CT Image Reconstruction in a Low Dimensional Manifold

Size: px
Start display at page:

Download "CT Image Reconstruction in a Low Dimensional Manifold"

Transcription

1 CT Image Reconstructon n a Low Dmensonal Manfol Wenxang Cong 1, Ge Wang 1, Qngsong Yang 1, Jang Hseh 3, Ja L, Rongje La 1 Bomecal Imagng Center, Department of Bomecal Engneerng, Department of Mathematcal scences Rensselaer Polytechnc Insttute, Troy, Y GE Healthcare Technologes, Waukesha, WI Abstract: Regularzaton methos are commonly use n X-ray CT mage reconstructon. Dfferent regularzaton methos reflect the characterzaton of fferent pror knowlege of mages. In a recent work, a new regularzaton metho calle a low-mensonal manfol moel (LDMM) s nvestgate to characterze the low-mensonal patch manfol structure of natural mages, where the manfol mensonalty characterzes structural nformaton of an mage. In ths paper, we propose a CT mage reconstructon metho base on the pror knowlege of the low-mensonal manfol of CT mage. Usng the clncal raw projecton ata from GE clnc, we conuct comparsons for the CT mage reconstructon among the propose metho, the smultaneous algebrac reconstructon technque (SART) wth the total varaton (TV) regularzaton, an the fltere back projecton (FBP) metho. Results show that the propose metho can successfully recover structural etals of an magng object, an acheve hgher spatal an contrast resoluton of the reconstructe mage than counterparts of FBP an SART wth TV. Key Wors: X-ray compute tomography (CT), mage reconstructon, fltere backprojecton (FBP), smultaneous algebrac reconstructon technque (SART), total varaton (TV), low mensonal manfol moel (LDMM). 1. Introucton X-ray compute tomography (CT) s a major magng moalty n mecal, securty, an nustral applcatons. The fltere back-projecton (FBP) s an effcent an robust metho for x-ray CT mage reconstructon [1], but t generates strong mage nose an artfacts n the cases of low-ose or ncomplete atasets. Extensve efforts have been mae to mprove mage qualty for practcal purposes [-4]. Iteratve methos ncorporate pror nformaton of mages, an offer stnct avantages over the analytc methos n cases of nosy an few-vew ata. The statstcal teratve methos moel the statstcs of photons to mprove the reconstructe mage qualty from the low-ose acqustons [4, 5]. Recently, the compressve sensng (CS) approach [6, 7] s apple for the mage reconstructon from less measurements than that requre by the yqust-shannon samplng theorem. Base on the CS theory, mage reconstructon algorthms were evelope for varous problems of CT mage reconstructon for mprovng mage qualty an reucng raaton ose, such as total varaton (TV) regularzaton [3, 5], nonlocal mean (LM) [, 8], ctonary learnng (DL) [9], pror mage constrane compresse sensng (PICCS) [10], an pror rank an sparsty moel (PRISM)-base mage reconstructon [11]. TV s a typcal sparse transform for an mage, an s a popular regularzaton form for mage

2 reconstructon ue to ts ablty to preserve mage eges. However, t s effectve only for reconstructon of pecewse constant mages an woul over-smoothen texture regons, whch may sacrfce mportant etals. LM explots a hgh egree of reunancy of an mage for e-nosng [8]. The smlarty s erve from ntensty fferences between neghborng patches of pxels or voxels. A non-lnear flter can be use to reuce mage nose by upatng each pxel value wth a weghte average of ts neghbors accorng to the smlarty of nvolve patches. DL buls aaptve sparse representaton elements from a tranng set of mages, an utlzes oman knowlege at a eeper level [9]. The ctonary tens to capture local mage features effectvely an helps mage enosng an feature nference. However, the structural fferences between a true mage an tranng mages coul affect the mage reconstructon qualty. PICSS regularzes mage reconstructon wth a pror mage nstea of mage patches [10]. PRISM combnes sparsty an low rank expectatons of an mage. All these methos were reporte wth varous egrees of success but no perfect soluton exsts that s suffcently accurate an robust, an further mprovement n mage qualty remans a popular topc. The ea of the propose X-ray CT mage reconstructon moel s nspre by a recent metho calle the lowmensonal manfol moel (LDMM) [1, 13]. Usng the mage patches scusse n nonlocal methos [13], the LDMM nterprets mage patches as a pont clou sample n a low-mensonal manfol embee n a hgh mensonal ambent space, whch proves a new way of regularzaton by mnmzng the menson of the corresponng mage patch manfol. Ths can be explane as a natural extenson of the ea of low-rank regularzaton for lnear objects to ata wth more complcate structures. Moreover, the authors n [1] elegantly fn that the pont-wsely efne manfol menson can be compute as a Drchlet energy of the coornate functons on the manfol, whose corresponng bounary value problem can be further solve by a pont ntegral metho propose n [14]. The LDMM performs very well n mage mprntng an super-resoluton. In ths paper, the regularzaton metho base on LDMM s propose for CT mage reconstructon. The patch manfol of mages s generally a low mensonal structure, an yet accommoates rch structural nformaton [13]. Usng the Bregman teraton [15], the propose reconstructon moel can be teratvely solve by a sequence of soft thresholng, Posson equatons prove by the Laplace-Beltram operator over a pont clou usng the pont ntegral metho [1], an upatng the patch manfol structure by renewng the K-nearest neghborhoo. The rest of the paper s organze as follows. In secton, we prove a etale escrpton for the propose X-ray CT mage reconstructon moel base on LDMM. A umercal algorthm s also esgne base on Bregman teraton. In secton 3, we perform the mage reconstructon for the clncal raw projecton ata from GE Clnc usng the propose LDMM-base reconstructon metho. In aton, we also conuct reconstructon comparsons wth results obtane from FBP an SART wth TV. Our numercal results valate the effectveness of the propose metho. After that, we conclue the paper n the last secton.. Image Reconstructon Metho In ths secton, we frst revew the statstcal moel of x-ray CT magng. After that, we wll scuss the propose moel of CT mage reconstructon base on LDMM an ts numercal algorthm.

