Hybrid MPI-OpenMP Parallelization Of Image Reconstruction

Size: px
Start display at page:

Download "Hybrid MPI-OpenMP Parallelization Of Image Reconstruction"

Transcription

1 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH Hybrid MPI-OpenMP Parallelization Of Iage Recontruction Jinliang Wan College of Coputer and Inforation Engineering, Henan Univerity of Econoic and Law Zhengzhou, China Eail: Yanhui Liu State Key Laboratory for Seiic Reduction/Control & Structural Safety (Cultivation), Guangzhou Univerity Guangzhou, China Eail: Abtract Perceptual coding hould take full advantage of the reult fro huan viual yte (HVS) tudie. In thi paper, we exploit an iage recontruction algorith, which can iply and reliably repreent iage uing regional hape and texture inforation and effectually eliinate perceptual redundancy. But real-tie application of the algorith i liited due to it inherent coplex and intenive coputation. Therefore, we ipleent iage recontruction with a hybrid eage paing interface (MPI) and OpenMP approach on the bai of a tandard MPI ipleentation. Experiental reult confir our iage recontruction algorith can get optial retoration reult. Copared with JPEG and JPEG000 copreion, thi algorith can not only get ore coding gain but reain ot inforation people care. Our hybrid MPI-OpenMP approach can ignificantly iprove tie perforance of iage recontruction algorith. Index Ter huan viual yte, iage recontruction, parallel proceing I. INTRODUCTION The aintrea of iage coding chee i baed on hybrid coding fraework integrated with three clae of traditional technologie. Tranfor coding, prediction coding and entropy coding are ued to reduce and reove patial redundancy, teporal redundancy and tatitic redundancy. But huan eye are the terinal receptor for iage, and thu there till i a lot of perceptual redundant inforation according to the characteritic of huan viual yte (HVS). However, it i difficult to achieve additional ignificant progre for copreion efficiency becaue of the liitation of pixel-baed iage repreentation [6]. Therefore, how to find a ore efficient iage repreentation ethod ha alway been coding cientit ardent puruit. The econd-generation iage coding technique were propoed by Kunt [], which can take advantage of the huan viual perceptual characteritic. In recent year, with the etablihent and developent of the wavelet tranfor theory [], fractal theory [3, 4] and viual iulation theory [5], Iage proceing ha been coniderable developent. And, actually any till iage contain aive texture like gra, brick, cloud, and, etc., which copoe the till background. Ndjiki- Nya [7] aued that the texture in an iage could be claified into two categorie: texture with uniportant ubjective detail and the reainder. Sun [8] utilized thi idea and conidered texture a uniportant part in ter of the inherent iperfection of the HVS. Change of texture detail will not affect the ubjective coprehenion toward the original texture. It indicate that thee viual feature can be utilized to eliinate perceptual redundancy. In recent year, there have eerged large quantitie of efficient and effective algorith of iage texture analyi and ynthei [9-3]. A non-paraetric ethod for texture ynthei wa propoed in []. The ethod can produce good yntheized reult for a wide range of texture by titching together all texture patche. In addition, the detection and extraction of linear tructure which uually refer to the contour ued to define the target hape or the boundarie ued to dearcate the region alo have been reearched far and wide [7-0]. Mot of the early hape decription technique ued binary iage. At preent, thee reearche have a wide range of application in the field of iage proceing and coputer viion. In thi tudy, we propoe an iage recontruction algorith and it hybrid MPI-OpenMP approach. Thi algorith can elect the allet region texture aple and obtain optial retoration iage. But with the iage ize increaing, iage recontruction will cot a large executing tie. To iprove it tie efficiency, we dicu the hybrid MPI-OpenMP approach in thi paper. The parallel prograing approach i ipleented on a dedicated cluter. The reainder of thi paper i organized a follow. In the next ection, the detail of the propoed iage recontruction algorith are preented. And Sect.3 give the detail of the hybrid MPI- OpenMP approach. The propoed iage recontruction doi:0.4304/jw

2 688 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH 03 algorith and hybrid MPI-OpenMP approach are teted in Sect.4. Finally, thi paper i concluded in Sect.5. II. IMAGE RECONSTRUCTION ALGORITHM Diagra of iage recontruction algorith i hown in Fig.. The ipleenting procedure of the iage texture ubtitution algorith conit of three phae: ultiregion extraction, iage feature repreentation and ulti-region iage recontruction. purpoe, a contour tracing algorith [7] i applied to the input binary iage. The hape of thi coding region i drawn by the white cloed curve, a i hown in Fig. (b). Figure. Diagra of the iage recontruction algorith A. Multi-Region Extraction An iage i firt egented into any all region in ter of hoogeneou color and texture. The egentation ethod i the o-called JSEG algorith [4, 5]. Conidering that texture aple election i enitive to egentation reult, we erge connected all region if they are nearby in pace o that each iage can obtain bigger region [6]. And, nuber of region which each iage get ay be variable in order to obtain optial retoration reult. Through ulti-region extraction, hoogeneou pixel belong to the ae region. Each region ha a unique index and every pixel belonged to one region i aigned the ae region index. Region indexe of all pixel copoe of region index lit. The region index lit i a the ae ize a the original iage if the input one i graycale, and it i one third ize a the original color iage naturally. Each eleent of index lit correpond to the pixel of original iage. Specifically, the region index lit play an iportant role in the iage feature repreentation and the hybrid MPI-OpenMP parallel prograing approach. B. Iage Feature Repreentation Shape and texture are alient feature of the appearance of object in natural cene. The id-level region i iage repreenting and recontructing unit which contain hape and texture characteritic. Decribing approache of hape and texture feature will be dicued repectively. The ipleenting procedure of regional hape feature repreentation i decribed a the following tep: binarization proceing, contour tracking, down apling and piecewie iterative curve fitting. Fig. indicate the cheatic drawing of four tage above. In order to elaborate conveniently, we jut take into account one region. Firtly, the iage hould be binarized according to region index lit. Thi coding region correpond to the white area and other region correpond to the black area, a i depicted in Fig. (a). Secondly, an ordered equence of contour point approxiating the regional hape i extracted. For thi Figure. Scheatic drawing of regional hape feature repreentation Thirdly, a vector copoed of equally ditributed point along the regional contour i extracted fro the ordered equence of contour pixel. Contour point are extracted in uch a way that they will be approxiately equally ditributed along the regional contour curve, howed a Fig. (c). The regional contour i repreented by the ordered equence ( x, y ) of contour point, where denote the poition along the regional contour curve. Finally, the piecewie iterative curve fitting [8] cobined with top-down plit algorith and curve-fitting principle i ipleented to repreent region tructure feature. It ipleentation procedure i decribed a the following tep: Connecting the two farthet edge point A and B into a line egent L, and thu plit the cloed contour into two curve and BA, a i hown in Fig. (d). Calculate the ditance d of each edge point on curve to thi line egent L uing (), and deterine the edge point farthet fro the line egent L. Here, uppoe the coordinate of A and B are ( xa, ya) and ( xb, y B), o the forula for line egent L paing fro the two end point i hown a (): xy ( y) + yx ( x) + xy xy = 0 () A B A B A B B A The ditance d of edge point ( x, y ) to the line egent L i: r d = () Δ

