Matching Images with Different Resolutions

Size: px
Start display at page:

Download "Matching Images with Different Resolutions"

Transcription

1 Matchng Images wth Dfferent Resolutons Yves Dufournaud, Cordela Schmd, Radu Horaud To cte ths verson: Yves Dufournaud, Cordela Schmd, Radu Horaud. Matchng Images wth Dfferent Resolutons. Internatonal Conference on Computer son & Pattern Recognton (CPR 00), Jun 000, Hlton Head Island, Unted States. IEEE Computer Socety,, pp., 000, < all.jsp?arnumber=>. <0.09/CPR.000.>. <nra-009> HAL Id: nra Submtted on 0 Dec 00 HAL s a mult-dscplnary open access archve for the depost and dssemnaton of scentfc research documents, whether they are publshed or not. The documents may come from teachng and research nsttutons n France or abroad, or from publc or prvate research centers. L archve ouverte plurdscplnare HAL, est destnée au dépôt et à la dffuson de documents scentfques de nveau recherche, publés ou non, émanant des établssements d ensegnement et de recherche franças ou étrangers, des laboratores publcs ou prvés.

2 Matchng Images wth Dfferent Resolutons Yves Dufournaud Cordela Schmd Radu Horaud INRIA RHÔNE-ALPES & GRAIR-CNRS av. de l Europe 0 Montbonnot, France Yves.Dufournaud@nralpes.fr Abstract In ths paper we address the problem of matchng two mages wth two dfferent resolutons: a hgh-resoluton mage and a low-resoluton one. On the premse that changes n resoluton act as a smoothng equvalent to changes n scale, a scale-space representaton of the hgh-resoluton mage s produced. Hence the one-to-one classcal mage matchng paradgm becomes one-to-many because the lowresoluton mage s compared wth all the scale-space representatons of the hgh-resoluton one. Key to the success of such a process s the proper representaton of the features to be matched n scale-space. We show how to extract nterest ponts at varable scales and we devse a method allowng the comparson of two mages at two dfferent resolutons. The method comprses the use of photometrc- and rotatonnvarant descrptors, a geometrc model mappng the hghresoluton mage onto a low-resoluton mage regon, and an mage matchng strategy based on the robust estmaton of ths geometrc model. Extensve experments show that our matchng method can be used for scale changes up to a factor. Introducton The problem of matchng two mages has been an actve topc of research n computer vson for the last two decades. The vast majorty of exstng methods consder two vews of the same scene where the vewponts dffer by small offsets n poston, orentaton and vewng parameters such as focal length. Under such condtons, the mages assocated wth the two vews have comparatve reso- Y. Dufournaud acknowledges support from Aerospatale. Fgure. An example of matchng a lowresoluton mage wth a hgh-resoluton one. lutons and hence they encapsulate scene features at approxmatvely the same scale. In ths paper we address a somehow dfferent problem that has only lttle been addressed n the past. We consder for matchng two mages wth very dfferent resolutons. More precsely, f we denote by the approxmate dstance from an observed scene object to a vewpont and by the focal length assocated wth the vewng parameters, the mage resoluton may be defned as or more generally as a functon of. Therefore we are nterested n developng a matchng technque whch takes as nput a low resoluton mage, mage #, and a hgh resoluton mage, mage #, such that ther assocated resolutons and satsfy the constrant. In practce t wll be shown that, usng the approach advocated below, t s possble to match two mages such that. As an example we consder the mage par n Fgure. Both mages were taken wth a camera placed at klometers (.9 mles) away from the top of the mountan. For the frst mage (left) we used a focal length equal to mm whle for the second one (rght) we used a focal length equal to mm. Notce that the hgh-resoluton mage corresponds to a small regon of the low-resoluton one and t

3 s qute dffcult to fnd the exact poston and sze of ths regon. Clearly, a scene object and/or texture may appear at dfferent szes and postons n the two mages. Therefore, the search space assocated wth the featureto-feature matchng of two such mages s larger and more complex than the one assocated wth the classcal stereo matchng paradgm. The classcal approach to mage matchng extracts nterestng pont-features from each mage, matches them based on cross-correlaton, computes the eppolar geometry through the robust estmaton of the fundamental matrx, and establshes many other matches once ths matrx s known. For a number of reasons, ths method cannot be appled anymore:. Pont-feature extracton and matchng are resoluton dependent processes.. The hgh-resoluton mage corresponds to a small regon of the low-resoluton one and hence the latter contans many features whch do not have a match n the former.. It may be dffcult to estmate the eppolar geometry because there s not enough depth assocated wth the hgh resoluton mage. The soluton suggested n ths paper conssts of consderng a scale-space representaton of the hgh-resoluton mage and of matchng the low-resoluton mage aganst the scale-space descrpton of the hgh-resoluton one. A scalespace representaton may be obtaned by smoothng an mage wth Gaussan kernels of ncreasng standard devatons. Therefore, the hgh-resoluton mage wll be descrbed by a dscrete set of mages at varous scales. On the premse that decreasng the resoluton can be modeled as a smoothng equvalent to a scale change, the one-to-one mage matchng problem at hand becomes a one-to-many mage matchng problem. In ths paper we descrbe such a matchng method. Key to ts success are the followng features: The scale-space representaton of nterest ponts together wth ther assocated descrptors. A geometrc model descrbng the mappng from the hgh-resoluton mage to the low-resoluton one. An mage-matchng strategy whch combnes pont-topont assgnments wth a robust estmaton of the geometrc mappng. Several authors addressed the problem of matchng two mages gathered from two very dfferent ponts of vew [,, 9] but they dd not consder a change n resoluton. The use of scale-space n conjuncton wth stereo matchng has been restrcted to herarchcal matchng: correspondences obtaned at low resoluton constran the search space at hgher resolutons [,, 0]. Scale-space propertes are thoroughly studed n [] and the same author attempted to characterze the best scale at whch an mage feature should be represented []. A smlar dea s presented n [] to detect stable ponts n scale space. Our work s closely related wth [] whch attempts to match two mages of the same object gathered wth two dfferent zoom settngs. Pont-to-pont correspondences are characterzed n scale space by correlaton traces. The method s able to recover the scale factor for whch two mage ponts are the most smlar but t cannot deal wth camera rotatons. Image descrptors that are nvarant wth respect to local affne greyvalue changes, mage rotatons, and mage translatons were studed theoretcal n [9] and an effcent mplementaton was proposed n []. These descrptors are based on convolutons wth Gaussan kernels and ther dervatves. They are therefore consstent wth scale-space representatons. They are best appled to nterest ponts and a recent study showed that the Harrs corner detector s the most relable one []. However, they are not scalenvarant and, n spte of good theoretcal models for such nvarants [, ], t s more judcous from a practcal pont of vew to compute local descrptors at varous scales n a dscrete scale-space []. Paper organzaton. The remander of ths paper s organzed as follows. Secton brefly outlnes the geometrc model assocated wth the mage par. Secton suggests a framework for adaptng the detecton of nterest ponts to scale changes. Secton descrbes the hgh-resoluton to low-resoluton matchng and secton presents results. Geometrc modelng One of the key observatons enablng the matchng of two mages at two dfferent resolutons s that the hghresoluton mage corresponds to a small regon of the lowresoluton one. Hence, one reasonable assumpton s to consder that the mappng between the hgh resoluton mage and the correspondng low-resoluton regon s a plane projectve transformaton,.e., the scene correspondng to ths regon s planar. Such a homography may well be represented by a homogeneous full rank matrx H. Let be a pont n the frst mage (low resoluton) and be a pont n the second mage (hgh resoluton). One can characterze a regon n the low-resoluton mage such that the