3 .1. Statstcal Moel for X-ray CT magng In x-ray CT magng, the number of x-ray photons recore by a etector element s a ranom varable, whch obeys a Posson strbuton [1]: y y p y exp y. (1) y! The expectaton value of x-ray photons along a path l from x-ray source to -th etector element obeys Beer- Lambert law:, () where b s the number of x-ray photons etecte by -th etector element n the blank scannng (wthout any object n the beam path), an s the lnear attenuaton coeffcent of the object. To mplement the numercal computaton, Eq. () can be scretze as, y b expa μ (3) where μ s a vector compose of pxel values on mage of lnear attenuaton coeffcents, an A s the weghtng coeffcents of the pxel values on -th beam path. Snce ata are nepenent between etectors, the lkelhoo functon for x-ray photons probablty strbuton on etectors s, 1 y y PY μ exp-y, (4) y! T where Y,,,. Accorng to the Bayesan rule: P P P P y1 y y μ Y Y Y μ μ, the mage reconstructon task can be mplemente by maxmzng a posteror (MAP) strbuton P μy [5, 16]. From the monotonc property of the natural logarthm, the mage reconstructon can be reuce to followng mnmzaton problem [5]: where R P μ arg mn y y log y R μ, (5) 1 μ ln μ s a regularzaton term expressng the pror knowlege about the attenuaton mage μ, an s the total number of x-ray beam paths. In the context, we propose to use the low-menson of an mage as pror knowlege to conuct mage reconstructon, whch s scusse n the next Secton. After nsertng Eq. (3) n Eq. (5), a secon-orer approxmaton s apple to smplfy the complcate optmzaton to a quaratc optmzaton: b μ argmn Aμ y R μ (6) 1

4 .. Image Reconstructon algorthm usng LDMM Fg.1. The patch manfol of a CT mage (left) an the corresponng menson functon of the patch manfol wth patch sze 16X16 (rght). Let I enote an mage contane m n pxels: I I, j 1 m,1 j n, an P I enotes a patch of mage I, whch s a sub-mage of I wth sze of s1 s, s,,, here, P I I j s s j s j j s s j s the central coornates of the patch. An mage s ecompose nto a set of patches. These patches can be overlappng or nonoverlappng. Let enotes all patch set such that the unon of the patch set covers the whole mage, for example 1, s 1, s 1,, m 1, s 1, s 1,, n s an nex set of the patch. pont set n n 1 1 R wth a menson of s1 s. P I samples a low mensonal manfol PI P I can be also seen as a MI embee R, whch s calle the patch manfol of I as shown n the left mage of Fg. 1. The patch manfol s low mensonal for many natural mages [13]. In fact, for X-ray CT mages, ths low-mensonal structure of the patch manfol s also true. As an example llustrate n the rght mage of Fg. 1, we construct a patch manfol of a CT mage usng patchng sze 16X16. Ths leas to a pont clou, whch pont-wse menson s colorcoe on the mage. Base on ths assumpton, one natural regularzaton term s efne as the menson of the patch manfol to seekng etal structure nformaton for the mage reconstructon. Ths metho recovers the CT mage such that the menson of ts patch manfol s as small as possble. Therefore, the optmzaton moel Eq. (6) s reformulate for the measurement ata felty an the manfol mensonal quantfcaton: μ arg mn b A μ y m μ (7) 1 where m μ enotes the mensonalty of the patch manfol μ of an mage μ. Wth fferental geometry, the mensonalty of the patch manfol can be calculate by the coornate functon [1], m M x μ (8) 1

5 where s the embeng coornate functon efne by, 1,,, 1 x x, x,, x M R. Combnng Eqs. (7) an (8), we obtan x x, for any mn M,.., M b A μ y s t P M μ, (9) μ 1 1 where M s a manfol, an P μ s the patch set. The optmzaton (9) can be solve by alternatng recton teraton. Gven an ntal mage μ, the manfols M s establshe. Then optmzaton (9) s mplemente to upate the mage μ. From the reconstructe mage μ, the manfol s further upate, an mage reconstructon s performe. Ths process s repeate untl convergence of teratve proceure. The computaton of manfol from an mage s rect an easy. Gven the manfol M, the optmzaton problem Eq. (9) can be solve to compute the coornate functons 1,,, Bregman teraton [15]. an upate the mage μ usng the splt 1,,, arg mn M μ -, 1 μ arg mn b A μ y P μ - P μ Q, b F 1 k1 k Q Q P P c P P μ Q a μ - μ, (10) In the Bregman teraton, Eq. (10b) can be reuce to a l mnmzaton, whch can be solve usng the conjugate graent (CG) metho, whch prouces the exact soluton after a fnte number of teratons. The most ffcult task s to solve the optmzaton (10a) because t contans fferental of coornate functons. Applyng the stanar varaton metho, Eq. (10a) s equvalent to solvng followng Laplace-Beltram equaton. Mu x x y u y v y 0, x M y u x 0, x M n where n s the out normal of M, an M s the bounary of M. Recently, the pont ntegral metho has been propose to solve Laplace-Beltram equaton over a pont clou [Ref]. The man ea of the pont ntegral metho s to apply followng ntegral approxmaton for the fferental term n Laplace-Beltram equaton: where R, t 1 u y Mu yrt x, yy u x u yrt x, yy Rt x, yy t n (1) M M M x y are kernel functons gven as follows, (11)