3 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH Where, denote the poition of any point along the curve, and r = x ( y y ) y ( x x ) + x y x y (3) A B A B A B B A Δ = A B (4) Thu, the axiu abolute error i: MAE d = ax (5) [ A, B] Clearly, point C with MAE i the farthet edge point fro the line egent L..If the axiu error of that point fro the line egent L i above a threhold, plit the curve into two curve egent at that point (i.e. new vertex point C ), one between A and C, the other between C and B. Repeat econd tep and third tep eparately for the above two ub-curve egent AC and CB to deterine ore and ore vertice until the error i aller than the plit threhold et in advance. Ipleent polynoial curve fitting on each ubcurve egent and the polynoial coefficient are deeed a region hape feature. Siply, we only take ub-curve egent AC a an exaple. The curve AC i repreented by the order equence ( x, y),( x, y),...,( xn, y n) of edge point, where n denote the nuber of eleent in thi order equence. A polynoial alway ay be expreed by the u of oe orthogonal polynoial. Suppoe the fitted polynoial can be expreed by (6): F ( x) = C P( x) i i i= = CP( x) + CP( x) + + CP( x) = P + Px+ P x + + P x (6) Our purpoe i to calculate P 0, P, L, P, where denote order of the fitted polynoial. The orthogonal function faily can be contructed by (7): P0 ( x) = P( x) = ( x A) P0( x) P( x) = ( x A) P( x) BP 0( x) (7)... P ( x) = ( x A ) P ( x) B P ( x) Where, j+ j+ j j j n n n xipj xi xp i j xi yipj xi i= i= i= j+ =, j =, n n j = n Pj ( xi) Pj ( xi) Pj ( xi) i= i= i= ( ) ( ) ( ) A B C (8) And j = 0,, L,. Finally, we ay calculate the polynoial coefficient P0, P, L, P in ter of j Pj ( x ) above. In C and { } thi way, the contour curve of one region i figured by thee coefficient and neceary endpoint. Regional texture feature i repreented by regional texture aple elected. A regional texture aple hould contain a ajority of local and global characteritic of the inner texture. The inner texture i analyzed by a Dautocorrelation tatitic analyi ethod []. The autocorrelation function of an iage can be ued to ae the aount of regularity a well a the finene/coarene of the texture preent in the iage. The autocorrelation function of an iage i defined a follow: MN ριι( xy, ) = ( M x)( N y) M x N y u= v= M IuvIu (, ) ( + xv, + y) N u= v= I ( u, v) For regular tructural texture, the function will exhibit peak and valley. We can eaily deterine the cale of the texture priitive fro the given texture. The texture aple hould contain ~5 texture priitive. For tochatic texture, 90% above value of the function are bigger than 0.9 generally. Correpondingly, the ize of texture aple not only ay be et aller but alo can be controlled by the reearcher. C. Multi-Region Iage Recontruction The ipleenting procedure of ulti-region iage recontruction i decribed a the following tage: region contour recontruction, region texture ynthei and region retoration. In the firt tage, the contour curve of one region can be decribed a a polynoial function a follow: y = P0 + Px + Px + + P x (9) L (0) P P L Where, the polynoial coefficient 0,,, have been attained through region tructure feature repreentation. According to the x-coordinate of two endpoint, uch a x and x n, it i eay to attain an r abcia vector x = { x, x+, L, xn}, where each eleent i the x-coordinate of one point on the curve. Subtitute eleent of x r in (0) one by one, then the y- coordinate of each point will be gained. In thi way, the region contour i recontructed. In order to ake the connection between two neighboring curve perfect and guarantee the contour cloed, a generic algorith of dilation i applied. P

4 690 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH 03 In the econd tage, a texture ynthei algorith i perfored in the anner of Efro and Freean iage quilting in []. And any ipleentation detail are introduced in []. For intance, a bigger patch ean better capturing of texture characteritic in the texture patche and thu ore iilarity between the original texture and the yntheized one. It i uually aued that the patch contain one texture eleent at leat. Finally, region retoration i achieved through uch a way that yntheized region texture i filled to the recontructed region contour. Multi-region iage recontruction i achieved when all region are uccefully retored. III. HYBRID MPI-OPENMP APPROACH To iprove the efficiency of iage recontruction algorith, during the ipleenting procedure, parallel technique are utilized to achieve iage feature extraction and ulti-region iage recontruction. The ipleenting procedure of thi parallel prograing approach conit of two phae: MPI paralleli and OpenMP paralleli. In order to illutrate the ipleenting proce of the propoed hybrid MPI- OpenMP approach, we give it parallel ipleenting flowchart, a hown in Fig.3. The proceor whoe ID nuber i i take charge of region which ha ae index. For exaple, the ater take charge of region whoe index i 0. In the MPI parallel ipleenting proce, Firtly, according to region index lit, The ater and all lave obtain regional tructure feature through perforing contour tracking, down apling and piecewie iterative curve fitting and regional texture aple through perforing aple election. After that, the ater and all lave accoplih regional texture ynthei according to regional texture aple. Secondly, becaue contour curve of each region i different and polynoial coefficient are generated randoly, nuber of polynoial coefficient of region contour curve i different. Therefore, the ater and all lave gather nuber of thee polynoial coefficient of contour curve of all region fro all proceor, which could be ipleented by uing the MPI_Allgather() function. After that, the ater gather thee polynoial coefficient of contour curve of other region fro all laver, which could be ipleented by uing the MPI_Gatherv() function. Then, the ater gather yntheized texture of other region fro all laver, which could be ipleented by uing the MPI_Gather() function. Finally, the ater achieve contour recontruction of all region. Then, the ater accoplihe ulti-region iage recontruction through copleting retoration of all region ucceively. B. OpenMP Paralleli Figure 4. The OpenMP parallel code Figure 3. The hybrid MPI-OpenMP parallel ipleenting flowchart A. MPI Paralleli The MPI paralleli i deigned baed on the Mater- Slave deign pattern [3] and it ethodology i baed on the Tak-Channel odel. In order to elaborate conveniently, we aue that nuber of region i N. And then indexe of thee region are 0,,, L, N, repectively. Each region i apped a a tak and each tak correpond to a proce. ID nuber of ater i 0; ID nuber of all laver are,, 3, L, N, repectively. The piecewie iterative curve fitting play a key role in the proce of region tructure feature repreentation and it execution tie can not be ignored. In addition, with the iage ize increaing, the execution tie conued by piecewie iterative curve fitting will alo increae. That will affect the efficiency of iage recontruction. In order to olve thi proble, we take full advantage of potential parallel feature of iage recontruction algorith and propoe a ulti-threaded piecewie iterative curve fitting which i baed on the OpenMP technique [3]. At the ae tie, ulti-threaded paralleli baed on OpenMP doe not produce counication overhead. Fig.4 illutrate the OpenMP

5 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH parallel piecewie iterative curve fitting in the for of code. C. Effective Load-Balancing There i effective load-balancing in our hybrid MPI- OpenMP parallel prograing approach. On the one hand, becaue all region have ae texture aple ize and texture ynthei paraeter, the tie conued by aple election and texture ynthei i alo ae. Becaue the contour of each region i different, the tie conued by contour tracing, down apling, piecewie iterative curve fitting and contour retoration i alo not ae. But in the real environent, ince the tie conued by the latter i aller than the tie conued by the forer, the difference of total execution tie aong proceor i all. On the other hand, in the ipleenting procedure of the piecewie iterative curve fitting, we execute a ultithreaded paralleli baed on OpenMP. Thi way, though the contour of each region i different, the parallel execution tie conued by piecewie iterative curve fitting i alot ae. Therefore, the difference of total execution tie aong proceor will becoe aller. Clearly, ulti-threaded paralleli baed on OpenMP i beneficial to load-balancing. IV. EXPERIMENTAL RESULTS AND PERFORMANCE ANALYSIS The propoed fraework i copoed of two part. The firt part of the propoed fraework i in Sect., which derive the iage recontruction algorith. In Sect.3, the econd part of the propoed fraework how the detail of the hybrid MPI-OpenMP approach. Experiental reult are then given according to thee two part. For the firt part, we perfor experient in Sect.4. to evaluate our iage recontruction algorith. For the econd part, we perfor experient in Sect.4. to evaluate the tie perforance of our hybrid MPI- OpenMP approach. A. Evaluation on Iage Recontruction Algorith We tet our iage recontruction algorith on oe natural iage with aive texture. For ulti-region extraction, the JSEG algorith ha three paraeter which need to be pecified artificially [5]. And we pecify the three paraeter a follow: TQUAN = -, NSCALE = -, threhcolor = 0.8, which ake the perforance of hoogeneity detection perfect. For the piecewie iterative curve fitting, the plit threhold aount to 5~0 and the degree of polynoial of curve fitting i pecified a 4 generally. Here, the JPEG verion ued i JPEG Iager...5 and the JPEG000 verion ued i Kakadu_V..3. In order to illutrate the ipleenting procedure of the propoed iage recontruction algorith, we how the reult of each tage in Fig.5. Two region of original iage are obtained through ulti-region extraction, a i hown in Fig.5 (b). Fig.5 (c) and Fig.5 (d) how the recontructed contour and the dilated contour of the upper region, repectively. Fig.5 (e) and Fig.5 (f) diplay the recontructed contour and the dilated contour of the lower region, repectively. Fig.5 (g) diplay the yntheized texture of the upper region and Fig.5 (h) diplay the yntheized texture of the lower region. Finally, the recontructed iage i how in Fig.5 (i). Figure 5. Diagra how reult of each phae Figure 6. Recontruction reult There are any recontruction reult with different nuber of region in Fig.6. Experiental reult how thee iage recontructed by our algorith have viual ipairent. But viual ipairent of JPEG iage and JPEG000 iage i alot iperceptible. The reaon why recontructed reult have viual ipairent i that lo of non-texture detailed inforation. Thi lo i the ain caue which caue the viual ipairent of

