 2004] analyzed human shape varablty usng a volumetrc representaton of 3D human bodes and appled a prncpal components analyss (PCA) to the volumetrc data to extract domnant components of shape varablty for a target populaton. Through vsualzaton, they also showed the man modes of human shape varaton. The work of [Allen 2004] demonstrated a system of syntheszng 3D human body shapes, accordng to user specfed parameters; they used 250 CAESAR body scans for tranng. Retreval based on head shape was performed by [Ip and Wong 2002]. Ther smlarty measure was based on Extended Gaussan Images of the polygon normal. They also compared t to an Egenhead approach. The 3D scans of human bodes n the CAESAR human database contan over two hundred ffty thousand grd ponts. To be used effectvely for ndexng, searchng, clusterng and retreval, ths human body data requres a compact representaton. We have developed two such representatons based on human body shape: 1) a descrptor vector d, based on lengths mostly between sngle large bones. Thus, we form a 3D body descrpton vector of ffteen dstances, d, wth wrst to elbow, elbow to shoulder, hp to knee etc.; and 2) three slhouettes of the human body are created by renderng the human body from the front, sde and top. These slhouettes are then encoded as Fourer descrptors of features for later smlarty based retreval. These two methods are explaned n more detals n the Body Shape Descrptor secton. We also have developed two compact representaton based on human head shape: 1) applyng Prncpal Component Analyss (PCA) on the 3D facal surface and creatng PCA based facal descrptors; and 2) n the second method the 3D trangular grd of the head s transformed to a sphercal coordnate system by a least squares approach and expanded n a bass of sphercal harmoncs. More explanaton of these two

2 representatons of human head shape follow n the Head shape Descrptor secton. We also have used these four descrptors for clusterng of human bodes based on each descrptor. The four descrptors allow the selecton of the best descrptor for the applcaton, such as the use of a head descrptor for Helmet Desgn. CAESAR database The CAESAR (Cvlan Amercan and European Surface Anthropometry Resource) proect has collected 3D Scans, seventy three Anthropometry Landmarks, and Tradtonal Measurements data for each of the 5000 subects. The obectve of ths study was to represent, n three dmensons, the anthropometrc varablty of the cvlan populatons of Europe and North Amerca and t was the frst successful anthropometrc survey to use 3 D scannng technology. The CAESAR proect employs both 3 D scannng and tradtonal tools for body measurements for people ages A typcal CAESAR body s shown n Fgure 1. Fgure 2. A Caesar body wth landmark numbers and postons BODY SHAPE DESCRIPTOR We now descrbe two methods for creatng descrptors based on human body shape: Dstance Based The frst method uses a descrptor vector d based on lengths mostly between sngle large bones. For descrptor vector purposes, we requre lengths only between landmark ponts where ther separaton dstance s somewhat pose ndependent. The reason t s not completely pose nvarant s that dstance are between landmark ponts whch are on the surface body compared to the dstance between the center of the ont axs. Ths apples to ponts connected by a sngle large bone as shown n Fgure 3. Thus, we form a descrptor vector of ffteen dstances, d, wth d1 wrst to elbow, d2, elbow to shoulder, d3 hp to knee etc. For whch the Eucldean dstance Fgure 1a. A CAESAR body n standng pose Fgure 1b. A CAESAR body n sttng pose The seventy three anthropometrc landmarks ponts were extracted from the scans as shown n Fgure 2. These landmark ponts are pre marked by pastng small stckers on the body and are automatcally extracted usng landmark software. There are around 250,000 ponts n each surface grd on a body and ponts are dstrbuted unformly. d = P P s somewhat nvarant across dfferent poses. Dstances such as chn knee are avoded. The dstance based descrptor s then used wth the L1 and L2 norm to create a smlarty matrx. The L1 dstance: d ( P, P ) = k = 1 P P The L2 dstance: d ( P, P ) = k = 1 P 2 P 2 More detals and shortcomngs about ths descrptor were descrbed n the paper [Godl 2003] To test how well the dstance based descrptor performs, we studed the dentfcaton rate of a subset of 200