6 x y Rt x, y Ct exp, 4t (13) where C t s a normalzng factor. Usng the ntegral approxmaton (1), followng ntegral equaton can be obtane to approxmate the Laplace-Beltram equaton, ux uyrtx yy t Rtx yu x u y,, 0 (14) M The ntegral equaton (14) can be further scretze nto a matrx equaton over the pont set P μ usng some quarature rule [1]: y L+ W U = W V L = D -W (15) where t M, j Rt x, x j,, j 1,,,, W j, j 1,,, s the weght matrx, j D ag 1,,, s a agnoss matrx. Thus, the optmzaton (10a) can be solve base on the matrx equaton (15). The etale formulaton an alternatng mnmzaton steps for solvng Eq. (10) are escrbe n the flowchart for Algorthm 1. Algorthm 1 Intalze an ntal mage, Q0 0 an parameters an ; j1 1: Whle the current soluton s not converge o : Compute the weght matrx W w, j, L D W, D ag, w j j from the patch mage P n, an the matrces 3: Solve the lnear systems: L W U WV n n V P μ Q n1 4: Upate by solvng the problem: μ argmn b A y U P Q μ μ 1 5: Upate n Q : n1 n n1 Q Q U P μ n F 6: En Whle 3. Image reconstructon results In the secton, we test the propose LDM-base reconstructon moel wth real patent atasets obtane on a GE clncal CT scanner. In aton, we also compare our results wth those obtane by the conventonal fltere back projecton (FBP) metho an the smultaneous algebrac reconstructon technque (SART) wth a

7 total varaton (TV). All numercal computatons n ths secton are mplemente by MATLAB n a PC wth 16G RAM an.8ghz CPU Smulaton result: A realstc phantom aapte from a human CT slce s use to evaluate the propose algorthms. We use an computerassste tomography smulaton envronment (CatSm) [17], whch was evelope by GE Global Research Center, to smulate x-ray magng. CatSm ncorporates polychromatcty, realstc quantum an electronc nose moels, fnte focal spot sze an shape, fnte etector cell sze, an etector cross-talk for the smulaton of real x-ray magng. All acqustons are smulate wth polychromatc x-ray source operate at 10 kvp an 0.mSv ose for the low ose magng. The raus of the scannng Fg. The snogram from CatSm. trajectory s 54.1cm. 984 projectons are unformly acqure over a 360-egree angular range. For each projecton, 888 etector elements are equangular strbute. The phantom s scretze nto a matrx, an the snogram s forme by stackng all projectons of fferent vews, as shown n Fg.. We perform mage reconstructon respectvely usng the propose LDM-base mage reconstructon, the smultaneous algebrac reconstructon technque (SART) wth a total varaton (TV) an FBP metho. The comparsons show that the LDM-base mage reconstructon moel s better than the other reconstructon metho, as shown n Fg. 3. (a) (b) (c) () Fg. 3: Comparson of CT reconstructon results over lung tumor. (a) Groun truth CT mages, (b) the reconstructe mage usng the propose metho; (c) the reconstructe mage usng SART wth TV, an () the reconstructe mage usng a FBP metho. 3.. Expermental results In ths ata set, the scan s n a typcal helcal geometry. After approprate preprocessng, we obtane a set of 64-slce fan-beam snograms, as shown n Fg. 3. The raus of the scannng trajectory s 54.1cm. Over a 360- egree angular range 984 projectons are unformly acqure. For each projecton, 888 etector elements were equangular strbute. The fel of vew (FOV) s of a 5 cm raus. The mage matrx was of pxels. Then, the snogram s forme by stackng all projectons of fferent vews, as shown n Fg. 4.

8 From the snogram, we frst conuct mage reconstructon usng the propose metho. As the mage llustrate n Fg.5 (a), the propose LDMbase mage reconstructon well preserves structural nformaton especally texture features. In our metho, we choose the patch sze of 16x16 to form the patch manfol an regularzaton parameters are chosen as 0.5 an 0.. For comparson, the FBP metho an the SART wth TV regularzaton are apple as well to perform the mage reconstructon from same projecton ataset, whose results are showe n Fg.5 (b-c), respectvely. The comparsons show that the LDM-base mage reconstructon moel outperforms the other two reconstructon Fg. 4. The snogram from a clncal scanner. methos. The mage reconstructe va only SART teraton wth TV s blurry. SART wth TV s sutable to reconstruct smple structural mages. For complex mecal mages, SART-TV over-smoothens texture regons, resultng n the loss of etals. FBP keeps the structural nformaton but t makes the reconstructe mage nosy. (a) (b) (c) Fg. 5. Comparson of CT mage reconstructons from raw patent ata. (a) The reconstructe mage usng the LDM-base metho, (b) the reconstructe mage usng SART wth TV, an (c) the reconstructe mage usng FPB. 4. Dscussons an Concluson The major contrbuton n ths paper s to present an mage reconstructon metho ae by the regularzaton of a low mensonal manfol (LDM) moel. Ths metho promses substantally ncrease spatal an contrast resoluton. Our teratve algorthm also ncorporates pror knowlege, an account for photon statstcs at a low ose level. However, the computatonal cost of the propose LDM-base mage reconstructon metho s