6 69 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH 03 recontructed reult. Ditortion of regional contour in t obviou. TLE I. COMPARISON OF BYTES REQUIRED BY JPEG, JPEG000 AND OUR ALGORITHM Figure 7. Execution tie, Speedup and Parallel efficiency with different nuber of region In our iage recontruction algorith, byte required by iage recontruction are coputed by (): N i i () i= Ω= ( Q + T) Where, Ω denote byte required by iage recontruction; N i nuber of region; i i index of region; Q i byte of polynoial coefficient i repreenting regional contour with index i ; T i i byte of regional texture aple with index i. In Table, we how nuber of byte ued in our iage recontruction algorith and copare the to the JPEG and JPEG000 copreion for the equivalent iage. Our recontructed iage are fair approxiation and we ay do ore ueful attept for etablihing ore ophiticated iage coding algorith to recontruct very realitic iage. B. Evaluation on Hybrid MPI-OpenMP Approach We ipleent the hybrid MPI-OpenMP approach uing tandard C with Microoft MPI (MS-MPI) and OpenMP. A erie of tet have been perfored on a dedicated cluter of 8 coputing node running Window HPC Server 008, each with Quad-core Xeon X5430 (.66GHz) and 6GB eory and connected by an Infiniband witch. Now we turn to the tie perforance eaureent of the propoed hybrid MPI-OpenMP approach. We ue original iage in Fig.6 (b) and Fig.6 (d) to eaure the execution tie, peedup and parallel efficiency of our ipleentation. In addition, conidering the actual characteritic of iage hape, nuber of region of original iage in Fig.6 (b) i, 3 and 4, repectively; and nuber of region of original iage in Fig.6 (d) i, 3, 4, 5, 6 and 7, repectively. Although the nuber of thread can be arbitrarily et, the nuber of thread i pecified a two in really experientation. Thee eaureent are deontrated in Fig.7. A hown in Fig.7, we can ee clearly that the execution tie can be reduced greatly by iage feature extraction and recontruction in parallel. Moreover, the ore nuber of region i, the ore the aved tie i. In addition, high peedup are alo obtained. Moreover, the ore nuber of region i, the higher the peedup i. However, further reearch and iproveent are till required for the low parallel efficiency when the nuber of proceor i increaing. To u up, we believe that iage feature extraction and recontruction in parallel i a feaible approach for iage recontruction algorith. And it will perfor better a the further developent of parallel technique. V. CONCLUSIONS Perceptual coding hould take full advantage of the reult fro huan viual yte (HVS) tudie. Iage can be pared into ediu-level viion repreentation: regional contour curve and texture. An effective iage recontruction algorith i propoed in thi paper. Through electing the allet region texture aple, the iage recontruction algorith can effectually eliinate perceptual redundancy. Copared with JPEG and JPEG000 copreion, our algorith can get ore coding gain but reain ot iage inforation people care. Siulation reult how that our algorith can obtain optial recontructed iage. The hybrid MPI- OpenMP approach propoed i ipleented on a dedicated cluter. Thi parallel approach can ignificantly iprove efficiency of iage recontruction. Repone

7 JOURNAL OF SOFTWARE, VOL. 8, NO. 3, MARCH tie of retoring iage fro original iage with any region can be reduced greatly. In our experient, everal liitation are found for the iage recontruction algorith. One cae i regional hape ditortion. Another cae i how to handle the lo of non-texture detailed inforation. Future reearch work i on how to olve thee proble and etablih ore ophiticated coding algorith to recontruct very realitic iage. ACKNOWLEDGMENT We acknowledge the funding provided by the National Natural Science Foundation of China key project (Grant No ) and youth project (Grant No ). REFERENCES [] M. Kunt, A. Ikonoopoulo, M. Kocher, Second- Generation Iage Coding Technique, Proc. IEEE, Vol. 73, No. 4, Apr. 985, pp [] R.A. DeVore, B. Jawerth, B.J. Lucier, Iage Copreion Through Wavelet Tranfor Coding, IEEE Tranaction on Inforation Theory, Vol. 38, No., Mar. 99, pp [3] L. Thoa, F. Deravi, Region-baed Fractal Iage Copreion uing Heuritic Search, IEEE Tranaction on Iage Proceing, Vol. 4, No. 6, Jun. 995, pp [4] H. Hartentein, M. Ruhl, D. Saupe, Region-baed Fractal Iage Copreion, IEEE Tranaction on Iage Proceing, Vol. 9, No. 7, Jul. 000, pp [5] J.W. Han, K.N. Ngan, Unupervied Extraction of Viual Attention Object in Color Iage, IEEE Tranaction on Circuit and Syte for Video Technology, Vol. 6, No., Jan. 006, pp [6] T. Sikora, Trend and Perpective in Iage and Video Coding, Proc. IEEE, Vol. 93, No., Jan. 005, pp [7] P. Ndjiki-Nya, B. Makai, G. Blatterann, Iproved H.64/AVC Coding uing Texture Analyi and Synthei, Proc. IEEE Int. Conf. Iage Proceing, Sept. 4-7, 003, pp. II [8] K. Sun, Y.Y. Yang, L. Ye, Q. Zhang, Iage Retoration Uing Piecewie Iterative Curve Fitting and Texture Synthei, Proc. 4th Int. Conf. Intelligent Coputing, Shanghai, China, Sept. 5-8, 008, pp [9] R.J. Chen, L.G. Liu, G.C. Dong, Local Reapling for Patch-baed Texture Synthei in Vector Field, International Journal of Coputer Application in Technology, Vol. 38, No. //3, Jul. 00, pp [0] D.S. Wickraanayake, E.A. Ediriinghe, H.E. Bez, Tranfor Doain Texture Synthei, Signal Proceing: Iage Counication, Vol. 3, No., Jan. 008, pp.-3. [] A.A. Efro, W.T. Freean, Iage Quilting for Texture Synthei and Tranfer, ACM SIGGRAPH, 00, pp [] G. Peyre, Texture Synthei with Grouplet, IEEE Tranaction on Pattern Analyi and Machine Intelligence, Vol. 3, No. 4, Apr. 00, pp [3] P.P. Bartakke, S.A. Vaidya, M.S. Sutaone, Refining Structural Texture Synthei Approach, IET Iage Proceing, Vol. 5, No., Mar. 0, pp [4] Y. Deng, B.S. Manjunath, H. Shin, Color Iage Segentation, Proc. IEEE Coputer Viion and Pattern Recognition, Fort Collin, USA, Jun. 3-5,999, pp [5] Y. Deng, B.S. Manjunath, Unupervied Segentation of Color-Texture Region in Iage and Video, IEEE Tranaction on Pattern Analyi and Machine Intelligence, Vol. 3, No. 8, Aug. 00, pp [6] F. Jing, M. Li, H.J. Zhang, B. Zhang, An Efficient and Effective Region-baed Iage Retrieval Fraework, IEEE Tranaction on Iage Proceing, Vol. 3, No. 5, May 004, pp [7] T. Adaek, N. O Connor, Efficient Contour-baed Shape Repreentation and Matching, Proc. 5th ACM SIGMM Int. Workhop on Multiedia Inforation Retrieval, Nov. 003, pp [8] P. Dollar, Z.W. Tu, S. Belongie, Supervied Learning of Edge and Object Boundarie, Proc. IEEE Coputer Viion and Pattern Recognition, 006, pp [9] D.R. Martin, C.C. Fowlke, J. Malik, Learning to Detect Natural Iage Boundarie uing Local Brightne, Color, and Texture Cue, IEEE Tranaction on Pattern Analyi and Machine Intelligence, Vol. 6, No. 5, May 004, pp [0] Q.L. Tang, N. Sang, T.X. Zhang, Contour Detection baed on Contextual Influence, Iage and Viion Coputing, Vol. 5, No. 8, Aug. 007, pp [] C.H. Chen, P.S.P. Wang, Handbook of Pattern Recognition and Coputer Viion, World Scientific Publihing Co., 999, Ch., pp 8-. [] L. Liang, C. Liu, Y. Xu, Real-Tie Texture Synthei by Patch-baed Sapling, ACM Tranaction on Graphic, Vol. 0, No. 3, Jul. 00, pp [3] M.J. Quinn, Parallel Prograing in C with MPI and OpenMP, McGraw-Hill Copanie, Inc., 004. Jinliang Wan i lecturer fro Henan Univerity of Econoic and Law. My reearch area focue on iage and video coding, real-tie digital iage proceing and high perforance coputing. I received the B.E. degree in Counication Engineering fro Zhengzhou Univerity, Zhengzhou, China, and the M.Sc. degree in Counication and Inforation Syte fro Counication Univerity of China, Beijing, China. I a currently lecturer in Henan Univerity of Econoic and Law, Zhengzhou, China, and Ph.D. candidate in Inforation Engineering School, Counication Univerity of China, Beijing, China. Now, I take part in one National Natural Science Foundation of China key project and one youth project. Yanhui Liu, Potdoctor, Certified tructural engineer, t. grade of China. State Key Laboratory for Seiic Reduction /Control & Structural Safety (Cultivation), Guangzhou Univerity. Reearch field: tructure vibration control. In 003, 007 and 009, I obtained the bachelor' degree of engineering in Hainan Univerity, ater degree of engineering in Lanzhou Univerity of Technology and doctor degree of engineering in Lanzhou Univerity of Technology repectively. In 009-0, I went in for potdoctor in Beijing Univerity of Technology. Now, I a working in State Key Laboratory for Seiic Reduction /Control & Structural Safety (Cultivation), Guangzhou Univerity. Now, I hold one National Natural Science Foundation of China and one Potdoctoral Science Foundation of China, obtain one patent of China and have publihed twenty acadeic paper of which ot have been indexed SCI or EI.