4 GF >. = > : $ GF <; > $ $ > m $ r m ponts wthn ths regon verfy: H () Smlarly, ponts outsde ths regon, say do not verfy ths equaton. In the general case t s qute tedous to fnd a parameterzaton of H. Moreover, mage descrptors whch are nvarant to such a general plane-to-plane projectve transformaton are dffcult to compute and therefore t s dffcult to properly select potental canddate ponts satsfyng eq. (). We can further smplfy the geometrc model and consder a restrcted class of homographes, namely a rotaton about the optcal axs, a translaton, and a scale factor:! "#%$'&)(+*-,.'$/*0!, $'*0, $'&)(*, 9 9 : () Notce that the projectve equalty n eq. () s replaced by an equalty and two pont-to-pont correspondences are suffcent to lnearly estmate such a smlarty transformaton. In practce t wll be useful to replace the -vectors and used above by -vectors = and =?> such that: A@BDCE: IH =:J and K L@BMCE > Wth ths notaton, eq. () becomes =?>Q NH =O> :PJ R=SRUT where R s the rotaton matrx and T s the translaton assocated wth the mage transformaton. Ideally, one would lke to characterze mage ponts by descrptors nvarant to mage rotaton, translaton and scale. Unfortunately, as already outlned, scale-nvarant mage descrptors are hard to compute n practce. Therefore, the matchng strategy wll buld a dscrete scale space on top of the hgh-resoluton mage thus by-passng the scale-nvarance problem. The mage matchng problem at hand becomes the problem of () extractng sets of ponts from the two mages, =W YX[Z\Z[Z)X=?]_^ and =?> X\Z[Z\Z[X=`>ab^, () properly characterzng these ponts such that pont-to-pont correspondences are allowed, and () determnng the largest set of such correspondences compatble wth a homography between the hgh-resoluton mage and a low-resoluton regon. Scale-space nterest pont detecton In order to match two mages one has to defne a measure of smlarty. One possble defnton s correlaton. In our case, ths can be wrtten as: c dfe+gh $ R =. d ^^. d ^kj where l s $ a wndow around =. Therefore, one must fnd a scale factor and a rotaton matrx R for whch the expresson above s mnmzed. The search space assocated wth such a technque s very large and the assocated non-lnear mnmzaton procedure has problems. Alternatvely, one may use nterest ponts whch are detected by a rotaton-nvarant operator and characterze these ponts by rotaton-nvarant descrptors. Such an nterest pont detector was proposed n []. More precsely, consder an mage pont = and the assocated mage greyvalue =W^. Interest ponts are detected by:. Compute the mage dervatves n the C and E drectons,, and \m. These computatons are carred out by convoluton wth the dfferental of a Gaussan kernel of standard devaton n.. Form the auto-correlaton matrx. Ths matrx C =oxpnqxr ns^ averages dervatves n a wndow around a ns^ s used for weghtng : pont =. A Gaussan t C =oxnqxr ns^o ut ns^vxw r =oxpny^ =oxny^ m =oxny^ [m =oxpny^{z (). = s an nterest pont f the matrx C has two sgnfcant egenvalues, that s f the determnant and trace of ths matrx verfy: -}[~ C^.U trace C^f () where s a fxed threshold and a parameter. Notce that the nterest pont detector defned above s rotaton-nvarant ths s due to the symmetry of matrx C. However, $ IT IS NOT nvarant to a change n the mage sze or mage resoluton. Wthout loss of generalty we can therefore omt the mage-plane rotaton at nterest ponts detected by the operator descrbed above. Under the assumpton that the greyvalues are properly normalzed, the smlarty condton that must be satsfed s > =O>^o =W^ where, as before, s the hgh-resoluton mage and > s the low resoluton one. Snce the rotaton s omtted we have =O>s =ƒr T. Takng the dervatves of the above expresson $ wth respect to the mage coordnates and E, we obtan and C $. m Therefore, the relatonshp between the nterest pont detector appled to the hgh-resoluton mage and the nterest pont detector appled to the low-resoluton mage s: C> = > X nqx ny^? r : $ C =oxnqxr ns^

5 : t m : m : We consder now the scale-space assocated wth the hgh resoluton mage. The scale-space s obtaned by convolvng the ntal mage wth a Gaussan kernel who s standard devaton s ncreasng monotoncally, say n wth. At some scale n ths space the hgh resoluton mage s gven by: =oxp ny^o =W^ v t =oxˆ [ny^ At ths scale, the mage s frst order dervatves wrte: =oxp ny^? =W^v t =oxˆ [ny^ =oxp ny^? =W^v t =oxˆ [ny^ m Therefore, one can detect nterest ponts at any scale by smply replacng n wth n n eqs. () and (). If the task conssts of matchng the hgh-resoluton mage wth the low-resoluton one >, t s crucal to select the scale of at whch ths matchng has $ to be performed. The scale $ must absorb the sze rato, therefore one may wrte. The nterest pont detector at scale s defned by: C =oxp nqxˆ r nš^o r ns^ v w =oxp ny^ =oxp ny^ m =oxˆ ny^ m =oxp ny^ z () In order to llustrate the results obtaned wth ths scalespace nterest pont detector, we appled t to the hghresoluton mage of Fgure (rght) at scales,.e.,, and. Fgure shows these results where n and nb uœ r. s= s= Robust mage matchng s= The scale-space extracton and representaton of nterest ponts that are rotaton-nvarant wll enable us to devse the one-to-many mage matchng technque descrbed below. The man dea s to compare the low-resoluton mage at one scale wth the hgh-resoluton mage at many scales. Hence, the scale at whch ths matchng process provdes the best results, provdes the correct one-to-one assgnments between nterest ponts. Because the matchng s supported by the robust estmaton of a homography between the two mages, the estmated parameters wll provde among others the resoluton rato between the two mages. Wthout loss of generalty, we assume that the hghresoluton mage, mage #, s represented at dfferent scales n, n,..., n wth n. At each scale, nterest ponts are extracted usng eq. (). Furthermore, a number of dfferental nvarants are extracted at each scale as well. These descrptors are photometrc-, mage rotaton-, and mage translaton-nvarant. Lkewse, nterest ponts and ther descrptors are computed and assocated wth the low-resoluton mage, mage #, at only one scale, n. Fgure. Interest ponts detected at scales. s=