9 hgher than the SART teratve methos. Major computatonal cost s matrx-vector multplcaton operatons n the teratve algorthm. Ths problem can be solve by parallel computaton on GPU computer because matrxvector multplcaton s hghly ata parallel computaton. The computatonal spee of the propose teratve metho can be mprove on a GPU workstaton. The comparson between the propose metho an several representatve methos has been performe to llustrate the merts of the LDMM-base reconstructon approach. The raw atasets from a clncal CT scanner have been use to evaluate the mage qualty. Results show that the regularzaton metho of low mensonal manfol s an effcent an robust mage reconstructon technque, an well preserves mage eges an structural etals of the reconstructe mage comparng to the FBP metho an the SART wth TV regularzaton. Ths LDM-base approach s very promsng for mecal magng an other applcatons. Acknowlegment: Ths work s partally supporte by the atonal Insttutes of Health Grant IH/IBIB R01 EB an U01 EB R. La s work s partally supporte by the atonal Scence Founaton SF DMS References [1] A. C. Kak, an M. Slaney, Prncples of computerze tomographc magng, Phlaelpha: Socety for Inustral an Apple Mathematcs, 001. [] S. Ha, an K. Mueller, Low ose CT mage restoraton usng a atabase of mage patches, Phys Me Bol, vol. 60, no., pp , Jan 1, 015. [3] E. Y. Sky, Y. Duchn, X. Pan, an C. Ullberg, A constrane, total-varaton mnmzaton algorthm for low-ntensty x-ray CT, Me Phys, vol. 38 Suppl 1, pp. S117, Jul, 011. [4] I. A. Elbakr, an J. A. Fessler, Statstcal mage reconstructon for polyenergetc X-ray compute tomography, IEEE Trans Me Imagng, vol. 1, no., pp , Feb, 00. [5] J. Tang, B. E. ett, an G. H. Chen, Performance comparson between total varaton (TV)-base compresse sensng an statstcal teratve reconstructon algorthms, Phys Me Bol, vol. 54, no. 19, pp , Oct 07, 009. [6] E. J. Canes, J. Romberg, an T. Tao, Robust uncertanty prncples: Exact sgnal reconstructon from hghly ncomplete frequency nformaton, IEEE Transactons on Informaton Theory, vol. 5, no., pp , Feb, 006. [7] E. J. Canes, J. K. Romberg, an T. Tao, Stable sgnal recovery from ncomplete an naccurate measurements, Communcatons on Pure an Apple Mathematcs, vol. 59, no. 8, pp , Aug, 006. [8] T. Brox, O. Klenschmt, an D. Cremers, Effcent nonlocal means for enosng of textural patterns, IEEE Trans Image Process, vol. 17, no. 7, pp , Jul, 008. [9] Q. Xu, H. Yu, X. Mou, L. Zhang, J. Hseh, an G. Wang, Low-ose X-ray CT reconstructon va ctonary learnng, IEEE Trans Me Imagng, vol. 31, no. 9, pp , Sep, 01. [10] G. H. Chen, J. Tang, an S. Leng, Pror mage constrane compresse sensng (PICCS): a metho to accurately reconstruct ynamc CT mages from hghly unersample projecton ata sets, Me Phys, vol. 35, no., pp , Feb, 008. [11] H. Gao, H. Yu, S. Osher, an G. Wang, Mult-energy CT base on a pror rank, ntensty an sparsty moel (PRISM), Inverse Probl, vol. 7, no. 11, ov 01, 011. [1] S. Osher, Z. Sh, an W. Zhu, Low mensonal manfol moel for mage processng, UCLA Tech. Rep., no. CAM 16-04, 016. [13] G. Peyre, Manfol moels for sgnals an mages, Computer Vson an Image Unerstanng, vol. 113, no., pp , Feb, 009. [14] Z. L, Z. Sh, an J. Sun, Pont ntegral metho for solvng posson-type equatons on manfols from pont clous wth convergence guarantees, arxv vol , 014.

10 [15] T. Golsten, an S. Osher, The Splt Bregman Metho for L1-Regularze Problems, Sam Journal on Imagng Scences, vol., no., pp , 009. [16] B. De Man, J. uyts, P. Dupont, G. Marchal, an P. Suetens, An teratve maxmum-lkelhoo polychromatc algorthm for CT, Ieee Transactons on Mecal Imagng, vol. 0, no. 10, pp , Oct, 001. [17] B. De Man, S. Basu,. Chanra, B. Dunham, P. Ec, M. Iatrou, S. McOlash, P. Sanath, C. Shaughnessy, an B. Tower, "CatSm: a new computer assste tomography smulaton envronment." pp. 6510G-6510G-8.

A Model-Based Iterative Algorithm for Dual-Energy X-Ray CT Reconstruction

A Model-Based Iterative Algorithm for Dual-Energy X-Ray CT Reconstruction A Model-Based Iteratve Algorthm for Dual-Energy X-Ray CT Reconstructon Ruoqao Zhang, Jean-Baptste Thbault, Member, IEEE, Charles A. Bouman, Fellow, IEEE, Ken D. Sauer, Member, IEEE, and Jang Hseh, Senor

More information

The Objective Function Value Optimization of Cloud Computing Resources Security

The Objective Function Value Optimization of Cloud Computing Resources Security Open Journal of Optmzaton, 2015, 4, 40-46 Publshe Onlne June 2015 n ScRes. http://www.scrp.org/journal/ojop http://x.o.org/10.4236/ojop.2015.42005 The Objectve Functon Value Optmzaton of Clou Computng

More information

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications Effcent Loa-Balance IP Routng Scheme Base on Shortest Paths n Hose Moel E Ok May 28, 2009 The Unversty of Electro-Communcatons Ok Lab. Semnar, May 28, 2009 1 Outlne Backgroun on IP routng IP routng strategy

More information

Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach

Faces Recognition with Image Feature Weights and Least Mean Square Learning Approach Faces Recognton wth Image Feature Weghts an Least Mean Square Learnng Approach We-L Fang, Yng-Kue Yang an Jung-Kue Pan Dept. of Electrcal Engneerng, Natonal Tawan Un. of Sc. & Technology, Tape, Tawan Emal:

More information

Learning Depth from Single Still Images: Approximate Inference 1

Learning Depth from Single Still Images: Approximate Inference 1 Learnng Depth from Sngle Stll Images: Approxmate Inference 1 MS&E 211 course project Ashutosh Saxena, Ilya O. Ryzhov Channng Wong, Janln Wang June 7th, 2006 1 In ths report, Saxena, et. al. [1] somethng