PERFORMANCE MEASUREMENT OF OEE USING DATA ENVELOPMENT ANALYSIS (DEA) Muhamad Arifpin Mansor 1 and Ario Ohsato 2

PERFORMANCE MEASUREMENT OF OEE USING DATA ENVELOPMENT ANALYSIS (DEA) Muhamad Arifpin Mansor 1 and Ario Ohsato 2 National Conference in Mechanical Engineering Reearch and Potgraduate Student (1 t NCMER 2010) 26-27 MAY 2010, FKM Conference Hall, UMP, Kuantan, Pahang, Malayia; pp. 65-71 ISBN: 978-967-5080-9501 (CD

More information

Position Control of Manipulator s Links Using Artificial Neural Network with Backpropagation Training Algorithm

Position Control of Manipulator s Links Using Artificial Neural Network with Backpropagation Training Algorithm Poition Control of Manipulator Link Uing Artificial Neural Network with Backpropagation Training Algorith Thiang, Handry Khowanto, Tan Hendra Sutanto Electrical Engineering Departent, Petra Chritian Univerity

More information

Lip Segmentation with the Presence of Beards

Lip Segmentation with the Presence of Beards Lip Segentation with the Preence of Beard Author ang, S., Lau, W., Leung, S., Liew, A. Publihed 004 Conference Title Proceeding of the IEEE International Conference on Acoutic, Speech, and Signal Proceing,

More information

DENSE CORRESPONDING PIXEL MATCHING USING A FIXED WINDOW WITH RGB INDEPENDENT INFORMATION

DENSE CORRESPONDING PIXEL MATCHING USING A FIXED WINDOW WITH RGB INDEPENDENT INFORMATION ISRS Annal of the hotograetry, Reote Sening and Spatial Inforation Science Volue I-4, 202 XXII ISRS Congre 25 Augut 0 Septeber 202, Melbourne, Autralia DENSE CORRESONDING IXEL MATCHING USING A FIXED WINDOW

More information

Laboratory Exercise 1

Laboratory Exercise 1 Laboratory Eercie Switche, Light, and Multipleer The purpoe of thi eercie i to learn how to connect iple input and output device to an FPGA chip and ipleent a circuit that ue thee device. We will ue the

More information

Hong Yao, Han Zhang, Changkai Zhang and Deze Zeng. Jie Wu* and Huanyang Zheng

Hong Yao, Han Zhang, Changkai Zhang and Deze Zeng. Jie Wu* and Huanyang Zheng 330 Int. J. Coputational Science and Engineering, Vol. 4, No. 4, 207 Data or index: a trade-off in obile delay tolerant network Hong Yao, Han Zhang, Changkai Zhang and Deze Zeng Hubei Key Laboratory of

More information

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 13

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 13 Coputer Aided Drafting, Design and Manufacturing Volue 26, uber 2, June 2016, Page 13 CADDM 3D reconstruction of coplex curved objects fro line drawings Sun Yanling, Dong Lijun Institute of Mechanical

More information

Geometry Inspired Algorithms for Linear Programming

Geometry Inspired Algorithms for Linear Programming Geoetry Inpired Algorith or Linear Prograing Dhananjay P. Mehendale Sir Parahurabhau College, Tilak Road, Pune-4030, India Abtract In thi paper we dicu oe novel algorith or linear prograing inpired by

More information

The optimization design of microphone array layout for wideband noise sources

The optimization design of microphone array layout for wideband noise sources PROCEEDINGS of the 22 nd International Congress on Acoustics Acoustic Array Systes: Paper ICA2016-903 The optiization design of icrophone array layout for wideband noise sources Pengxiao Teng (a), Jun

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each circuit will be decribed in Verilog and implemented

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each type of circuit will be implemented in two

More information

Automatic Pavement Crack Detection by Multi-Scale Image Fusion

Automatic Pavement Crack Detection by Multi-Scale Image Fusion Autoatic Paveent Crack Detection by Multi-Scale Iage Fuion Haifeng Li, Dezhen Song, Yu Liu, and Binbin Li Abtract Paveent crack detection fro iage i a challenging proble due to intenity inhoogeneity, topology

More information

Contents. Cameron Ellum and Prof. Naser El- Sheimy 19 April 2005 mobile multi-sensor systems research group

Contents. Cameron Ellum and Prof. Naser El- Sheimy 19 April 2005 mobile multi-sensor systems research group The Coon Adjutent of GPS and Photograetric Caeron Ellu and Prof. Naer El- Sheiy 19 April 2005 obile ulti-enor yte reearch group Content Background Reearch objective Ipleentation Teting Concluion Outlook

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier a a The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each b c circuit will be decribed in Verilog

More information

3D SMAP Algorithm. April 11, 2012

3D SMAP Algorithm. April 11, 2012 3D SMAP Algorithm April 11, 2012 Baed on the original SMAP paper [1]. Thi report extend the tructure of MSRF into 3D. The prior ditribution i modified to atify the MRF property. In addition, an iterative

More information

Anisotropy Estimation and Image Remapping Using Model Based Moveout

Anisotropy Estimation and Image Remapping Using Model Based Moveout Aniotropy Etiation and Iae Reappin Uin Model Baed Moveout Z. Liu* (PGS), N.D. Whitore (PGS) & C. Zhou (PGS) SUMMARY Typically odel paraeter etiation i achieved throuh ultiple iteration of linearized tooraphy

More information

A MODULAR COMPOSABLE SOFTWARE ARCHITECTURE FOR THE SIMULATION OF MECHATRONIC SYSTEMS

A MODULAR COMPOSABLE SOFTWARE ARCHITECTURE FOR THE SIMULATION OF MECHATRONIC SYSTEMS Proceeding of DETC 98 1998 ASME 18th Coputer in Engineering Conference Septeber 13-16, 1998, Atlanta, Georgia, USA DETC98/CIE-5704 A MODULAR COMPOSABLE SOFTWARE ARCHITECTURE FOR THE SIMULATION OF MECHATRONIC

More information

PERFORMANCE OPTIMIZATIONS FOR PATCHMATCH-BASED PIXEL- LEVEL MULTIVIEW INPAINTING

PERFORMANCE OPTIMIZATIONS FOR PATCHMATCH-BASED PIXEL- LEVEL MULTIVIEW INPAINTING PERFORMANCE OPTIMIZATIONS FOR PATCHMATCH-BASED PIXEL- LEVEL MULTIVIEW INPAINTING Shao-Ping Lu, Beerend Ceulean, Adrian Munteanu, Peter Schelken Departent of Electronic and Inforatic, Vrije Univeriteit

More information

Universität Augsburg. Institut für Informatik. Approximating Optimal Visual Sensor Placement. E. Hörster, R. Lienhart.