6 We then consder one-by-one the scale-space representatons of mage # and attempt to fnd whch one of these mages best matches a regon n mage #. Snce there s a strong relatonshp between scale and resoluton, one may assume that the scale of the best match corresponds to the resoluton rato between mages # and #. s= At each scale one-to-one correspondences are determned by drect comparson of the descrptors assocated wth the nterest ponts. In practce there are such descrptors lmted to thrd-order dervatves of the ntensty sgnal. These descrptors are nvarant to mage rotaton as well as local affne changes of llumnaton. Two such -vector descrptors are compared usng the Mahalanobs dstance. Ths dstance requres the covarance matrx assocated wth each descrptor. Ths matrx encapsulates sgnal nose, varatons n photometry, naccuracy of nterest pont locaton, and so forth. s estmated statstcally over a large set of mage samples. In order to solve as many ambgutes as possble, each one-to-one assgnment thus establshed s checked for local coherence. Namely, for each one of the two ponts n an assgnment we consder ther neghbors and check whether the two groups of ponts n the two neghborhoods are mutually compatble. Ths local compatblty check based on local geometrc dstrbuton has a cost [] but t s worth the effort because t allows to elmnate spurous matches. The pont matchng process just descrbed s appled at scales. Next, we have to evaluate the qualty of mage-tomage matchngs based on these pont matches n order to select the scale assocated wth the best match. We therefore estmate a mappng between the two mages as defned by eq. () and use robust statstcs [, ]. Once an approxmate scale has been selected usng the strategy just descrbed, a robust estmator takes as nput the potental one-to-one pont assgnments, computes the best homography between the two mages, and splts the pont assgnments nto two sets: () nlers,.e. ponts lyng n the small regon correspondng to the homography mappng of the hgh resoluton mage onto the low resoluton one and () outlers,.e. ponts that are ether outsde ths regon or msmatched ponts nsde the regon. Commonly used robust estmators nclude M-estmators, least-medan-squares (LMedS), and RANdom SAmple Consensus (RANSAC). In our case, the number of outlers may be qute large. Ths occurs n partcular when the two mages have very dfferent resolutons and hence only 0% or less of the low-resoluton mage corresponds to the hgh resoluton one. Therefore, we ruled out M-estmators because they tolerate only a few outlers. Among the two remanng technques, we preferred RANSAC because t allows the user to defne n advance the number of potental outlers through the selecton of a threshold. Hence, ths s= s= 0 s= Fgure. Pont-to-pont assgnments obtaned at four scales. threshold can be chosen as a functon of the scale factor. Detals concernng threshold selecton can be found n []. Experments The matchng strategy just descrbed was appled and tested over a large number of mage pars where the resoluton factor between the two mages vared from to. Here we present three examples. The fnal result of applyng the matchng to the par of Fgure s shown n Fgure. Let us explan n detal how ths type of result s obtaned for another example, e.g. Table and Fgures and. Interest ponts are frst extracted from the low-resoluton mage at one scale ( ) and from the hgh-resoluton mage at dfferent scales ( to ). Therefore, eght mage matchngs are performed. The result of pont-to-pont matchng s shown on Fgure at four dfferent scales:,,, and. Obvously scale and scale have the best matches assocated wth them and scale s a better canddate. Therefore, :

7 Fgure. The hgh-resoluton mage s mapped onto the low-resoluton one usng the homography consstent wth pont-to-pont assgnments. Resoluton factor No. of ponts No. of matches Predcted Computed Intal guess Inlers Outlers (%) %. 90 % 0 % 0 % 9 % Table. Ths table shows, at each scale, the computed resoluton factor, the number of ponts n the hgh-resoluton mage, the number of potental matches, the fnal number of matches, and the percentage of outlers. Notce that scales and yeld very smlar results. Conclusons In ths paper we presented a new method for matchng two mages wth two dfferent resolutons. We showed that t s enough to represent the hgh-resoluton mage n scalespace and we descrbed a one-to-many robust mage matchng strategy. Key to the success of ths method s the scalespace representaton of nterest ponts. In spte of a huge number of publcatons n the magematchng doman, t seems to us that none of the exstng methods s able to deal wth large changes n resoluton. Here we have been able to match mages wth a resoluton factor of. In practce the mages shown n ths paper were gathered by varyng the focal length usng the zoom-lens of a dgtal camcorder. The advent of dgtal photography opens new felds of applcatons and we beleve that our matchng technque wll allow the smultaneous explotaton of multple vewponts and varable resoluton. t would have been suffcent to run the robust matchng algorthm at scale only. In practce we run the latter algorthm at all the scales and dsplayed the results n Table. Thus we can verfy that the best match s, ndeed, obtaned at _. Out of ponts detected at ths scale, of them have a potental assgnment n the low-resoluton mage and of them are fnally selected by the robust matchng technque. The latter rejected 0% of the matches. Fnally the homography thus obtaned was appled to the hgh resoluton mage and ths mage s reproduced on top of the lowresoluton one (cf. Fgure ). A thrd example s dsplayed on Fgure. References [] G. Csurka, D. Demrdjan, and R. Horaud. Fndng the collneaton between two projectve reconstructons. CIU, ():0, 999. [] M. Fschler and R. Bolles. Random sample consensus: A paradgm for model fttng wth applcatons to mage analyss and automated cartography. Graphcs and Image Processng, (): 9, 9. [] N. Georgs, M. Petrou, and J. Kttler. On the correspondence problem for wde angular separaton of non-coplanar ponts. IC, :, 99.

8 Fgure. The fnal result obtaned for the second mage par at scale. All of the matches are correct. [] F. Glazer, G. Reynolds, and P. Anandan. Scene matchng by herarchcal correlaton. In CPR, 9. [] B. B. Hansen and B. S. Morse. Multscale mage regstraton usng scale trace correlaton. In CPR, 999. [] C. Harrs and M. Stephens. A combned corner and edge detector. In Alvey son Conference, 9. [] R. Horaud and T. Skordas. Stereo matchng through feature groupng and maxmal clques. PAMI,(): 0, 99. [] J. Koendernk. The structure of mages. Bologcal Cybernetcs, 0: 9, 9. [9] J. Koendernk and A. van Doorn. Representaton of local geometry n the vsual system. Bologcal Cybernetcs, :, 9. [0] M. S. Lew and T. S. Huang. Optmal mult-scale matchng. In CPR, 999. [] T. Lndeberg. Scale-Space Theory n Computer son. Kluwer Academc Publshers, 99. [] T. Lndeberg. Feature detecton wth automatc scale selecton. IJC, 0():9, 99. [] D. G. Lowe. Object recognton from local scale-nvarant features. In ICC, 999. [] P. Meer, D. Mntz, A. Rosenfeld, and D. Km. Robust regresson methods for computer vson: a revew. IJC, ():9 0, 99. [] P. Prtchett and A. Zsserman. Wde baselne stereo matchng. In ICC, 99. [] L. H. Quam. Herarchcal warp stereo. In Readng n computer son, pages 0. Morgan Kaufman, 9. [] C. Schmd and R. Mohr. Local grayvalue nvarants for mage retreval. PAMI, 9():0, 99. [] C. Schmd, R. Mohr, and C. Bauckhage. Comparng and evaluatng nterest ponts. In ICC, 99. [9] T. Tuytelaars, L.. Gool, L. D haene, and R. Koch. Matchng of affnely nvarant regons for vsual servong. In ICRA, Fgure. An other example wth