3 subects of CESAR database where the gallery set contans the standng and the probe set contans the sttng pose of each subect. In ths dscusson, the gallery s the group of enrolled descrptor vector and the probe set refers to the group of unknown test descrptor vectors. The measure of dentfcaton performance s the rank order statstc called the Cumulatve Match Characterstc (CMC). The rank order statstcs ndcates the probablty that the gallery subect wll be among the top r matches to a probe mage of the same subect. Ths probablty depends upon both gallery sze and rank. The CMC at rank 1 for the study s 40%. Subect 0082 s rendered n three vews Each slhouette s then represented as R Front Sde Top R Angle d 6 d 5 d Body shape descrptor consst of of dstances b/w landmark pts d = {d 1,d 2,d 3, d 4 } Dstances: d 1 hp to knee d 2 knee to ankle d 3 wrst to elbow d 4 elbow to shoulder etc Fgure 3. A dstance based body shape descrptor Slhouette Fourer Based d 7 The second method of body shape descrptor that we propose s based on renderng the human body from the front, sde and top drectons and creatng three slhouettes of the human body as shown n Fgure 4. The theory s that 3D models are smlar f they also look smlar from dfferent vewng angles. The slhouette s then represented as R(radus) of the outer contour from the center of orgn of the area of the slhouettes. These three contours are then encoded as Fourer descrptors whch are used later as features for smlarty based retreval. The number of real part of Fourer modes used to descrbe each slhouette s sxteen (16); hence each human body s descrbed by a vector of length forty eght (48). Ths method s pose dependent, so only bodes of the same pose can be compared. The Fourer based descrptor s then used wth the L1 and L2 norm to create a smlarty matrx. d 1 d 2 d 4 d 3 Rgd Connectons (Bones) Dstances are some what Invarant to movement, poston, and pose Fgure 4. Subect s rendered n three slhouette vews HEAD SHAPE DESCRIPTOR We now descrbe two methods for creatng descrptors based on human head shape: PCA Based In ths method we neglected the effect of facal expresson. By cuttng part of the facal grd from the whole CAESAR body grd usng the landmark ponts 5 and 10 as shown n Fgure 5 and lsted n Table 1. Table 1 lst all the numbers and names of landmark ponts used n our 3D face recognton study. The new generated facal grd for some of the subects wth two dfferent vews s shown n Fgure 6. In the case of people standng the mnmum number of grd ponts s 2445 and the mean number s For the case of people sttng the mnmum number of grd ponts n the facal surface s 660 and the mean number s Ths shows that the grd s very coarse for some of the subects n the seated pose.

4 neghbor method when there are vods n the orgnal facal grd. For some of the subects there are large vods n the facal surface grds. Fgure 7 shows the facal surface and the new rectangular grd. Fgure 5. Landmark ponts 1, 2, 3, 4, 5 and 10. Vertcal and horzontal lnes are the cuttng plane Table 1. Numbers and names of landmark ponts used n our 3D face 1 Sellon 2 Rt Infraobtale 3 Lt Infraobtale 4 Supramenton 5 Rt.Tragon 6 Rt. Gonon 7 Lt. Tragon 8 Lt. Gonon 10 Rt. Clavcale 12 Lt.Clavcale Fgure 7. Shows the new facal rectangular grd for two subects We properly postoned and algned the facal surface and then nterpolated the surface nformaton on a regular rectangular grd whose sze s proportonal to the dstance between the landmark ponts. Next we perform Prncpal Component Analyss (PCA) on the 3D surface and smlarty based descrptors are created. In ths method the head descrptor s only based on the facal regon. The PCA recognton method s a nearest neghbor classfer operatng n the PCA subspace. The smlarty measure n our study s based on L1 dstance and Mahalanobs dstance. To test how well the PCA based descrptor performs, we studed the dentfcaton between 200 standng and sttng subects. The CMC at rank 1 for the study s 85%. More detals about ths descrptor are descrbed n the paper by [Godl 2004] Fgure 6. Facal surfaces after the cut from the CAESAR body n two dfferent vews. Next, we use four anthropometrc landmark ponts (L1, L2, L3, L4) as shown n Fgure 5, located on the facal surface, to properly poston and algn the face surface usng an teratve method. There s some error n algnment and poston because of error n measurements of the poston of these landmark ponts. Ths Max error was 15 mm, obtaned by takng the dfference of dstance between landmark ponts L1 L2 and between L3 L4 for subects standng compared to subects sttng. Then we nterpolate the facal surface nformaton and color map on a regular rectangular grd whose sze s proportonal to the dstance between the landmark ponts L2 and L3 ( d= L3 L2 ) and whose grd sze s 128 n both drectons. We use a cubc nterpolaton and handle mssng values wth the nearest Sphercal Harmoncs Based In the second method the 3D trangular grd of the head s transformed to a sphercal coordnate system by a least square approach and expanded n a sphercal harmonc bass as shown n Fgure 8. Snce the CAESAR head grd has large vods n the top of the head and also because of cuttng the grd at the neck there s crcular hole. Snce these holes are not flled properly, we have a convergence problem wth 10% of the head grds. The man advantage of the Sphercal Harmoncs Based head descrptor s that t s orentaton and poston ndependent. In the near future we plan to fx ths problem usng a method whch flls vods. The sphercal harmoncs based descrptor s then used wth the L1 and L2 norm to create smlarty measure. To test how well the Sphercal Harmoncs Based head descrptor performs, we studed the dentfcaton of the human head between 220 standng and sttng subects. The CMC at rank 1 for the study s 94%.