Universität Augsburg. Institut für Informatik. Approximating Optimal Visual Sensor Placement. E. Hörster, R. Lienhart. Univerität Augburg à ÊÇÅÍÆ ËÀǼ Approximating Optimal Viual Senor Placement E. Hörter, R. Lienhart Report 2006-01 Januar 2006 Intitut für Informatik D-86135 Augburg Copyright c E. Hörter, R. Lienhart Intitut

More information

Analyzing Hydra Historical Statistics Part 2

Analyzing Hydra Historical Statistics Part 2 Analyzing Hydra Hitorical Statitic Part Fabio Maimo Ottaviani EPV Technologie White paper 5 hnode HSM Hitorical Record The hnode i the hierarchical data torage management node and ha to perform all the

More information

Planning of scooping position and approach path for loading operation by wheel loader

Planning of scooping position and approach path for loading operation by wheel loader 22 nd International Sympoium on Automation and Robotic in Contruction ISARC 25 - September 11-14, 25, Ferrara (Italy) 1 Planning of cooping poition and approach path for loading operation by wheel loader

More information

Lecture 14: Minimum Spanning Tree I

Lecture 14: Minimum Spanning Tree I COMPSCI 0: Deign and Analyi of Algorithm October 4, 07 Lecture 4: Minimum Spanning Tree I Lecturer: Rong Ge Scribe: Fred Zhang Overview Thi lecture we finih our dicuion of the hortet path problem and introduce

More information

Laboratory Exercise 6

Laboratory Exercise 6 Laboratory Exercie 6 Adder, Subtractor, and Multiplier The purpoe of thi exercie i to examine arithmetic circuit that add, ubtract, and multiply number. Each circuit will be decribed in VHL and implemented

More information

Hassan Ghaziri AUB, OSB Beirut, Lebanon Key words Competitive self-organizing maps, Meta-heuristics, Vehicle routing problem,

Hassan Ghaziri AUB, OSB Beirut, Lebanon Key words Competitive self-organizing maps, Meta-heuristics, Vehicle routing problem, COMPETITIVE PROBABIISTIC SEF-ORGANIZING MAPS FOR ROUTING PROBEMS Haan Ghaziri AUB, OSB Beirut, ebanon ghaziri@aub.edu.lb Abtract In thi paper, we have applied the concept of the elf-organizing map (SOM)

More information

Research on Star Image Noise Filtering Based on Diffusion Model of Regularization Influence Function

Research on Star Image Noise Filtering Based on Diffusion Model of Regularization Influence Function 016 Sith International Conference on Intrumentation & Meaurement Computer Communication and Control Reearch on Star Image Noie Filtering Baed on Diffuion Model of Regularization Influence Function SunJianming

More information

SLA Adaptation for Service Overlay Networks

SLA Adaptation for Service Overlay Networks SLA Adaptation for Service Overlay Network Con Tran 1, Zbigniew Dziong 1, and Michal Pióro 2 1 Department of Electrical Engineering, École de Technologie Supérieure, Univerity of Quebec, Montréal, Canada

More information

Distributed Packet Processing Architecture with Reconfigurable Hardware Accelerators for 100Gbps Forwarding Performance on Virtualized Edge Router

Distributed Packet Processing Architecture with Reconfigurable Hardware Accelerators for 100Gbps Forwarding Performance on Virtualized Edge Router Ditributed Packet Proceing Architecture with Reconfigurable Hardware Accelerator for 100Gbp Forwarding Performance on Virtualized Edge Router Satohi Nihiyama, Hitohi Kaneko, and Ichiro Kudo Abtract To

More information

Performance of a Robust Filter-based Approach for Contour Detection in Wireless Sensor Networks

Performance of a Robust Filter-based Approach for Contour Detection in Wireless Sensor Networks Performance of a Robut Filter-baed Approach for Contour Detection in Wirele Senor Network Hadi Alati, William A. Armtrong, Jr., and Ai Naipuri Department of Electrical and Computer Engineering The Univerity

More information

else end while End References

else end while End References 621-630. [RM89] [SK76] Roenfeld, A. and Melter, R. A., Digital geometry, The Mathematical Intelligencer, vol. 11, No. 3, 1989, pp. 69-72. Sklanky, J. and Kibler, D. F., A theory of nonuniformly digitized

More information

/06/$ IEEE 364

/06/$ IEEE 364 006 IEEE International ympoium on ignal Proceing and Information Technology oie Variance Etimation In ignal Proceing David Makovoz IPAC, California Intitute of Technology, MC-0, Paadena, CA, 95 davidm@ipac.caltech.edu;

More information

Multi-Target Tracking In Clutter

Multi-Target Tracking In Clutter Multi-Target Tracking In Clutter John N. Sander-Reed, Mary Jo Duncan, W.B. Boucher, W. Michael Dimmler, Shawn O Keefe ABSTRACT A high frame rate (0 Hz), multi-target, video tracker ha been developed and

More information

ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION

ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION ANALYSIS OF THE FIRST LAYER IN WEIGHTLESS NEURAL NETWORKS FOR 3_DIMENSIONAL PATTERN RECOGNITION A. Váque-Nava * Ecuela de Ingeniería. CENTRO UNIVERSITARIO MEXICO. DIVISION DE ESTUDIOS SUPERIORES J. Figueroa

More information

On successive packing approach to multidimensional (M-D) interleaving

On successive packing approach to multidimensional (M-D) interleaving On ucceive packing approach to multidimenional (M-D) interleaving Xi Min Zhang Yun Q. hi ankar Bau Abtract We propoe an interleaving cheme for multidimenional (M-D) interleaving. To achieved by uing a

More information

LJPS Gurgaon. Class XII- Physics - Assignment Topic: - Ray Optics

LJPS Gurgaon. Class XII- Physics - Assignment Topic: - Ray Optics LJPS Gurgaon 1. The refractive index of the ediu i 3. What i the angle of refraction, if the unpolaried light i incident on it at the polarizing angle of the ediu? [An : 30 degree] Cla XII- Phyic - Aignent

More information

Imaging issues for interferometric measurement of aspheric surfaces using CGH null correctors

Imaging issues for interferometric measurement of aspheric surfaces using CGH null correctors Invited Paper Iaging iue for interferoetric eaureent of apheric urface uing CGH null corrector Ping Zhou*, Ji Burge, Chunyu Zhao College of Optical Science, Univ. of Arizona, 63 E. Univ. Blvd, Tucon, AZ,

More information

A User-Attention Based Focus Detection Framework and Its Applications

A User-Attention Based Focus Detection Framework and Its Applications A Uer-Attention Baed Focu Detection Framework and It Application Chia-Chiang Ho, Wen-Huang Cheng, Ting-Jian Pan, Ja-Ling Wu Communication and Multimedia Laboratory, Department of Computer Science and Information

More information

Image authentication and tamper detection using fragile watermarking in spatial domain

Image authentication and tamper detection using fragile watermarking in spatial domain International Journal of Advanced Reearch in Computer Engineering & Technology (IJARCET) Volume 6, Iue 7, July 2017, ISSN: 2278 1323 Image authentication and tamper detection uing fragile watermarking