Face Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching)

Face Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching) Face Recognton Problem Face Verfcaton Problem Face Verfcaton (1:1 matchng) Querymage face query Face Recognton (1:N matchng) database Applcaton: Access Control www.vsage.com www.vsoncs.com Bometrc Authentcaton

More information

L10: Linear discriminants analysis

L10: Linear discriminants analysis L0: Lnear dscrmnants analyss Lnear dscrmnant analyss, two classes Lnear dscrmnant analyss, C classes LDA vs. PCA Lmtatons of LDA Varants of LDA Other dmensonalty reducton methods CSCE 666 Pattern Analyss

More information

How To Understand The Results Of The German Meris Cloud And Water Vapour Product

How To Understand The Results Of The German Meris Cloud And Water Vapour Product Ttel: Project: Doc. No.: MERIS level 3 cloud and water vapour products MAPP MAPP-ATBD-ClWVL3 Issue: 1 Revson: 0 Date: 9.12.1998 Functon Name Organsaton Sgnature Date Author: Bennartz FUB Preusker FUB Schüller

More information

An Alternative Way to Measure Private Equity Performance

An Alternative Way to Measure Private Equity Performance An Alternatve Way to Measure Prvate Equty Performance Peter Todd Parlux Investment Technology LLC Summary Internal Rate of Return (IRR) s probably the most common way to measure the performance of prvate

More information

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis

The Development of Web Log Mining Based on Improve-K-Means Clustering Analysis The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.

More information

An Enhanced Super-Resolution System with Improved Image Registration, Automatic Image Selection, and Image Enhancement

An Enhanced Super-Resolution System with Improved Image Registration, Automatic Image Selection, and Image Enhancement An Enhanced Super-Resoluton System wth Improved Image Regstraton, Automatc Image Selecton, and Image Enhancement Yu-Chuan Kuo ( ), Chen-Yu Chen ( ), and Chou-Shann Fuh ( ) Department of Computer Scence

More information

Support Vector Machines

Support Vector Machines Support Vector Machnes Max Wellng Department of Computer Scence Unversty of Toronto 10 Kng s College Road Toronto, M5S 3G5 Canada wellng@cs.toronto.edu Abstract Ths s a note to explan support vector machnes.

More information

8.5 UNITARY AND HERMITIAN MATRICES. The conjugate transpose of a complex matrix A, denoted by A*, is given by

8.5 UNITARY AND HERMITIAN MATRICES. The conjugate transpose of a complex matrix A, denoted by A*, is given by 6 CHAPTER 8 COMPLEX VECTOR SPACES 5. Fnd the kernel of the lnear transformaton gven n Exercse 5. In Exercses 55 and 56, fnd the mage of v, for the ndcated composton, where and are gven by the followng

More information

v a 1 b 1 i, a 2 b 2 i,..., a n b n i.

v a 1 b 1 i, a 2 b 2 i,..., a n b n i. SECTION 8.4 COMPLEX VECTOR SPACES AND INNER PRODUCTS 455 8.4 COMPLEX VECTOR SPACES AND INNER PRODUCTS All the vector spaces we have studed thus far n the text are real vector spaces snce the scalars are

More information

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ).

benefit is 2, paid if the policyholder dies within the year, and probability of death within the year is ). REVIEW OF RISK MANAGEMENT CONCEPTS LOSS DISTRIBUTIONS AND INSURANCE Loss and nsurance: When someone s subject to the rsk of ncurrng a fnancal loss, the loss s generally modeled usng a random varable or

More information

How To Calculate The Accountng Perod Of Nequalty

How To Calculate The Accountng Perod Of Nequalty Inequalty and The Accountng Perod Quentn Wodon and Shlomo Ytzha World Ban and Hebrew Unversty September Abstract Income nequalty typcally declnes wth the length of tme taen nto account for measurement.

More information

Brigid Mullany, Ph.D University of North Carolina, Charlotte

Brigid Mullany, Ph.D University of North Carolina, Charlotte Evaluaton And Comparson Of The Dfferent Standards Used To Defne The Postonal Accuracy And Repeatablty Of Numercally Controlled Machnng Center Axes Brgd Mullany, Ph.D Unversty of North Carolna, Charlotte

More information

Forecasting the Direction and Strength of Stock Market Movement

Forecasting the Direction and Strength of Stock Market Movement Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems

More information

Causal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting

Causal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting Causal, Explanatory Forecastng Assumes cause-and-effect relatonshp between system nputs and ts output Forecastng wth Regresson Analyss Rchard S. Barr Inputs System Cause + Effect Relatonshp The job of

More information

Vision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION

Vision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION Vson Mouse Saurabh Sarkar a* a Unversty of Cncnnat, Cncnnat, USA ABSTRACT The report dscusses a vson based approach towards trackng of eyes and fngers. The report descrbes the process of locatng the possble

More information

GRAVITY DATA VALIDATION AND OUTLIER DETECTION USING L 1 -NORM

GRAVITY DATA VALIDATION AND OUTLIER DETECTION USING L 1 -NORM GRAVITY DATA VALIDATION AND OUTLIER DETECTION USING L 1 -NORM BARRIOT Jean-Perre, SARRAILH Mchel BGI/CNES 18.av.E.Beln 31401 TOULOUSE Cedex 4 (France) Emal: jean-perre.barrot@cnes.fr 1/Introducton The

More information

Single and multiple stage classifiers implementing logistic discrimination

Single and multiple stage classifiers implementing logistic discrimination Sngle and multple stage classfers mplementng logstc dscrmnaton Hélo Radke Bttencourt 1 Dens Alter de Olvera Moraes 2 Vctor Haertel 2 1 Pontfíca Unversdade Católca do Ro Grande do Sul - PUCRS Av. Ipranga,

More information

Recurrence. 1 Definitions and main statements

Recurrence. 1 Definitions and main statements Recurrence 1 Defntons and man statements Let X n, n = 0, 1, 2,... be a MC wth the state space S = (1, 2,...), transton probabltes p j = P {X n+1 = j X n = }, and the transton matrx P = (p j ),j S def.