5 Fgure 8. 3D head grd s mapped nto a sphere RESULTS Retreval Results The web based nterface enables us to select a partcular body, or a random body or bodes, based on some crtera such as weght, age, heght, etc as shown Fgure 9. Subsequently, we can perform smlarty based retreval based on a sngle descrptor (out of the four descrptors). Usng four descrptors allows users to select the best descrptor for ther applcaton, such as the use of head descrptor for helmet or eyeglasses desgn. The partal results from a body shape based smlarty retreval for subect number are shown Fgure 10. Fgure 10. Smlarty based retreval for based on body shape The partal results from a head shape PCA based smlarty retreval for subect number are shown Fgure 11 and for subect number are shown n Fgure 12. The ntal results show that the results and amount of tme for retreval are very reasonable. Fgure 11. Smlarty based retreval for based on PCA facal shape Fgure 9. The web based nterface allows one to select a partcular body, or a random body Fgure 12. Smlarty based retreval for based on PCA facal shape

6 Clusterng Results We have used the compact body and head descrptors for clusterng. Clusterng s the process of organzng a set of bodes/heads nto groups n such a way that the bodes/heads wthn the group are more smlar to each other than they are to other bodes belongng to dfferent clusters. Many methods for clusterng are found n varous communtes; we have tred a herarchcal clusterng method. We then use Dendrogram whch s a vsual representaton of herarchcal data to show the clusters. The Dendrogram tree starts at the root, whch s at the top for a vertcal tree (the nodes represent clusters). Fgure 12 shows the Agglomeratve Clusterng of Body Shape Dstances descrptor wth number of clusters = 100 and Fgure 13 shows the same wth number of clusters = 30. Concluson We have developed four methods for searchng the human database usng smlarty of human body and head shape. Based on some of our ntal observatons and from our CMC results for an dentfcaton study between 200 standng subects and 200 sttng subects, t can be sad that the body and head descrptors represent the CAESAR bodes qute accurately. We have seen that our approach performs the smlarty based retreval and clusterng n a reasonable amount of tme and therefore, has potental to be a practcal approach. References CAESAR: Cvlan Amercan and European Surface Anthropometry Resource web ste: Paquet, E., Roux, M "Anthropometrc Vsual Data Mnng: A Content Based Approach," Submtted to IEA 2003 Internatonal Ergonomcs Assocaton XVth Trennal Congress. Seoul, Korea. NRC Paquet, E., "Explorng Anthropometrc Data Through Cluster Analyss," Dgtal Human Modelng for Desgn and Engneerng (DHM). Oakland Unversty, Rochester, Mchgan, USA. June 15 17, NRC Ben Azouz, Z., Roux, M., Lepage, R. "3D Descrpton of the Human Body Shape: Applcaton of Karhunen Loève Expanson to the CAESAR Database," Proceedngs of the 16th Internatonal Congress Exhbton of Computer Asssted Radology Surgery. Pars, France. June 26 29, 2002 Fgure 12. Agglomeratve Clusterng of Body Shape Dstances descrptor (number of clusters=100 ) Ben Azouz, Z., Roux, M., Shu, C., Lepage, R., Analyss of Human Shape Varaton usng Volumetrc Technques, The 17th Annual Conference on Computer Anmaton and Socal Agents (CASA2004). Geneva, Swtzerland. July 7 9, Ip, H. H. S. and Wong W D Head Model Retreval Based on Herarchcal Facal Regon Smlarty, Proc. of 15th Internatonal Conference on Vsual Interface (VI2002), Canada. Afzal Godl, Patrck Grother, Sandy Ressler, Human Identfcaton from Body Shape, proceedngs of 4th IEEE Internatonal Conference on 3D Dgtal Imagng and Modelng, Oct , Banff, Canada. Fgure 13. Clusterng of Body Shape Dstances descrptor (number of clusters=30 ) Afzal, Godl, Sandy Ressler and Patrck Grother, "Face Recognton usng 3D surface and color map nformaton: Comparson and Combnaton", the SPIE s symposum on Bometrcs Technology for Human Identfcaton, Aprl 12 13, 2004, Orlando, FL