More information

Statistical Interior Tomography

Statistical Interior Tomography Statstcal Interor Tomography Qong Xu a, Hengyong Yu b,c, Xuanqn Mou a, Ge Wang c,d a Insttute of Image processng and Pattern recognton, X'an Jaotong Unversty, X'an, Shaanx 70049, P.R.Chna b Dept. of Radology,

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

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

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method Internatonal Journal of Computatonal and Appled Mathematcs. ISSN 89-4966 Volume, Number (07), pp. 33-4 Research Inda Publcatons http://www.rpublcaton.com An Accurate Evaluaton of Integrals n Convex and

More information

Learning a Class-Specific Dictionary for Facial Expression Recognition

Learning a Class-Specific Dictionary for Facial Expression Recognition BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 4 Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-0067 Learnng a Class-Specfc Dctonary for

More information

High resolution 3D Tau-p transform by matching pursuit Weiping Cao* and Warren S. Ross, Shearwater GeoServices

High resolution 3D Tau-p transform by matching pursuit Weiping Cao* and Warren S. Ross, Shearwater GeoServices Hgh resoluton 3D Tau-p transform by matchng pursut Wepng Cao* and Warren S. Ross, Shearwater GeoServces Summary The 3D Tau-p transform s of vtal sgnfcance for processng sesmc data acqured wth modern wde

More information

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

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

More information

Wavefront Reconstructor

Wavefront Reconstructor A Dstrbuted Smplex B-Splne Based Wavefront Reconstructor Coen de Vsser and Mchel Verhaegen 14-12-201212 2012 Delft Unversty of Technology Contents Introducton Wavefront reconstructon usng Smplex B-Splnes

More information

Level set segmentation using image second order statistics

Level set segmentation using image second order statistics Level set segmentaton usng mage secon orer statstcs Bo Ma, Yuwe Wu, Pe L Bejng Laboratory of Intellgent Informaton Technology, School of omputer Scence, Bejng Insttute of Technology (BIT), Bejng, P.R.

More information

Smoothing Spline ANOVA for variable screening

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

More information

Discriminative Dictionary Learning with Pairwise Constraints

Discriminative Dictionary Learning with Pairwise Constraints Dscrmnatve Dctonary Learnng wth Parwse Constrants Humn Guo Zhuoln Jang LARRY S. DAVIS UNIVERSITY OF MARYLAND Nov. 6 th, Outlne Introducton/motvaton Dctonary Learnng Dscrmnatve Dctonary Learnng wth Parwse

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

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches Proceedngs of the Internatonal Conference on Cognton and Recognton Fuzzy Flterng Algorthms for Image Processng: Performance Evaluaton of Varous Approaches Rajoo Pandey and Umesh Ghanekar Department of

More information

Super-resolution with Nonlocal Regularized Sparse Representation

Super-resolution with Nonlocal Regularized Sparse Representation Super-resoluton wth Nonlocal Regularzed Sparse Representaton Wesheng Dong a, Guangmng Sh a, Le Zhang b, and Xaoln Wu c a Key Laboratory of Intellgent Percepton and Image Understandng (Chnese Mnstry of

More information

Reversible Digital Watermarking

Reversible Digital Watermarking Reversble Dgtal Watermarkng Chang-Tsun L Department of Computer Scence Unversty of Warwck Multmea Securty an Forenscs 1 Reversble Watermarkng Base on Dfference Expanson (DE) In some mecal, legal an mltary

More information

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

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

More information

CS 534: Computer Vision Model Fitting

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

More information

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

Image Deblurring and Super-resolution by Adaptive Sparse Domain Selection and Adaptive Regularization

Image Deblurring and Super-resolution by Adaptive Sparse Domain Selection and Adaptive Regularization Image Deblurrng and Super-resoluton by Adaptve Sparse Doman Selecton and Adaptve Regularzaton Wesheng Dong a,b, Le Zhang b,1, Member, IEEE, Guangmng Sh a, Senor Member, IEEE, and Xaoln Wu c, Senor Member,

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

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

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

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

More information

Support Vector Machines

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

More information

Mohammed El Hassouni DESTEC FLSHR, University of Mohammed V-Agdal- Rabat, Morocco

Mohammed El Hassouni DESTEC FLSHR, University of Mohammed V-Agdal- Rabat, Morocco (IJCSIS) Internatonal Journal of Computer Scence an Informaton Securty, Vol. 8, No., 00 3D-Mesh enosng usng an mprove vertex base ansotropc ffuson Mohamme El Hassoun DESTEC FLSHR, Unversty of Mohamme V-Agal-

More information

Solving two-person zero-sum game by Matlab

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

More information

The Research of Support Vector Machine in Agricultural Data Classification

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

More information

Nonlocally Centralized Sparse Representation for Image Restoration

Nonlocally Centralized Sparse Representation for Image Restoration Nonlocally Centralzed Sparse Representaton for Image Restoraton Wesheng Dong a, Le Zhang b,1, Member, IEEE, Guangmng Sh a, Senor Member, IEEE, and Xn L c, Senor Member, IEEE a Key Laboratory of Intellgent

More information

K-means Clustering Algorithm in Projected Spaces

K-means Clustering Algorithm in Projected Spaces K-means Clusterng Algorthm n Projecte paces Alssar NAER, Dens HAMAD.A.. -U..C.O 50 rue F. Busson, BP 699, 68 Calas, France Emal: nasser@lasl.unv-lttoral.fr Chaban NAR ebanese Unversty E.F Rue Al-Arz, rpol