More information

An interactive system for structure-based ASCII art creation

An interactive system for structure-based ASCII art creation An nteractve system for structure-based ASCII art creaton Katsunor Myake Henry Johan Tomoyuk Nshta The Unversty of Tokyo Nanyang Technologcal Unversty Abstract Non-Photorealstc Renderng (NPR), whose am

More information

The OC Curve of Attribute Acceptance Plans

The OC Curve of Attribute Acceptance Plans The OC Curve of Attrbute Acceptance Plans The Operatng Characterstc (OC) curve descrbes the probablty of acceptng a lot as a functon of the lot s qualty. Fgure 1 shows a typcal OC Curve. 10 8 6 4 1 3 4

More information

8 Algorithm for Binary Searching in Trees

8 Algorithm for Binary Searching in Trees 8 Algorthm for Bnary Searchng n Trees In ths secton we present our algorthm for bnary searchng n trees. A crucal observaton employed by the algorthm s that ths problem can be effcently solved when the

More information

Project Networks With Mixed-Time Constraints

Project Networks With Mixed-Time Constraints Project Networs Wth Mxed-Tme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa

More information

Damage detection in composite laminates using coin-tap method

Damage detection in composite laminates using coin-tap method Damage detecton n composte lamnates usng con-tap method S.J. Km Korea Aerospace Research Insttute, 45 Eoeun-Dong, Youseong-Gu, 35-333 Daejeon, Republc of Korea yaeln@kar.re.kr 45 The con-tap test has the

More information

A Multi-mode Image Tracking System Based on Distributed Fusion

A Multi-mode Image Tracking System Based on Distributed Fusion A Mult-mode Image Tracng System Based on Dstrbuted Fuson Ln zheng Chongzhao Han Dongguang Zuo Hongsen Yan School of Electroncs & nformaton engneerng, X an Jaotong Unversty X an, Shaanx, Chna Lnzheng@malst.xjtu.edu.cn

More information

Can Auto Liability Insurance Purchases Signal Risk Attitude?

Can Auto Liability Insurance Purchases Signal Risk Attitude? Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang

More information

+ + + - - This circuit than can be reduced to a planar circuit

+ + + - - This circuit than can be reduced to a planar circuit MeshCurrent Method The meshcurrent s analog of the nodeoltage method. We sole for a new set of arables, mesh currents, that automatcally satsfy KCLs. As such, meshcurrent method reduces crcut soluton to

More information

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic

Institute of Informatics, Faculty of Business and Management, Brno University of Technology,Czech Republic Lagrange Multplers as Quanttatve Indcators n Economcs Ivan Mezník Insttute of Informatcs, Faculty of Busness and Management, Brno Unversty of TechnologCzech Republc Abstract The quanttatve role of Lagrange

More information

A machine vision approach for detecting and inspecting circular parts

A machine vision approach for detecting and inspecting circular parts A machne vson approach for detectng and nspectng crcular parts Du-Mng Tsa Machne Vson Lab. Department of Industral Engneerng and Management Yuan-Ze Unversty, Chung-L, Tawan, R.O.C. E-mal: edmtsa@saturn.yzu.edu.tw

More information

Conversion between the vector and raster data structures using Fuzzy Geographical Entities

Conversion between the vector and raster data structures using Fuzzy Geographical Entities Converson between the vector and raster data structures usng Fuzzy Geographcal Enttes Cdála Fonte Department of Mathematcs Faculty of Scences and Technology Unversty of Combra, Apartado 38, 3 454 Combra,

More information

What is Candidate Sampling

What is Candidate Sampling What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble

More information

Traffic State Estimation in the Traffic Management Center of Berlin

Traffic State Estimation in the Traffic Management Center of Berlin Traffc State Estmaton n the Traffc Management Center of Berln Authors: Peter Vortsch, PTV AG, Stumpfstrasse, D-763 Karlsruhe, Germany phone ++49/72/965/35, emal peter.vortsch@ptv.de Peter Möhl, PTV AG,

More information

where the coordinates are related to those in the old frame as follows.

where the coordinates are related to those in the old frame as follows. Chapter 2 - Cartesan Vectors and Tensors: Ther Algebra Defnton of a vector Examples of vectors Scalar multplcaton Addton of vectors coplanar vectors Unt vectors A bass of non-coplanar vectors Scalar product

More information

Calculating the high frequency transmission line parameters of power cables

Calculating the high frequency transmission line parameters of power cables < ' Calculatng the hgh frequency transmsson lne parameters of power cables Authors: Dr. John Dcknson, Laboratory Servces Manager, N 0 RW E B Communcatons Mr. Peter J. Ncholson, Project Assgnment Manager,

More information

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..

More information

) of the Cell class is created containing information about events associated with the cell. Events are added to the Cell instance

) of the Cell class is created containing information about events associated with the cell. Events are added to the Cell instance Calbraton Method Instances of the Cell class (one nstance for each FMS cell) contan ADC raw data and methods assocated wth each partcular FMS cell. The calbraton method ncludes event selecton (Class Cell

More information

A Secure Password-Authenticated Key Agreement Using Smart Cards

A Secure Password-Authenticated Key Agreement Using Smart Cards A Secure Password-Authentcated Key Agreement Usng Smart Cards Ka Chan 1, Wen-Chung Kuo 2 and Jn-Chou Cheng 3 1 Department of Computer and Informaton Scence, R.O.C. Mltary Academy, Kaohsung 83059, Tawan,

More information

Point cloud to point cloud rigid transformations. Minimizing Rigid Registration Errors

Point cloud to point cloud rigid transformations. Minimizing Rigid Registration Errors Pont cloud to pont cloud rgd transformatons Russell Taylor 600.445 1 600.445 Fall 000-014 Copyrght R. H. Taylor Mnmzng Rgd Regstraton Errors Typcally, gven a set of ponts {a } n one coordnate system and

More information

Exhaustive Regression. An Exploration of Regression-Based Data Mining Techniques Using Super Computation

Exhaustive Regression. An Exploration of Regression-Based Data Mining Techniques Using Super Computation Exhaustve Regresson An Exploraton of Regresson-Based Data Mnng Technques Usng Super Computaton Antony Daves, Ph.D. Assocate Professor of Economcs Duquesne Unversty Pttsburgh, PA 58 Research Fellow The

More information

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College

Feature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure

More information

MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION

MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION MACHINE VISION SYSTEM FOR SPECULAR SURFACE INSPECTION: USE OF SIMULATION PROCESS AS A TOOL FOR DESIGN AND OPTIMIZATION R. SEULIN, F. MERIENNE and P. GORRIA Laboratore Le2, CNRS FRE2309, EA 242, Unversté

More information

Illumination Normalization for Robust Face Recognition Against Varying Lighting Conditions

Illumination Normalization for Robust Face Recognition Against Varying Lighting Conditions llumnaton Normalzaton for Robust Face Recognton Aganst Varyng Lghtng Condtons Shguang Shan, Wen Gao, Bo Cao, Debn Zhao C-SVSON JDL, nsttute of Computng echnology, CAS, P.O.Box 274, Beng, Chna, 18 Computer

More information

Distributed Multi-Target Tracking In A Self-Configuring Camera Network

Distributed Multi-Target Tracking In A Self-Configuring Camera Network Dstrbuted Mult-Target Trackng In A Self-Confgurng Camera Network Crstan Soto, B Song, Amt K. Roy-Chowdhury Department of Electrcal Engneerng Unversty of Calforna, Rversde {cwlder,bsong,amtrc}@ee.ucr.edu