7 Allen, B., Curless, B., and Popovc, Z Explorng the space of human body shapes: data drven synthess under anthropometrc control To appear n Proc. Dgtal Human Modelng for Desgn and Engneerng Conference, Rochester, MI, June SAE Internatonal CONTACT Afzal Godl can be contacted at afzal.godl@nst.gov NIST, 100 Bureau Dr, MS 8940, Gathersburg, MD ACKNOWLEDGMENTS We would lke to thank Dr. Kathleen Robnette of Wrght Patterson Ar Force Base, Dayton, USA for provdng us the CAESAR Anthropometry database.

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

3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks

3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks 3D Shape Representation and Analysis of the Human Body and Ontology for Anthropometric Landmarks Afzal Godil National Institute of Standards and Technology, USA WEAR conference, Banff, Canada 2007 Introduction

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

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 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

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

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

Hierarchical clustering for gene expression data analysis

Hierarchical clustering for gene expression data analysis Herarchcal clusterng for gene expresson data analyss Gorgo Valentn e-mal: valentn@ds.unm.t Clusterng of Mcroarray Data. Clusterng of gene expresson profles (rows) => dscovery of co-regulated and functonally

More information

3D Description of the Human Body Shape Using Karhunen-Loève Expansion

3D Description of the Human Body Shape Using Karhunen-Loève Expansion Internatonal Journal of Informaton Technology Vol. 8, No. 2 September 2002 3D Descrpton of the Human Body Shape Usng Karhunen-Loève Expanson Zouhour Ben Azouz (1, 2), Marc Roux (2), Rchard Lepage (1) (1):

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

Detection of an Object by using Principal Component Analysis

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

More information

3D Virtual Eyeglass Frames Modeling from Multiple Camera Image Data Based on the GFFD Deformation Method

3D Virtual Eyeglass Frames Modeling from Multiple Camera Image Data Based on the GFFD Deformation Method NICOGRAPH Internatonal 2012, pp. 114-119 3D Vrtual Eyeglass Frames Modelng from Multple Camera Image Data Based on the GFFD Deformaton Method Norak Tamura, Somsangouane Sngthemphone and Katsuhro Ktama

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

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

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

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

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

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition Mathematcal Methods for Informaton Scence and Economcs Novel Pattern-based Fngerprnt Recognton Technque Usng D Wavelet Decomposton TUDOR BARBU Insttute of Computer Scence of the Romanan Academy T. Codrescu,,

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

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

TN348: Openlab Module - Colocalization

TN348: 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 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

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

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervsed Learnng and Clusterng Why consder unlabeled samples?. Collectng and labelng large set of samples s costly Gettng recorded speech s free, labelng s tme consumng 2. Classfer could be desgned

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

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

Inference of Human Postures by Classification of 3D Human Body Shape

Inference of Human Postures by Classification of 3D Human Body Shape IEEE Internatonal Workshop on Analyss and Modelng of Faces and Gestures, ICCV 23 Inference of Human Postures by Classfcaton of 3D Human Body Shape Isaac COHEN, Hongxa LI Insttute for Robotcs and Intellgent

More information

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task

Term Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto

More information

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.