More information

Image Retrieval using Dual Tree Complex Wavelet Transform

Image Retrieval using Dual Tree Complex Wavelet Transform Image Retreval usng Dual Tree Complex Wavelet Transform Sanjay Patl # an Sanjay Talbar $ # Assocate Professor, Jaywant College of Engg. an Management, K.M. Ga, Maharashtra, Ina E-mal: sanjayashr@reffmal.com

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

MODULE - 9 LECTURE NOTES 1 FUZZY OPTIMIZATION

MODULE - 9 LECTURE NOTES 1 FUZZY OPTIMIZATION Water Resources Systems Plannng an Management: vance Tocs Fuzzy Otmzaton MODULE - 9 LECTURE NOTES FUZZY OPTIMIZTION INTRODUCTION The moels scusse so far are crs an recse n nature. The term crs means chotonomous.e.,

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

Unsupervised Learning

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

More information

The Comparison of Calibration Method of Binocular Stereo Vision System Ke Zhang a *, Zhao Gao b

The Comparison of Calibration Method of Binocular Stereo Vision System Ke Zhang a *, Zhao Gao b 3rd Internatonal Conference on Materal, Mechancal and Manufacturng Engneerng (IC3ME 2015) The Comparson of Calbraton Method of Bnocular Stereo Vson System Ke Zhang a *, Zhao Gao b College of Engneerng,

More information

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Overvew 2 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Introducton Mult- Smulator MASIM Theoretcal Work and Smulaton Results Concluson Jay Wagenpfel, Adran Trachte Motvaton and Tasks Basc Setup

More information

Local Ridge Regression for Face Recognition

Local Ridge Regression for Face Recognition Local Rge Regresson for Face Recognton Hu Xue 1,2 Yulan Zhu 1 Songcan Chen *1,2 1 Department of Computer Scence & Engneerng, Nanjng Unversty of Aeronautcs & Astronautcs, 210016, Nanjng, P.R. Chna 2 State

More information

IMAGE reconstruction in positron emission tomography. ISWLS: Novel Algorithm for Image Reconstruction in PET

IMAGE reconstruction in positron emission tomography. ISWLS: Novel Algorithm for Image Reconstruction in PET IEEE TRASACTIOS O IFORMATIO TECHOLOGY I BIOMEDICIE, VOL. 00, O. 00, 2011 1 ISWLS: ovel Algorthm for Image Reconstructon n PET E. Karal, S. Pavlopoulos, S. Lambropoulou, and D. Koutsours Abstract The purpose

More information

A fast algorithm for color image segmentation

A fast algorithm for color image segmentation Unersty of Wollongong Research Onlne Faculty of Informatcs - Papers (Arche) Faculty of Engneerng and Informaton Scences 006 A fast algorthm for color mage segmentaton L. Dong Unersty of Wollongong, lju@uow.edu.au

More information

JOINT METAL ARTIFACT REDUCTION AND SEGMENTATION OF CT IMAGES USING DICTIONARY-BASED IMAGE PRIOR AND CONTINUOUS-RELAXED POTTS MODEL

JOINT METAL ARTIFACT REDUCTION AND SEGMENTATION OF CT IMAGES USING DICTIONARY-BASED IMAGE PRIOR AND CONTINUOUS-RELAXED POTTS MODEL JOINT METAL ARTIFACT REDUCTION AND SEGMENTATION OF CT IMAGES USING DICTIONARY-BASED IMAGE PRIOR AND CONTINUOUS-RELAXED POTTS MODEL Pengchong Jn, Dong Hye Ye, Charles A. Bouman School of Electrcal and Computer

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

Statistical models and regularization strategies in statistical image reconstruction of low-dose X-ray CT: a survey

Statistical models and regularization strategies in statistical image reconstruction of low-dose X-ray CT: a survey Statstcal models and regularzaton strateges n statstcal mage reconstructon of low-dose X-ray CT: a survey Hao Zhang 1,, Jng Wang 3, Janhua Ma 4, Hongbng Lu 5, and Zhengrong Lang 1, 1 Department of Radology,

More information

High-Boost Mesh Filtering for 3-D Shape Enhancement

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

More information

Power of Iterative Reconstruction

Power of Iterative Reconstruction Iteratve Reconstructon Methods n Computed Tomography J. Webster Stayman I-STAR Laboratory Dept. of Bomedcal Engneerng, Johns Hopkns Unversty Power of Iteratve Reconstructon FBP reconstructon Iteratve Reconstructon

More information

Nonlocal Mumford-Shah Model for Image Segmentation

Nonlocal Mumford-Shah Model for Image Segmentation for Image Segmentaton 1 College of Informaton Engneerng, Qngdao Unversty, Qngdao, 266000,Chna E-mal:ccluxaoq@163.com ebo e 23 College of Informaton Engneerng, Qngdao Unversty, Qngdao, 266000,Chna E-mal:

More information

Identifying Efficient Kernel Function in Multiclass Support Vector Machines

Identifying Efficient Kernel Function in Multiclass Support Vector Machines Internatonal Journal of Computer Applcatons (0975 8887) Volume 8 No.8, August 0 Ientfng Effcent Kernel Functon n Multclass Support Vector Machnes R.Sangeetha Ph.D Research Scholar Department of Computer

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

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

More information

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

Optimal Scheduling of Capture Times in a Multiple Capture Imaging System

Optimal Scheduling of Capture Times in a Multiple Capture Imaging System Optmal Schedulng of Capture Tmes n a Multple Capture Imagng System Tng Chen and Abbas El Gamal Informaton Systems Laboratory Department of Electrcal Engneerng Stanford Unversty Stanford, Calforna 9435,