More information

Fault tolerance in cloud technologies presented as a service

Fault tolerance in cloud technologies presented as a service Internatonal Scentfc Conference Computer Scence 2015 Pavel Dzhunev, PhD student Fault tolerance n cloud technologes presented as a servce INTRODUCTION Improvements n technques for vrtualzaton and performance

More information

2. Existing work about dissymmetry. 3. The computation of dissymmetry maps. 3.1. Symmetry, chirality and mid-plane

2. Existing work about dissymmetry. 3. The computation of dissymmetry maps. 3.1. Symmetry, chirality and mid-plane Statstcal Analyss of Normal and Abnormal Dssymmetry n Volumetrc Medcal Images Jean-Phlppe Thron, Sylvan Prma, Gérard Subsol EPIDAURE Project, INRIA 2004, route des Lucoles, BP 93 06902 Sopha Antpols Cedex,

More information

BERNSTEIN POLYNOMIALS

BERNSTEIN POLYNOMIALS On-Lne Geometrc Modelng Notes BERNSTEIN POLYNOMIALS Kenneth I. Joy Vsualzaton and Graphcs Research Group Department of Computer Scence Unversty of Calforna, Davs Overvew Polynomals are ncredbly useful

More information

Loop Parallelization

Loop Parallelization - - Loop Parallelzaton C-52 Complaton steps: nested loops operatng on arrays, sequentell executon of teraton space DECLARE B[..,..+] FOR I :=.. FOR J :=.. I B[I,J] := B[I-,J]+B[I-,J-] ED FOR ED FOR analyze

More information

Luby s Alg. for Maximal Independent Sets using Pairwise Independence

Luby s Alg. for Maximal Independent Sets using Pairwise Independence Lecture Notes for Randomzed Algorthms Luby s Alg. for Maxmal Independent Sets usng Parwse Independence Last Updated by Erc Vgoda on February, 006 8. Maxmal Independent Sets For a graph G = (V, E), an ndependent

More information

Inter-Ing 2007. INTERDISCIPLINARITY IN ENGINEERING SCIENTIFIC INTERNATIONAL CONFERENCE, TG. MUREŞ ROMÂNIA, 15-16 November 2007.

Inter-Ing 2007. INTERDISCIPLINARITY IN ENGINEERING SCIENTIFIC INTERNATIONAL CONFERENCE, TG. MUREŞ ROMÂNIA, 15-16 November 2007. Inter-Ing 2007 INTERDISCIPLINARITY IN ENGINEERING SCIENTIFIC INTERNATIONAL CONFERENCE, TG. MUREŞ ROMÂNIA, 15-16 November 2007. UNCERTAINTY REGION SIMULATION FOR A SERIAL ROBOT STRUCTURE MARIUS SEBASTIAN

More information

Ring structure of splines on triangulations

Ring structure of splines on triangulations www.oeaw.ac.at Rng structure of splnes on trangulatons N. Vllamzar RICAM-Report 2014-48 www.rcam.oeaw.ac.at RING STRUCTURE OF SPLINES ON TRIANGULATIONS NELLY VILLAMIZAR Introducton For a trangulated regon

More information

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol

CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK. Sample Stability Protocol CHOLESTEROL REFERENCE METHOD LABORATORY NETWORK Sample Stablty Protocol Background The Cholesterol Reference Method Laboratory Network (CRMLN) developed certfcaton protocols for total cholesterol, HDL

More information

A DATA MINING APPLICATION IN A STUDENT DATABASE

A DATA MINING APPLICATION IN A STUDENT DATABASE JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul

More information

Efficient Project Portfolio as a tool for Enterprise Risk Management

Efficient Project Portfolio as a tool for Enterprise Risk Management Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse

More information

CHAPTER 14 MORE ABOUT REGRESSION

CHAPTER 14 MORE ABOUT REGRESSION CHAPTER 14 MORE ABOUT REGRESSION We learned n Chapter 5 that often a straght lne descrbes the pattern of a relatonshp between two quanttatve varables. For nstance, n Example 5.1 we explored the relatonshp

More information

Multi-Scale Banking to 45º

Multi-Scale Banking to 45º Mult-Scale Bankng to 45º Jeffrey Heer and Maneesh Agrawala Abstract In hs text Vsualzng Data, Wllam Cleveland demonstrates how the aspect rato of a lne chart can affect an analyst s percepton of trends

More information

1.1 The University may award Higher Doctorate degrees as specified from time-to-time in UPR AS11 1.

1.1 The University may award Higher Doctorate degrees as specified from time-to-time in UPR AS11 1. HIGHER DOCTORATE DEGREES SUMMARY OF PRINCIPAL CHANGES General changes None Secton 3.2 Refer to text (Amendments to verson 03.0, UPR AS02 are shown n talcs.) 1 INTRODUCTION 1.1 The Unversty may award Hgher

More information

Parallel Numerical Simulation of Visual Neurons for Analysis of Optical Illusion

Parallel Numerical Simulation of Visual Neurons for Analysis of Optical Illusion 212 Thrd Internatonal Conference on Networkng and Computng Parallel Numercal Smulaton of Vsual Neurons for Analyss of Optcal Illuson Akra Egashra, Shunj Satoh, Hdetsugu Ire and Tsutomu Yoshnaga Graduate

More information

"Research Note" APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES *

Research Note APPLICATION OF CHARGE SIMULATION METHOD TO ELECTRIC FIELD CALCULATION IN THE POWER CABLES * Iranan Journal of Scence & Technology, Transacton B, Engneerng, ol. 30, No. B6, 789-794 rnted n The Islamc Republc of Iran, 006 Shraz Unversty "Research Note" ALICATION OF CHARGE SIMULATION METHOD TO ELECTRIC

More information

CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES

CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES In ths chapter, we wll learn how to descrbe the relatonshp between two quanttatve varables. Remember (from Chapter 2) that the terms quanttatve varable

More information

Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch

Bypassing Synthesis: PLS for Face Recognition with Pose, Low-Resolution and Sketch Bypassng Synthess: PLS for Face Recognton wth Pose, Low-Resoluton and Setch Abhshe Sharma Insttute of Advanced Computer Scence Unversty of Maryland, USA bhoaal@umacs.umd.edu Davd W Jacobs Insttute of Advanced

More information

Liptracking and MPEG4 Animation with Feedback Control

Liptracking and MPEG4 Animation with Feedback Control Lptrackng and MPEG4 Anmaton wth Feedback Control Brce Beaumesnl, Franck Luthon, Marc Chaumont To cte ths verson: Brce Beaumesnl, Franck Luthon, Marc Chaumont. Lptrackng and MPEG4 Anmaton wth Feedback Control.