More information

Lecture #15 Lecture Notes

Lecture #15 Lecture Notes Lecture #15 Lecture Notes The ocean water column s very much a 3-D spatal entt and we need to represent that structure n an economcal way to deal wth t n calculatons. We wll dscuss one way to do so, emprcal

More information

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face 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 information

Development of an Active Shape Model. Using the Discrete Cosine Transform

Development 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 information

Image Alignment CSC 767

Image 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 information

3D Face Recognition Fusing Spherical Depth Map and Spherical Texture Map

3D Face Recognition Fusing Spherical Depth Map and Spherical Texture Map Journal of Computer and Communcatons, 14, *, ** Publshed Onlne **** 14 n ScRes. http://www.scrp.org/journal/jcc http://dx.do.org/1.436/jcc.14.***** 3D Face Recognton Fusng Sphercal Depth Map and Sphercal

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

Real-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution

Real-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 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

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval Fuzzy -Means Intalzed by Fxed Threshold lusterng for Improvng Image Retreval NAWARA HANSIRI, SIRIPORN SUPRATID,HOM KIMPAN 3 Faculty of Informaton Technology Rangst Unversty Muang-Ake, Paholyotn Road, Patumtan,

More information

Face Recognition using 3D Directional Corner Points

Face 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 information

Performance Evaluation of Information Retrieval Systems

Performance Evaluation of Information Retrieval Systems Why System Evaluaton? Performance Evaluaton of Informaton Retreval Systems Many sldes n ths secton are adapted from Prof. Joydeep Ghosh (UT ECE) who n turn adapted them from Prof. Dk Lee (Unv. of Scence

More information

Basic Pattern Recognition. Pattern Recognition Main Components. Introduction to PR. PR Example. Introduction to Pattern Recognition.

Basic Pattern Recognition. Pattern Recognition Main Components. Introduction to PR. PR Example. Introduction to Pattern Recognition. Introducton to Pattern Recognton Pattern Recognton (PR): Classfy what nsde of the mage Basc Pattern Recognton Xaojun Q Applcatons: Speech Recognton/Speaker Identfcaton Fngerprnt/Face Identfcaton Sgnature

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

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

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

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity ISSN(Onlne): 2320-9801 ISSN (Prnt): 2320-9798 Internatonal Journal of Innovatve Research n Computer and Communcaton Engneerng (An ISO 3297: 2007 Certfed Organzaton) Vol.2, Specal Issue 1, March 2014 Proceedngs

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

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

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

Human skeleton proportions from monocular data

Human skeleton proportions from monocular data 1266 Peng et al. / J Zheang Unv SCIENCE A 2006 7(7):1266-1274 Journal of Zheang Unversty SCIENCE A ISSN 1009-3095 (Prnt); ISSN 1862-1775 (Onlne) www.zu.edu.cn/zus; www.sprngerlnk.com E-mal: zus@zu.edu.cn

More information

Video Object Tracking Based On Extended Active Shape Models With Color Information

Video 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 information

Signature and Lexicon Pruning Techniques

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

More information

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

APPLICATION OF AN AUGMENTED REALITY SYSTEM FOR DISASTER RELIEF

APPLICATION OF AN AUGMENTED REALITY SYSTEM FOR DISASTER RELIEF APPLICATION OF AN AUGMENTED REALITY SYSTEM FOR DISASTER RELIEF Johannes Leebmann Insttute of Photogrammetry and Remote Sensng, Unversty of Karlsruhe (TH, Englerstrasse 7, 7618 Karlsruhe, Germany - leebmann@pf.un-karlsruhe.de

More information

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline

Image 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 information

CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES

CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES Marco A. Chavarra, Gerald Sommer Cogntve Systems Group. Chrstan-Albrechts-Unversty of Kel, D-2498 Kel, Germany {mc,gs}@ks.nformatk.un-kel.de

More information

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm Proceedngs of the 5th WSEAS Int. Conf. on Sgnal Processng, Robotcs and Automaton, Madrd, Span, February 5-7, 6 (pp4-45) Invarant Shape Obect Recognton Usng B-Splne, Cardnal Splne, and Genetc Algorthm PISIT

More information

Background Removal in Image indexing and Retrieval

Background Removal in Image indexing and Retrieval Background Removal n Image ndexng and Retreval Y Lu and Hong Guo Department of Electrcal and Computer Engneerng The Unversty of Mchgan-Dearborn Dearborn Mchgan 4818-1491, U.S.A. Voce: 313-593-508, Fax:

More information

An Image Fusion Approach Based on Segmentation Region

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

More information

A Novel 3D Object Categorization and Retrieval System Using Geometric Features

A Novel 3D Object Categorization and Retrieval System Using Geometric Features A Novel 3D Obect Categorzaton and Retreval System Usng Geometrc Features Mohammad Ramezan Computer Vson Lab, Electrcal Engneerng Faculty Sahand Unversty of Technology Tabrz, Iran mr_ramezan@sut.ac.r Hossen