More information

Novel Fuzzy logic Based Edge Detection Technique

Novel Fuzzy logic Based Edge Detection Technique Novel Fuzzy logc Based Edge Detecton Technque Aborsade, D.O Department of Electroncs Engneerng, adoke Akntola Unversty of Tech., Ogbomoso. Oyo-state. doaborsade@yahoo.com Abstract Ths paper s based on

More information

Categories and Subject Descriptors B.7.2 [Integrated Circuits]: Design Aids Verification. General Terms Algorithms

Categories and Subject Descriptors B.7.2 [Integrated Circuits]: Design Aids Verification. General Terms Algorithms 3. Fndng Determnstc Soluton from Underdetermned Equaton: Large-Scale Performance Modelng by Least Angle Regresson Xn L ECE Department, Carnege Mellon Unversty Forbs Avenue, Pttsburgh, PA 3 xnl@ece.cmu.edu

More information

BASIC PRINCIPLES OF ACOUSTIC EMISSION TOMOGRAPHY

BASIC PRINCIPLES OF ACOUSTIC EMISSION TOMOGRAPHY bstract BSIC PRINCIPLES OF COUSTIC EMISSION TOMOGRPHY FRNK SCHUBERT Fraunhofer-Insttute for Nondestructve Evaluaton (IZFP), Dresden, Germany The present paper descrbes the basc prncples of acoustc emsson

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

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

More information

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch Deep learnng s a good steganalyss tool when embeddng key s reused for dfferent mages, even f there s a cover source-msmatch Lonel PIBRE 2,3, Jérôme PASQUET 2,3, Dno IENCO 2,3, Marc CHAUMONT 1,2,3 (1) Unversty

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

Preconditioning Parallel Sparse Iterative Solvers for Circuit Simulation

Preconditioning Parallel Sparse Iterative Solvers for Circuit Simulation Precondtonng Parallel Sparse Iteratve Solvers for Crcut Smulaton A. Basermann, U. Jaekel, and K. Hachya 1 Introducton One mportant mathematcal problem n smulaton of large electrcal crcuts s the soluton

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

Segmentation in Echocardiographic Sequences Using Shape-Based Snake Model

Segmentation in Echocardiographic Sequences Using Shape-Based Snake Model Segmentaton n chocarographc Sequences Usng Shape-Base Snake Moel Chen Sheng 1, Yang Xn 1, Yao Lpng 2, an Sun Kun 2 1 Insttuton of Image Processng an Pattern Recognton, Shangha Jaotong Unversty, Shangha,

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

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

Very simple computational domains can be discretized using boundary-fitted structured meshes (also called grids)

Very simple computational domains can be discretized using boundary-fitted structured meshes (also called grids) Structured meshes Very smple computatonal domans can be dscretzed usng boundary-ftted structured meshes (also called grds) The grd lnes of a Cartesan mesh are parallel to one another Structured meshes

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

Hermite Splines in Lie Groups as Products of Geodesics

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

More information

An Investigation of Block-Sequential Algorithms in Statistical PET Image Reconstruction

An Investigation of Block-Sequential Algorithms in Statistical PET Image Reconstruction Journal of Medcal and Bologcal Engneerng, 4(): 77-83 77 An Investgaton of Bloc-Sequental Algorthms n Statstcal PET Image Reconstructon Chng-Han Hsu * Department of Nuclear Scence, Natonal Tsng Hua Unversty,

More information

A Study on Clustering for Clustering Based Image De-Noising

A Study on Clustering for Clustering Based Image De-Noising Journal of Informaton Systems and Telecommuncaton, Vol. 2, No. 4, October-December 2014 196 A Study on Clusterng for Clusterng Based Image De-Nosng Hossen Bakhsh Golestan* Department of Electrcal Engneerng,

More information

Super-resolution using Sparse Representations over Learned Dictionaries: Reconstruction of Brain Structure using Electron Microscopy

Super-resolution using Sparse Representations over Learned Dictionaries: Reconstruction of Brain Structure using Electron Microscopy Super-resoluton usng Sparse Representatons over Learned Dctonares: Reconstructon of Bran Structure usng Electron Mcroscopy Tao Hu, Juan Nunez-Iglesas, Shv Vtaladevun, Lou Scheffer, Shan Xu, Mehd Bolorzadeh,

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

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

Parallel Numerics. 1 Preconditioning & Iterative Solvers (From 2016)

Parallel Numerics. 1 Preconditioning & Iterative Solvers (From 2016) Technsche Unverstät München WSe 6/7 Insttut für Informatk Prof. Dr. Thomas Huckle Dpl.-Math. Benjamn Uekermann Parallel Numercs Exercse : Prevous Exam Questons Precondtonng & Iteratve Solvers (From 6)

More information

Dynamic wetting property investigation of AFM tips in micro/nanoscale

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

More information

A CLASS OF TRANSFORMED EFFICIENT RATIO ESTIMATORS OF FINITE POPULATION MEAN. Department of Statistics, Islamia College, Peshawar, Pakistan 2

A CLASS OF TRANSFORMED EFFICIENT RATIO ESTIMATORS OF FINITE POPULATION MEAN. Department of Statistics, Islamia College, Peshawar, Pakistan 2 Pa. J. Statst. 5 Vol. 3(4), 353-36 A CLASS OF TRANSFORMED EFFICIENT RATIO ESTIMATORS OF FINITE POPULATION MEAN Sajjad Ahmad Khan, Hameed Al, Sadaf Manzoor and Alamgr Department of Statstcs, Islama College,

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

Positive Semi-definite Programming Localization in Wireless Sensor Networks Postve Sem-defnte Programmng Localzaton n Wreless Sensor etworks Shengdong Xe 1,, Jn Wang, Aqun Hu 1, Yunl Gu, Jang Xu, 1 School of Informaton Scence and Engneerng, Southeast Unversty, 10096, anjng Computer

More information

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. *, NO. *, Dictionary Pair Learning on Grassmann Manifolds for Image Denoising

IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. *, NO. *, Dictionary Pair Learning on Grassmann Manifolds for Image Denoising IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. *, NO. *, 2015 1 Dctonary Par Learnng on Grassmann Manfolds for Image Denosng Xanhua Zeng, We Ban, We Lu, Jale Shen, Dacheng Tao, Fellow, IEEE Abstract Image

More information

RAPID CARDIAC MRI USING RANDOM RADIAL TRAJECTORIES S. M. EL-METWALLY 1, K. Z. ABD-ELMONIEM 2, A. M. YOUSSEF 1 AND Y. M.