More information

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters

Frequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters Frequency Selectve IQ Phase and IQ Ampltude Imbalance Adjustments for OFDM Drect Converson ransmtters Edmund Coersmeer, Ernst Zelnsk Noka, Meesmannstrasse 103, 44807 Bochum, Germany edmund.coersmeer@noka.com,

More information

An Algorithm for Data-Driven Bandwidth Selection

An Algorithm for Data-Driven Bandwidth Selection IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 2, FEBRUARY 2003 An Algorthm for Data-Drven Bandwdth Selecton Dorn Comancu, Member, IEEE Abstract The analyss of a feature space

More information

DEFINING %COMPLETE IN MICROSOFT PROJECT

DEFINING %COMPLETE IN MICROSOFT PROJECT CelersSystems DEFINING %COMPLETE IN MICROSOFT PROJECT PREPARED BY James E Aksel, PMP, PMI-SP, MVP For Addtonal Informaton about Earned Value Management Systems and reportng, please contact: CelersSystems,

More information

Using Series to Analyze Financial Situations: Present Value

Using Series to Analyze Financial Situations: Present Value 2.8 Usng Seres to Analyze Fnancal Stuatons: Present Value In the prevous secton, you learned how to calculate the amount, or future value, of an ordnary smple annuty. The amount s the sum of the accumulated

More information

Stochastic Protocol Modeling for Anomaly Based Network Intrusion Detection

Stochastic Protocol Modeling for Anomaly Based Network Intrusion Detection Stochastc Protocol Modelng for Anomaly Based Network Intruson Detecton Juan M. Estevez-Tapador, Pedro Garca-Teodoro, and Jesus E. Daz-Verdejo Department of Electroncs and Computer Technology Unversty of

More information

Generation of High-Resolution Mosaic for Photo-Realistic Texture-Mapping of Cultural Heritage 3D Models

Generation of High-Resolution Mosaic for Photo-Realistic Texture-Mapping of Cultural Heritage 3D Models The 5th Internatonal Symposum on Vrtual Realty, Archaeology and Cultural Hertage VAST (004) K. Can, Y. Chrysanthou, F. Nccolucc, N. Slberman (Edtors) Generaton of Hgh-Resoluton Mosac for Photo-Realstc

More information

Fast Fuzzy Clustering of Web Page Collections

Fast Fuzzy Clustering of Web Page Collections Fast Fuzzy Clusterng of Web Page Collectons Chrstan Borgelt and Andreas Nürnberger Dept. of Knowledge Processng and Language Engneerng Otto-von-Guercke-Unversty of Magdeburg Unverstätsplatz, D-396 Magdeburg,

More information

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12

PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 12 14 The Ch-squared dstrbuton PSYCHOLOGICAL RESEARCH (PYC 304-C) Lecture 1 If a normal varable X, havng mean µ and varance σ, s standardsed, the new varable Z has a mean 0 and varance 1. When ths standardsed

More information

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network

Forecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network 700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School

More information

A study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns

A study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns A study on the ablty of Support Vector Regresson and Neural Networks to Forecast Basc Tme Seres Patterns Sven F. Crone, Jose Guajardo 2, and Rchard Weber 2 Lancaster Unversty, Department of Management

More information

Eye Center Localization on a Facial Image Based on Multi-Block Local Binary Patterns

Eye Center Localization on a Facial Image Based on Multi-Block Local Binary Patterns Eye Center Localzaton on a Facal Image Based on Mult-Bloc Local Bnary Patterns Anatoly tn, Vladmr Khryashchev, Olga Stepanova Yaroslavl State Unversty Yaroslavl, Russa anatolyntnyar@gmal.com, vhr@yandex.ru,

More information

Hallucinating Multiple Occluded CCTV Face Images of Different Resolutions

Hallucinating Multiple Occluded CCTV Face Images of Different Resolutions In Proc. IEEE Internatonal Conference on Advanced Vdeo and Sgnal based Survellance (AVSS 05), September 2005 Hallucnatng Multple Occluded CCTV Face Images of Dfferent Resolutons Ku Ja Shaogang Gong Computer

More information

Linear Circuits Analysis. Superposition, Thevenin /Norton Equivalent circuits

Linear Circuits Analysis. Superposition, Thevenin /Norton Equivalent circuits Lnear Crcuts Analyss. Superposton, Theenn /Norton Equalent crcuts So far we hae explored tmendependent (resste) elements that are also lnear. A tmendependent elements s one for whch we can plot an / cure.

More information

An Empirical Study of Search Engine Advertising Effectiveness

An Empirical Study of Search Engine Advertising Effectiveness An Emprcal Study of Search Engne Advertsng Effectveness Sanjog Msra, Smon School of Busness Unversty of Rochester Edeal Pnker, Smon School of Busness Unversty of Rochester Alan Rmm-Kaufman, Rmm-Kaufman

More information

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals

Automated information technology for ionosphere monitoring of low-orbit navigation satellite signals Automated nformaton technology for onosphere montorng of low-orbt navgaton satellte sgnals Alexander Romanov, Sergey Trusov and Alexey Romanov Federal State Untary Enterprse Russan Insttute of Space Devce

More information

Vehicle Detection and Tracking in Video from Moving Airborne Platform

Vehicle Detection and Tracking in Video from Moving Airborne Platform Journal of Computatonal Informaton Systems 10: 12 (2014) 4965 4972 Avalable at http://www.jofcs.com Vehcle Detecton and Trackng n Vdeo from Movng Arborne Platform Lye ZHANG 1,2,, Hua WANG 3, L LI 2 1 School

More information

SIMPLE LINEAR CORRELATION

SIMPLE LINEAR CORRELATION SIMPLE LINEAR CORRELATION Smple lnear correlaton s a measure of the degree to whch two varables vary together, or a measure of the ntensty of the assocaton between two varables. Correlaton often s abused.

More information

1. Measuring association using correlation and regression

1. Measuring association using correlation and regression How to measure assocaton I: Correlaton. 1. Measurng assocaton usng correlaton and regresson We often would lke to know how one varable, such as a mother's weght, s related to another varable, such as a

More information

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services

An Evaluation of the Extended Logistic, Simple Logistic, and Gompertz Models for Forecasting Short Lifecycle Products and Services An Evaluaton of the Extended Logstc, Smple Logstc, and Gompertz Models for Forecastng Short Lfecycle Products and Servces Charles V. Trappey a,1, Hsn-yng Wu b a Professor (Management Scence), Natonal Chao

More information

Learning from Multiple Outlooks

Learning from Multiple Outlooks Learnng from Multple Outlooks Maayan Harel Department of Electrcal Engneerng, Technon, Hafa, Israel She Mannor Department of Electrcal Engneerng, Technon, Hafa, Israel maayanga@tx.technon.ac.l she@ee.technon.ac.l

More information

Descriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications

Descriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications CMSC828G Prncples of Data Mnng Lecture #9 Today s Readng: HMS, chapter 9 Today s Lecture: Descrptve Modelng Clusterng Algorthms Descrptve Models model presents the man features of the data, a global summary

More information

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS

INVESTIGATION OF VEHICULAR USERS FAIRNESS IN CDMA-HDR NETWORKS 21 22 September 2007, BULGARIA 119 Proceedngs of the Internatonal Conference on Informaton Technologes (InfoTech-2007) 21 st 22 nd September 2007, Bulgara vol. 2 INVESTIGATION OF VEHICULAR USERS FAIRNESS