More information

Gender Classification using Interlaced Derivative Patterns

Gender Classification using Interlaced Derivative Patterns Gender Classfcaton usng Interlaced Dervatve Patterns Author Shobernejad, Ameneh, Gao, Yongsheng Publshed 2 Conference Ttle Proceedngs of the 2th Internatonal Conference on Pattern Recognton (ICPR 2) DOI

More information

Electrical analysis of light-weight, triangular weave reflector antennas

Electrical analysis of light-weight, triangular weave reflector antennas Electrcal analyss of lght-weght, trangular weave reflector antennas Knud Pontoppdan TICRA Laederstraede 34 DK-121 Copenhagen K Denmark Emal: kp@tcra.com INTRODUCTION The new lght-weght reflector antenna

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

Querying by sketch geographical databases. Yu Han 1, a *

Querying by sketch geographical databases. Yu Han 1, a * 4th Internatonal Conference on Sensors, Measurement and Intellgent Materals (ICSMIM 2015) Queryng by sketch geographcal databases Yu Han 1, a * 1 Department of Basc Courses, Shenyang Insttute of Artllery,

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

PCA Based Gait Segmentation

PCA 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 information

Implementation of a Dynamic Image-Based Rendering System

Implementation of a Dynamic Image-Based Rendering System Implementaton of a Dynamc Image-Based Renderng System Nklas Bakos, Claes Järvman and Mark Ollla 3 Norrköpng Vsualzaton and Interacton Studo Lnköpng Unversty Abstract Work n dynamc mage based renderng has

More information

Brushlet Features for Texture Image Retrieval

Brushlet Features for Texture Image Retrieval DICTA00: Dgtal Image Computng Technques and Applcatons, 1 January 00, Melbourne, Australa 1 Brushlet Features for Texture Image Retreval Chbao Chen and Kap Luk Chan Informaton System Research Lab, School

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

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

Computer Animation and Visualisation. Lecture 4. Rigging / Skinning

Computer 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 information

Content-Based Bird Retrieval using Shape context, Color moments and Bag of Features

Content-Based Bird Retrieval using Shape context, Color moments and Bag of Features www.ijcsi.org 101 Content-Based Brd Retreval usng Shape context, Color moments and Features Bahr abdelkhalak 1 and hamd zouak 2 1 Faculty of Scences, Unversty Chouab Doukkal, Equpe: Modélsaton mathématque

More information

Machine Learning 9. week

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

More information

A Novel Similarity Measure using a Normalized Hausdorff Distance for Trademarks Retrieval Based on Genetic Algorithm

A Novel Similarity Measure using a Normalized Hausdorff Distance for Trademarks Retrieval Based on Genetic Algorithm Internatonal Journal of Computer Informaton Systems and Industral Management Applcatons (IJCISIM) ISSN: 50-7988 Vol. (009), pp.3-30 http://www.mrlabs.org/jcsm A Novel Smlarty Measure usng a Normalzed Hausdorff

More information

Accessibility Analysis for the Automatic Contact and Non-contact Inspection on Coordinate Measuring Machines

Accessibility Analysis for the Automatic Contact and Non-contact Inspection on Coordinate Measuring Machines Proceedngs of the World Congress on Engneerng 008 Vol I Accessblty Analyss for the Automatc Contact and Non-contact Inspecton on Coordnate Measurng Machnes B. J. Álvarez, P. Fernández, J. C. Rco and G.

More information

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros.

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros. Fttng & Matchng Lecture 4 Prof. Bregler Sldes from: S. Lazebnk, S. Setz, M. Pollefeys, A. Effros. How do we buld panorama? We need to match (algn) mages Matchng wth Features Detect feature ponts n both

More information

Study on Fuzzy Models of Wind Turbine Power Curve

Study on Fuzzy Models of Wind Turbine Power Curve Proceedngs of the 006 IASME/WSEAS Internatonal Conference on Energy & Envronmental Systems, Chalkda, Greece, May 8-0, 006 (pp-7) Study on Fuzzy Models of Wnd Turbne Power Curve SHU-CHEN WANG PEI-HWA HUANG