RAPID CARDIAC MRI USING RANDOM RADIAL TRAJECTORIES S. M. EL-METWALLY 1, K. Z. ABD-ELMONIEM 2, A. M. YOUSSEF 1 AND Y. M. JOURNAL OF ENGINEERING AND APPLIED SCIENCE, VOL. 55, NO. 5, OCT. 008, PP. 44-456 FACULTY OF ENGINEERING, CAIRO UNIVERSITY requred k-space. Sparse MRI s a fast magng method based on undersampled k-space

More information

LECTURE : MANIFOLD LEARNING

LECTURE : MANIFOLD LEARNING LECTURE : MANIFOLD LEARNING Rta Osadchy Some sldes are due to L.Saul, V. C. Raykar, N. Verma Topcs PCA MDS IsoMap LLE EgenMaps Done! Dmensonalty Reducton Data representaton Inputs are real-valued vectors

More information

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

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

More information

S1 Note. Basis functions.

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

More information

Mixed Linear System Estimation and Identification

Mixed Linear System Estimation and Identification 48th IEEE Conference on Decson and Control, Shangha, Chna, December 2009 Mxed Lnear System Estmaton and Identfcaton A. Zymns S. Boyd D. Gornevsky Abstract We consder a mxed lnear system model, wth both

More information

Beijing , China

Beijing , China Nose Equvalent Counts Based Emsson Image Reconstructon Algorthm of Tomographc Gamma Scannng * WANG Ke( 王珂 ) 1,2, LI Zheng( 李政 ) 1,2; 1), FENG We( 冯伟 ) 1,2, HAN Dong( 韩冬 ) 1,2 1 Key Laboratory of Partcle

More information

Kernel Collaborative Representation Classification Based on Adaptive Dictionary Learning

Kernel Collaborative Representation Classification Based on Adaptive Dictionary Learning Internatonal Journal of Intellgent Informaton Systems 2018; 7(2): 15-22 http://www.scencepublshnggroup.com/j/js do: 10.11648/j.js.20180702.11 ISSN: 2328-7675 (Prnt); ISSN: 2328-7683 (Onlne) Kernel Collaboratve

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

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION 24 CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION The present chapter proposes an IPSO approach for multprocessor task schedulng problem wth two classfcatons, namely, statc ndependent tasks and

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

A Saturation Binary Neural Network for Crossbar Switching Problem

A Saturation Binary Neural Network for Crossbar Switching Problem A Saturaton Bnary Neural Network for Crossbar Swtchng Problem Cu Zhang 1, L-Qng Zhao 2, and Rong-Long Wang 2 1 Department of Autocontrol, Laonng Insttute of Scence and Technology, Benx, Chna bxlkyzhangcu@163.com

More information

Review of approximation techniques

Review of approximation techniques CHAPTER 2 Revew of appromaton technques 2. Introducton Optmzaton problems n engneerng desgn are characterzed by the followng assocated features: the objectve functon and constrants are mplct functons evaluated

More information

Monte Carlo Rendering

Monte Carlo Rendering Monte Carlo Renderng Last Tme? Modern Graphcs Hardware Cg Programmng Language Gouraud Shadng vs. Phong Normal Interpolaton Bump, Dsplacement, & Envronment Mappng Cg Examples G P R T F P D Today Does Ray

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

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

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

More information

REMOTE SENSING REQUIREMENTS DEVELOPMENT: A SIMULATION-BASED APPROACH

REMOTE SENSING REQUIREMENTS DEVELOPMENT: A SIMULATION-BASED APPROACH REMOTE SENSING REQUIREMENTS DEVEOPMENT: A SIMUATION-BASED APPROAC V. Zanon a, B. Davs a, R. Ryan b, G. Gasser c, S. Blonsk b a Earth Scence Applcatons Drectorate, Natonal Aeronautcs and Space Admnstraton,

More information

The ray density estimation of a CT system by a supervised learning algorithm

The ray density estimation of a CT system by a supervised learning algorithm Te ray densty estaton of a CT syste by a suervsed learnng algort Nae : Jongduk Baek Student ID : 5459 Toc y toc s to fnd te ray densty of a new CT syste by usng te learnng algort Background Snce te develoent

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

More information

Learned Primal-dual Reconstruction

Learned Primal-dual Reconstruction 1 Learned Prmal-dual Reconstructon Jonas Adler Ozan Öktem Department of Mathematcs, KTH - Royal Insttute of Technology Elekta AB, Box 7593, SE-103 93 Stockholm, Sweden Emal: {jonasadl, ozan}@kth.se arxv:1707.06474v2

More information

THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS

THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS U THE FAULT LOCATION ALGORITHM BASED ON TWO CIRCUIT FUNCTIONS Z. Czaa Char of Electronc Measurement, Faculty of Electroncs, Telecommuncatons an Informatcs, Techncal Unversty of Gañsk, Polan The paper presents

More information

CLASSIFICATION OF ULTRASONIC SIGNALS

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

More information

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET 1 BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET TZU-CHENG CHUANG School of Electrcal and Computer Engneerng, Purdue Unversty, West Lafayette, Indana 47907 SAUL B. GELFAND School

More information