More information

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT

APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT APPLICATION OF PROBE DATA COLLECTED VIA INFRARED BEACONS TO TRAFFIC MANEGEMENT Toshhko Oda (1), Kochro Iwaoka (2) (1), (2) Infrastructure Systems Busness Unt, Panasonc System Networks Co., Ltd. Saedo-cho

More information

Addendum to: Importing Skill-Biased Technology

Addendum to: Importing Skill-Biased Technology Addendum to: Importng Skll-Based Technology Arel Bursten UCLA and NBER Javer Cravno UCLA August 202 Jonathan Vogel Columba and NBER Abstract Ths Addendum derves the results dscussed n secton 3.3 of our

More information

A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking

A Multi-Camera System on PC-Cluster for Real-time 3-D Tracking The 23 rd Conference of the Mechancal Engneerng Network of Thaland November 4 7, 2009, Chang Ma A Mult-Camera System on PC-Cluster for Real-tme 3-D Trackng Vboon Sangveraphunsr*, Krtsana Uttamang, and

More information

Enabling P2P One-view Multi-party Video Conferencing

Enabling P2P One-view Multi-party Video Conferencing Enablng P2P One-vew Mult-party Vdeo Conferencng Yongxang Zhao, Yong Lu, Changja Chen, and JanYn Zhang Abstract Mult-Party Vdeo Conferencng (MPVC) facltates realtme group nteracton between users. Whle P2P

More information

How Sets of Coherent Probabilities May Serve as Models for Degrees of Incoherence

How Sets of Coherent Probabilities May Serve as Models for Degrees of Incoherence 1 st Internatonal Symposum on Imprecse Probabltes and Ther Applcatons, Ghent, Belgum, 29 June 2 July 1999 How Sets of Coherent Probabltes May Serve as Models for Degrees of Incoherence Mar J. Schervsh

More information

ADVERTISEMENT FOR THE POST OF DIRECTOR, lim TIRUCHIRAPPALLI

ADVERTISEMENT FOR THE POST OF DIRECTOR, lim TIRUCHIRAPPALLI ADVERTSEMENT FOR THE POST OF DRECTOR, lm TRUCHRAPPALL The ndan nsttute of Management Truchrappall (MT), establshed n 2011 n the regon of Taml Nadu s a leadng management school n nda. ts vson s "Preparng

More information

Reconstruction of High Resolution 3D Objects from Incomplete Images and 3D Information

Reconstruction of High Resolution 3D Objects from Incomplete Images and 3D Information Internatonal Journal of Artfcal Intellgence and Interactve Multmeda, Vol. 2, Nº 6 Reconstructon of Hgh Resoluton 3D Objects from Incomplete Images and 3D Informaton Alexander Pacheco 1, Holman Bolívar

More information

Gender Classification for Real-Time Audience Analysis System

Gender Classification for Real-Time Audience Analysis System Gender Classfcaton for Real-Tme Audence Analyss System Vladmr Khryashchev, Lev Shmaglt, Andrey Shemyakov, Anton Lebedev Yaroslavl State Unversty Yaroslavl, Russa vhr@yandex.ru, shmaglt_lev@yahoo.com, andrey.shemakov@gmal.com,

More information

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING

ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING Matthew J. Lberatore, Department of Management and Operatons, Vllanova Unversty, Vllanova, PA 19085, 610-519-4390,

More information

Section 5.4 Annuities, Present Value, and Amortization

Section 5.4 Annuities, Present Value, and Amortization Secton 5.4 Annutes, Present Value, and Amortzaton Present Value In Secton 5.2, we saw that the present value of A dollars at nterest rate per perod for n perods s the amount that must be deposted today

More information

1 Example 1: Axis-aligned rectangles

1 Example 1: Axis-aligned rectangles COS 511: Theoretcal Machne Learnng Lecturer: Rob Schapre Lecture # 6 Scrbe: Aaron Schld February 21, 2013 Last class, we dscussed an analogue for Occam s Razor for nfnte hypothess spaces that, n conjuncton

More information

Support vector domain description

Support vector domain description Pattern Recognton Letters 20 (1999) 1191±1199 www.elsever.nl/locate/patrec Support vector doman descrpton Davd M.J. Tax *,1, Robert P.W. Dun Pattern Recognton Group, Faculty of Appled Scence, Delft Unversty

More information

J. Parallel Distrib. Comput.

J. Parallel Distrib. Comput. J. Parallel Dstrb. Comput. 71 (2011) 62 76 Contents lsts avalable at ScenceDrect J. Parallel Dstrb. Comput. journal homepage: www.elsever.com/locate/jpdc Optmzng server placement n dstrbuted systems n

More information

Properties of Indoor Received Signal Strength for WLAN Location Fingerprinting

Properties of Indoor Received Signal Strength for WLAN Location Fingerprinting Propertes of Indoor Receved Sgnal Strength for WLAN Locaton Fngerprntng Kamol Kaemarungs and Prashant Krshnamurthy Telecommuncatons Program, School of Informaton Scences, Unversty of Pttsburgh E-mal: kakst2,prashk@ptt.edu

More information

Snake-Based Segmentation of Teeth from Virtual Dental Casts

Snake-Based Segmentation of Teeth from Virtual Dental Casts 1 Snake-Based Segmentaton of Teeth from Vrtual Dental Casts Thomas Kronfeld, Davd Brunner and Gudo Brunnett Chemntz Unversty of Technology, Germany, {tkro, brunner, brunnett}@cs.tu-chemntz.de ABSTRACT

More information

Web Object Indexing Using Domain Knowledge *

Web Object Indexing Using Domain Knowledge * Web Object Indexng Usng Doman Knowledge * Muyuan Wang Department of Automaton Tsnghua Unversty Bejng 100084, Chna (86-10)51774518 Zhwe L, Le Lu, We-Yng Ma Mcrosoft Research Asa Sgma Center, Hadan Dstrct

More information

A New Technique for Vehicle Tracking on the Assumption of Stratospheric Platforms. Department of Civil Engineering, University of Tokyo **

A New Technique for Vehicle Tracking on the Assumption of Stratospheric Platforms. Department of Civil Engineering, University of Tokyo ** Fuse, Taash A New Technque for Vehcle Tracng on the Assumton of Stratosherc Platforms Taash FUSE * and Ehan SHIMIZU ** * Deartment of Cvl Engneerng, Unversty of Toyo ** Professor, Deartment of Cvl Engneerng,

More information

An MILP model for planning of batch plants operating in a campaign-mode

An MILP model for planning of batch plants operating in a campaign-mode An MILP model for plannng of batch plants operatng n a campagn-mode Yanna Fumero Insttuto de Desarrollo y Dseño CONICET UTN yfumero@santafe-concet.gov.ar Gabrela Corsano Insttuto de Desarrollo y Dseño

More information