More information

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

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

More information

3D Face Reconstruction With Local Feature Refinement. Abstract

3D 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 information

RECOGNITION AND AGE PREDICTION WITH DIGITAL IMAGES OF MISSING CHILDREN

RECOGNITION AND AGE PREDICTION WITH DIGITAL IMAGES OF MISSING CHILDREN RECOGNIION AND AGE PREDICION WIH DIGIAL IMAGES OF MISSING CHILDREN A Wrtng Project Presented to he Faculty of the Department of Computer Scence San Jose State Unversty In Partal Fulfllment of the Requrements

More information

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

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

More information

A Webpage Similarity Measure for Web Sessions Clustering Using Sequence Alignment

A Webpage Similarity Measure for Web Sessions Clustering Using Sequence Alignment A Webpage Smlarty Measure for Web Sessons Clusterng Usng Sequence Algnment Mozhgan Azmpour-Kv School of Engneerng and Scence Sharf Unversty of Technology, Internatonal Campus Ksh Island, Iran mogan_az@ksh.sharf.edu

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

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

More information

A high precision collaborative vision measurement of gear chamfering profile

A 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 information

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces

Range 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 information

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval

KIDS Lab at ImageCLEF 2012 Personal Photo Retrieval KD Lab at mageclef 2012 Personal Photo Retreval Cha-We Ku, Been-Chan Chen, Guan-Bn Chen, L-J Gaou, Rong-ng Huang, and ao-en Wang Knowledge, nformaton, and Database ystem Laboratory Department of Computer

More information

SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS

SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS SCALABLE AND VISUALIZATION-ORIENTED CLUSTERING FOR EXPLORATORY SPATIAL ANALYSIS J.H.Guan, F.B.Zhu, F.L.Ban a School of Computer, Spatal Informaton & Dgtal Engneerng Center, Wuhan Unversty, Wuhan, 430079,

More information

Palmprint Feature Extraction Using 2-D Gabor Filters

Palmprint 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 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

A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION

A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION ISSN: 0976-910(ONLINE) ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING, MAY 013, VOLUME: 03, ISSUE: 04 A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION A. Suruland 1, R. Reena

More information

Machine Learning. Topic 6: Clustering

Machine Learning. Topic 6: Clustering Machne Learnng Topc 6: lusterng lusterng Groupng data nto (hopefully useful) sets. Thngs on the left Thngs on the rght Applcatons of lusterng Hypothess Generaton lusters mght suggest natural groups. Hypothess

More information

Relevance Feedback for Image Retrieval

Relevance Feedback for Image Retrieval Vashal D Dhale et al, / (IJCSIT Internatonal Journal of Computer Scence and Informaton Technologes, Vol 4 (2, 203, 39-323 Relevance Feedback for Image Retreval Vashal D Dhale, Dr A R Mahaan, Prof Uma Thakur

More information

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

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

More information

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

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

KOHONEN'S SELF ORGANIZING NETWORKS WITH "CONSCIENCE"

KOHONEN'S SELF ORGANIZING NETWORKS WITH CONSCIENCE Kohonen's Self Organzng Maps and ther use n Interpretaton, Dr. M. Turhan (Tury) Taner, Rock Sold Images Page: 1 KOHONEN'S SELF ORGANIZING NETWORKS WITH "CONSCIENCE" By: Dr. M. Turhan (Tury) Taner, Rock

More information

A Robust Method for Estimating the Fundamental Matrix

A Robust Method for Estimating the Fundamental Matrix Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.

More information

A Resources Virtualization Approach Supporting Uniform Access to Heterogeneous Grid Resources 1

A Resources Virtualization Approach Supporting Uniform Access to Heterogeneous Grid Resources 1 A Resources Vrtualzaton Approach Supportng Unform Access to Heterogeneous Grd Resources 1 Cunhao Fang 1, Yaoxue Zhang 2, Song Cao 3 1 Tsnghua Natonal Labatory of Inforamaton Scence and Technology 2 Department

More information

3D Face Reconstruction With Local Feature Refinement

3D 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 information

A DATA ANALYSIS CODE FOR MCNP MESH AND STANDARD TALLIES

A DATA ANALYSIS CODE FOR MCNP MESH AND STANDARD TALLIES Supercomputng n uclear Applcatons (M&C + SA 007) Monterey, Calforna, Aprl 15-19, 007, on CD-ROM, Amercan uclear Socety, LaGrange Par, IL (007) A DATA AALYSIS CODE FOR MCP MESH AD STADARD TALLIES Kenneth

More information