More information

3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES

3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES MAKARA, TEKNOLOGI, VOL. 9, NO., APRIL 5: 3-35 3D MODELLING WITH LINEAR APPROACHES USING GEOMETRIC PRIMITIVES Mochammad Zulianyah Informatic Engineering, Faculty of Engineering, ARS International Univerity,

More information

CENTER-POINT MODEL OF DEFORMABLE SURFACE

CENTER-POINT MODEL OF DEFORMABLE SURFACE CENTER-POINT MODEL OF DEFORMABLE SURFACE Piotr M. Szczypinki Iintitute of Electronic, Technical Univerity of Lodz, Poland Abtract: Key word: Center-point model of deformable urface for egmentation of 3D

More information

UC Berkeley International Conference on GIScience Short Paper Proceedings

UC Berkeley International Conference on GIScience Short Paper Proceedings UC Berkeley International Conference on GIScience Short Paper Proceeding Title A novel method for probabilitic coverage etimation of enor network baed on 3D vector repreentation in complex urban environment

More information

Performance analysis of hybrid (M/M/1 and M/M/m) client server model using Queuing theory

Performance analysis of hybrid (M/M/1 and M/M/m) client server model using Queuing theory International Journal of Electronic and Couter cience Engineering vailable Online at wwwijeceorg IN- 77-9 erforance analyi of hybrid M/M/ and M/M/ client erver odel uing ueuing theory atarhi Guta, Dr Rajan

More information

Laboratory Exercise 2

Laboratory Exercise 2 Laoratory Exercie Numer and Diplay Thi i an exercie in deigning cominational circuit that can perform inary-to-decimal numer converion and inary-coded-decimal (BCD) addition. Part I We wih to diplay on

More information

Markov Random Fields in Image Segmentation

Markov Random Fields in Image Segmentation Preented at SSIP 2011, Szeged, Hungary Markov Random Field in Image Segmentation Zoltan Kato Image Proceing & Computer Graphic Dept. Univerity of Szeged Hungary Zoltan Kato: Markov Random Field in Image

More information

Key Terms - MinMin, MaxMin, Sufferage, Task Scheduling, Standard Deviation, Load Balancing.

Key Terms - MinMin, MaxMin, Sufferage, Task Scheduling, Standard Deviation, Load Balancing. Volume 3, Iue 11, November 2013 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Tak Aignment in

More information

A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS

A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS Vietnam Journal of Science and Technology 55 (5) (017) 650-657 DOI: 10.1565/55-518/55/5/906 A METHOD OF REAL-TIME NURBS INTERPOLATION WITH CONFINED CHORD ERROR FOR CNC SYSTEMS Nguyen Huu Quang *, Banh

More information

An NoC Traffic Compiler for efficient FPGA implementation of Parallel Graph Applications

An NoC Traffic Compiler for efficient FPGA implementation of Parallel Graph Applications An NoC Traffic Copiler for efficient FPGA ipleentation of Parallel Graph Application Nachiket Kapre California Intitute of Technology, Paadena, CA 9115 nachiket@caltech.edu André DeHon Univerity of Pennylvania

More information

Trainable Context Model for Multiscale Segmentation

Trainable Context Model for Multiscale Segmentation Trainable Context Model for Multicale Segmentation Hui Cheng and Charle A. Bouman School of Electrical and Computer Engineering Purdue Univerity Wet Lafayette, IN 47907-1285 {hui, bouman}@ ecn.purdue.edu

More information

TensorFlow and Keras-based Convolutional Neural Network in CAT Image Recognition Ang LI 1,*, Yi-xiang LI 2 and Xue-hui LI 3

TensorFlow and Keras-based Convolutional Neural Network in CAT Image Recognition Ang LI 1,*, Yi-xiang LI 2 and Xue-hui LI 3 2017 2nd International Conference on Coputational Modeling, Siulation and Applied Matheatics (CMSAM 2017) ISBN: 978-1-60595-499-8 TensorFlow and Keras-based Convolutional Neural Network in CAT Iage Recognition

More information

Course Project: Adders, Subtractors, and Multipliers a

Course Project: Adders, Subtractors, and Multipliers a In the name Allah Department of Computer Engineering 215 Spring emeter Computer Architecture Coure Intructor: Dr. Mahdi Abbai Coure Project: Adder, Subtractor, and Multiplier a a The purpoe of thi p roject

More information

High Quality Normal Map Compression

High Quality Normal Map Compression Graphic Hardware (2006) M. Olano, P. Sluallek (Editor) High Quality Noral Map Copreion Jacob Munkberg Toa Akenine-Möller Jacob Strö 2 Lund Univerity 2 Ericon Reearch Abtract Noral apping i a widely ued

More information

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 3, September 2015, Page 10

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 3, September 2015, Page 10 Computer Aided Drafting, Deign and Manufacturing Volume 5, umber 3, September 015, Page 10 CADDM Reearch of atural Geture Recognition and Interactive Technology Compatible with YCbCr and SV Color Space

More information

IMPROVED JPEG DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION. Tak-Shing Wong, Charles A. Bouman, and Ilya Pollak

IMPROVED JPEG DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION. Tak-Shing Wong, Charles A. Bouman, and Ilya Pollak IMPROVED DECOMPRESSION OF DOCUMENT IMAGES BASED ON IMAGE SEGMENTATION Tak-Shing Wong, Charle A. Bouman, and Ilya Pollak School of Electrical and Computer Engineering Purdue Univerity ABSTRACT We propoe

More information

MAT 155: Describing, Exploring, and Comparing Data Page 1 of NotesCh2-3.doc

MAT 155: Describing, Exploring, and Comparing Data Page 1 of NotesCh2-3.doc MAT 155: Decribing, Exploring, and Comparing Data Page 1 of 8 001-oteCh-3.doc ote for Chapter Summarizing and Graphing Data Chapter 3 Decribing, Exploring, and Comparing Data Frequency Ditribution, Graphic

More information

Compressed Sensing Image Processing Based on Stagewise Orthogonal Matching Pursuit

Compressed Sensing Image Processing Based on Stagewise Orthogonal Matching Pursuit Senor & randucer, Vol. 8, Iue 0, October 204, pp. 34-40 Senor & randucer 204 by IFSA Publihing, S. L. http://www.enorportal.com Compreed Sening Image Proceing Baed on Stagewie Orthogonal Matching Puruit

More information

Delaunay Triangulation: Incremental Construction

Delaunay Triangulation: Incremental Construction Chapter 6 Delaunay Triangulation: Incremental Contruction In the lat lecture, we have learned about the Lawon ip algorithm that compute a Delaunay triangulation of a given n-point et P R 2 with O(n 2 )

More information

AUTOMATIC TEST CASE GENERATION USING UML MODELS

AUTOMATIC TEST CASE GENERATION USING UML MODELS Volume-2, Iue-6, June-2014 AUTOMATIC TEST CASE GENERATION USING UML MODELS 1 SAGARKUMAR P. JAIN, 2 KHUSHBOO S. LALWANI, 3 NIKITA K. MAHAJAN, 4 BHAGYASHREE J. GADEKAR 1,2,3,4 Department of Computer Engineering,

More information

Focused Video Estimation from Defocused Video Sequences

Focused Video Estimation from Defocused Video Sequences Focued Video Etimation from Defocued Video Sequence Junlan Yang a, Dan Schonfeld a and Magdi Mohamed b a Multimedia Communication Lab, ECE Dept., Univerity of Illinoi, Chicago, IL b Phyical Realization

More information

A New Approach to Pipeline FFT Processor

A New Approach to Pipeline FFT Processor A ew Approach to Pipeline FFT Proceor Shouheng He and Mat Torkelon Department of Applied Electronic, Lund Univerity S- Lund, SWEDE email: he@tde.lth.e; torkel@tde.lth.e Abtract A new VLSI architecture

More information

Texture-Constrained Active Shape Models

Texture-Constrained Active Shape Models 107 Texture-Contrained Active Shape Model Shuicheng Yan, Ce Liu Stan Z. Li Hongjiang Zhang Heung-Yeung Shum Qianheng Cheng Microoft Reearch Aia, Beijing Sigma Center, Beijing 100080, China Dept. of Info.

More information

AN ALGORITHM FOR RESTRICTED NORMAL FORM TO SOLVE DUAL TYPE NON-CANONICAL LINEAR FRACTIONAL PROGRAMMING PROBLEM

AN ALGORITHM FOR RESTRICTED NORMAL FORM TO SOLVE DUAL TYPE NON-CANONICAL LINEAR FRACTIONAL PROGRAMMING PROBLEM RAC Univerity Journal, Vol IV, No, 7, pp 87-9 AN ALGORITHM FOR RESTRICTED NORMAL FORM TO SOLVE DUAL TYPE NON-CANONICAL LINEAR FRACTIONAL PROGRAMMING PROLEM Mozzem Hoain Department of Mathematic Ghior Govt

More information

Keywords: Defect detection, linear phased array transducer, parameter optimization, phased array ultrasonic B-mode imaging testing.

Keywords: Defect detection, linear phased array transducer, parameter optimization, phased array ultrasonic B-mode imaging testing. Send Order for Reprint to reprint@benthamcience.ae 488 The Open Automation and Control Sytem Journal, 2014, 6, 488-492 Open Acce Parameter Optimization of Linear Phaed Array Tranducer for Defect Detection

More information

Cutting Stock by Iterated Matching. Andreas Fritsch, Oliver Vornberger. University of Osnabruck. D Osnabruck.

Cutting Stock by Iterated Matching. Andreas Fritsch, Oliver Vornberger. University of Osnabruck. D Osnabruck. Cutting Stock by Iterated Matching Andrea Fritch, Oliver Vornberger Univerity of Onabruck Dept of Math/Computer Science D-4909 Onabruck andy@informatikuni-onabrueckde Abtract The combinatorial optimization

More information

Gray-level histogram. Intensity (grey-level) transformation, or mapping. Use of intensity transformations:

Gray-level histogram. Intensity (grey-level) transformation, or mapping. Use of intensity transformations: Faculty of Informatic Eötvö Loránd Univerity Budapet, Hungary Lecture : Intenity Tranformation Image enhancement by point proceing Spatial domain and frequency domain method Baic Algorithm for Digital

More information

OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS

OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS Key words SOA, optial, coplex service, coposition, Quality of Service Piotr RYGIELSKI*, Paweł ŚWIĄTEK* OPTIMAL COMPLEX SERVICES COMPOSITION IN SOA SYSTEMS One of the ost iportant tasks in service oriented

More information

A Novel Feature Line Segment Approach for Pattern Classification

A Novel Feature Line Segment Approach for Pattern Classification 12th International Conference on Information Fuion Seattle, WA, USA, July 6-9, 2009 A Novel Feature Line Segment Approach for Pattern Claification Yi Yang Intitute of Integrated Automation Xi an Jiaotong

More information

Keywords Cloud Computing, Service Level Agreements (SLA), CloudSim, Monitoring & Controlling SLA Agent, JADE

Keywords Cloud Computing, Service Level Agreements (SLA), CloudSim, Monitoring & Controlling SLA Agent, JADE Volume 5, Iue 8, Augut 2015 ISSN: 2277 128X International Journal of Advanced Reearch in Computer Science and Software Engineering Reearch Paper Available online at: www.ijarce.com Verification of Agent

More information

DAROS: Distributed User-Server Assignment And Replication For Online Social Networking Applications

DAROS: Distributed User-Server Assignment And Replication For Online Social Networking Applications DAROS: Ditributed Uer-Server Aignment And Replication For Online Social Networking Application Thuan Duong-Ba School of EECS Oregon State Univerity Corvalli, OR 97330, USA Email: duongba@eec.oregontate.edu

More information

The Association of System Performance Professionals

The Association of System Performance Professionals The Aociation of Sytem Performance Profeional The Computer Meaurement Group, commonly called CMG, i a not for profit, worldwide organization of data proceing profeional committed to the meaurement and

More information

Querying Geometric Figures Using a Controlled Language, Ontological Graphs and Dependency Lattices

Querying Geometric Figures Using a Controlled Language, Ontological Graphs and Dependency Lattices Querying Geoetric Figure Uing a Controlled Language, Ontological Graph and Dependency Lattice Yanni Haralabou 1 and Pedro Quarea 2 1 Intitut Mine-Téléco, Téléco retagne Coputer Science Departent UMR CNRS

More information

Aspects of Formal and Graphical Design of a Bus System

Aspects of Formal and Graphical Design of a Bus System Apect of Formal and Graphical Deign of a Bu Sytem Tiberiu Seceleanu Univerity of Turku, Dpt. of Information Technology Turku, Finland tiberiu.eceleanu@utu.fi Tomi Weterlund Turku Centre for Computer Science

More information

Routing Definition 4.1

Routing Definition 4.1 4 Routing So far, we have only looked at network without dealing with the iue of how to end information in them from one node to another The problem of ending information in a network i known a routing

More information

Using the Spanning Tree of a Criminal Network for Identifying its Leaders

Using the Spanning Tree of a Criminal Network for Identifying its Leaders Uing the Spanning Tree of a Criinal etwork for Identifying it Leader Kaal Taha, Senior Meber, IEEE and Paul D. Yoo, Senior Meber, IEEE Abtract We introduce a forenic analyi yte called that identifie the

More information

An Approach to a Test Oracle for XML Query Testing

An Approach to a Test Oracle for XML Query Testing An Approach to a Tet Oracle for XML Query Teting Dae S. Kim-Park, Claudio de la Riva, Javier Tuya Univerity of Oviedo Computing Department Campu of Vieque, /n, 33204 (SPAIN) kim_park@li.uniovi.e, claudio@uniovi.e,

More information

A reduced reference image quality metric based on feature fusion and neural networks

A reduced reference image quality metric based on feature fusion and neural networks Univerity of Wollongong Reearch Online Faculty of Engineering and Information Science - Paper: Part A Faculty of Engineering and Information Science 2011 A reduced reference image quality metric baed on

More information

Building a Compact On-line MRF Recognizer for Large Character Set using Structured Dictionary Representation and Vector Quantization Technique

Building a Compact On-line MRF Recognizer for Large Character Set using Structured Dictionary Representation and Vector Quantization Technique 202 International Conference on Frontier in Handwriting Recognition Building a Compact On-line MRF Recognizer for Large Character Set uing Structured Dictionary Repreentation and Vector Quantization Technique

More information

A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED

A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED A PROBABILISTIC NOTION OF CAMERA GEOMETRY: CALIBRATED VS. UNCALIBRATED Jutin Domke and Yianni Aloimono Computational Viion Laboratory, Center for Automation Reearch Univerity of Maryland College Park,

More information

How to Select Measurement Points in Access Point Localization

How to Select Measurement Points in Access Point Localization Proceeding of the International MultiConference of Engineer and Computer Scientit 205 Vol II, IMECS 205, March 8-20, 205, Hong Kong How to Select Meaurement Point in Acce Point Localization Xiaoling Yang,

More information

A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE CONSTITUTED WITH MACHINING PROCESS BY MATERIAL REMOVAL

A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE CONSTITUTED WITH MACHINING PROCESS BY MATERIAL REMOVAL International Journal of Mechanical and Production Engineering Reearch and Development (IJMPERD) ISSN 49-689 Vol. 3, Iue, Mar 3, 4-5 TJPRC Pvt. Ltd. A NEW APPROACH IN MEASURING OF THE ROUGHNESS FOR SURFACE

More information

Aalborg Universitet. Published in: Proceedings of the Working Conference on Advanced Visual Interfaces

Aalborg Universitet. Published in: Proceedings of the Working Conference on Advanced Visual Interfaces Aalborg Univeritet Software-Baed Adjutment of Mobile Autotereocopic Graphic Uing Static Parallax Barrier Paprocki, Martin Marko; Krog, Kim Srirat; Kritofferen, Morten Bak; Krau, Martin Publihed in: Proceeding

More information

Chapter 13 Non Sampling Errors

Chapter 13 Non Sampling Errors Chapter 13 Non Sampling Error It i a general aumption in the ampling theory that the true value of each unit in the population can be obtained and tabulated without any error. In practice, thi aumption

More information

All in-focus View Synthesis from Under-Sampled Light Fields

All in-focus View Synthesis from Under-Sampled Light Fields ICAT 2003 December 3-5, Tokyo, Japan All in-focu View Synthei from Under-Sampled Light Field Keita Takahahi,AkiraKubota and Takehi Naemura TheUniverityofTokyo Carnegie Mellon Univerity 7-3-1, Hongo, Bunkyo-ku,

More information

On combining Learning Vector Quantization and the Bayesian classifiers for natural textured images

On combining Learning Vector Quantization and the Bayesian classifiers for natural textured images On combining Learning Vector Quantization and the Bayeian claifier for natural textured image María Guiarro Dept. Ingeniería del Software e Inteligencia Artificial Facultad Informática Univeridad Complutene

More information

A DIVISIVE HIERARCHICAL CLUSTERING- BASED METHOD FOR INDEXING IMAGE INFORMATION

A DIVISIVE HIERARCHICAL CLUSTERING- BASED METHOD FOR INDEXING IMAGE INFORMATION A DIVISIVE HIERARCHICAL CLUSTERING- BASED METHOD FOR INDEXING IMAGE INFORMATION ABSTRACT Najva Izadpanah Department of Computer Engineering, Ilamic Azad Univerity, Qazvin Branch, Qazvin, Iran In mot practical

More information

Edits in Xylia Validity Preserving Editing of XML Documents

Edits in Xylia Validity Preserving Editing of XML Documents dit in Xylia Validity Preerving diting of XML Document Pouria Shaker, Theodore S. Norvell, and Denni K. Peter Faculty of ngineering and Applied Science, Memorial Univerity of Newfoundland, St. John, NFLD,

More information

Utility-Based Resource Allocation for Mixed Traffic in Wireless Networks

Utility-Based Resource Allocation for Mixed Traffic in Wireless Networks IEEE IFOCO 2 International Workshop on Future edia etworks and IP-based TV Utility-Based Resource Allocation for ixed Traffic in Wireless etworks Li Chen, Bin Wang, Xiaohang Chen, Xin Zhang, and Dacheng

More information

Cisco VM-FEX Best Practices for VMware ESX Environment

Cisco VM-FEX Best Practices for VMware ESX Environment Deployent Guide Cico VM-FEX Bet Practice for VMware ESX Environent Deployent Guide Deceber 211 Content 1 Executive Suary... 3 1.1 Target Audience... 3 1.2 Introduction... 3 2 Cico CS VM-FEX Bet Practice...

More information

Multiclass Road Sign Detection using Multiplicative Kernel

Multiclass Road Sign Detection using Multiplicative Kernel Proceeding of the Croatian Computer Viion Workhop, Year 1 Multicla Road Sign Detection uing Multiplicative Kernel Valentina Zadrija Mireo d. d. Zagreb, Croatia valentina.zadrija@mireo.hr Siniša Šegvić

More information

Advanced Encryption Standard and Modes of Operation

Advanced Encryption Standard and Modes of Operation Advanced Encryption Standard and Mode of Operation G. Bertoni L. Breveglieri Foundation of Cryptography - AES pp. 1 / 50 AES Advanced Encryption Standard (AES) i a ymmetric cryptographic algorithm AES

More information

Problem Solving of graph correspondence using Genetics Algorithm and ACO Algorithm

Problem Solving of graph correspondence using Genetics Algorithm and ACO Algorithm Proble Solving of graph correspondence using Genetics Algorith and ACO Algorith Alireza Rezaee, 1, Azizeh Ajalli 2 Assistant professor,departent of Mechatronics Engineering, Faculty of New Sciences and

More information

An Active Stereo Vision System Based on Neural Pathways of Human Binocular Motor System

An Active Stereo Vision System Based on Neural Pathways of Human Binocular Motor System Journal of Bionic Engineering 4 (2007) 185 192 An Active Stereo Viion Sytem Baed on Neural Pathway of Human Binocular Motor Sytem Yu-zhang Gu 1, Makoto Sato 2, Xiao-lin Zhang 2 1. Department of Advanced

More information

A Multi-objective Genetic Algorithm for Reliability Optimization Problem

A Multi-objective Genetic Algorithm for Reliability Optimization Problem International Journal of Performability Engineering, Vol. 5, No. 3, April 2009, pp. 227-234. RAMS Conultant Printed in India A Multi-objective Genetic Algorithm for Reliability Optimization Problem AMAR

More information

A Practical Model for Minimizing Waiting Time in a Transit Network

A Practical Model for Minimizing Waiting Time in a Transit Network A Practical Model for Minimizing Waiting Time in a Tranit Network Leila Dianat, MASc, Department of Civil Engineering, Sharif Univerity of Technology, Tehran, Iran Youef Shafahi, Ph.D. Aociate Profeor,

More information

A System Dynamics Model for Transient Availability Modeling of Repairable Redundant Systems

A System Dynamics Model for Transient Availability Modeling of Repairable Redundant Systems International Journal of Performability Engineering Vol., No. 3, May 05, pp. 03-. RAMS Conultant Printed in India A Sytem Dynamic Model for Tranient Availability Modeling of Repairable Redundant Sytem

More information

( ) subject to m. e (2) L are 2L+1. = s SEG SEG Las Vegas 2012 Annual Meeting Page 1

( ) subject to m. e (2) L are 2L+1. = s SEG SEG Las Vegas 2012 Annual Meeting Page 1 A new imultaneou ource eparation algorithm uing frequency-divere filtering Ying Ji*, Ed Kragh, and Phil Chritie, Schlumberger Cambridge Reearch Summary We decribe a new imultaneou ource eparation algorithm

More information

LinkGuide: Towards a Better Collection of Hyperlinks in a Website Homepage

LinkGuide: Towards a Better Collection of Hyperlinks in a Website Homepage Proceeding of the World Congre on Engineering 2007 Vol I LinkGuide: Toward a Better Collection of Hyperlink in a Webite Homepage A. Ammari and V. Zharkova chool of Informatic, Univerity of Bradford anammari@bradford.ac.uk,

More information

CERIAS Tech Report EFFICIENT PARALLEL ALGORITHMS FOR PLANAR st-graphs. by Mikhail J. Atallah, Danny Z. Chen, and Ovidiu Daescu

CERIAS Tech Report EFFICIENT PARALLEL ALGORITHMS FOR PLANAR st-graphs. by Mikhail J. Atallah, Danny Z. Chen, and Ovidiu Daescu CERIAS Tech Report 2003-15 EFFICIENT PARALLEL ALGORITHMS FOR PLANAR t-graphs by Mikhail J. Atallah, Danny Z. Chen, and Ovidiu Daecu Center for Education and Reearch in Information Aurance and Security,

More information

Dynamically Reconfigurable Neuron Architecture for the Implementation of Self- Organizing Learning Array

Dynamically Reconfigurable Neuron Architecture for the Implementation of Self- Organizing Learning Array Dynamically Reconfigurable Neuron Architecture for the Implementation of Self- Organizing Learning Array Januz A. Starzyk,Yongtao Guo, and Zhineng Zhu School of Electrical Engineering & Computer Science

More information

EE 364B Convex Optimization An ADMM Solution to the Sparse Coding Problem. Sonia Bhaskar, Will Zou Final Project Spring 2011

EE 364B Convex Optimization An ADMM Solution to the Sparse Coding Problem. Sonia Bhaskar, Will Zou Final Project Spring 2011 EE 364B Convex Optiization An ADMM Solution to the Sparse Coding Proble Sonia Bhaskar, Will Zou Final Project Spring 20 I. INTRODUCTION For our project, we apply the ethod of the alternating direction

More information

Performance Analysis of RAID in Different Workload

Performance Analysis of RAID in Different Workload Send Orders for Reprints to reprints@benthascience.ae 324 The Open Cybernetics & Systeics Journal, 2015, 9, 324-328 Perforance Analysis of RAID in Different Workload Open Access Zhang Dule *, Ji Xiaoyun,

More information

Tracking High Speed Skater by Using Multiple Model

Tracking High Speed Skater by Using Multiple Model Vol. 2, No. 26 Tracing High Speed Sater by Uing Multiple Model Guojun Liu & Xianglong Tang School of Computer Science & Engineering Harbin Intitute of Technology Harbin 5000, China E-mail: hitliu@hit.edu.cn

More information