Two Approaches for Vectorizing Image Outlines
|
|
- Pierce Randall
- 6 years ago
- Views:
Transcription
1 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 Two Approaches for Vectorzng Image Outlnes Muhammad Sarfraz, Member, IACSIT Abstract Two approaches, based on lnear and conc splnes, are proposed here for vectorzng mage outlnes. Both of the approaches have varous phases ncludng extractng outlnes of mages, detectng corner ponts from the detected outlnes, and curve fttng. Interpolaton splnes are the bases of the two approached. Lnear splne approach s straght forward as t does not have a degree of freedom.n terms of some shape controller n ts descrpton. However, the dea of the soft computng approach, namely smulated annealng, has been utlzed for conc splnes. Ths dea has been ncorporated to optmze the shape parameters n the descrpton of the generalzed conc splne. Both of the lnear and conc approaches ultmately produce optmal results for the approxmate vectorzaton of the dgtal contours obtaned from the generc shapes. Demonstratons and a comparatve study also make the essental parts of the paper. Index Terms Vectorzaton, corner ponts, generc shapes, curve fttng. I. INTRODUCTION Vectorzng outlnes of mages s requred n varous real lfe problems ncludng font desgn, cartoonng, pattern recognton, etc. It s one of the mportant problems of computer graphcs, vson, and magng. Varous mathematcal and computatonal phases are nvolved n the whole process. Ths s usually done by computng a curve close to the data pont set. Computatonally economcal and optmally good soluton s an ultmate objectve to acheve the vectorzed outlnes of mages for planar objects. Desgnng and modelng some approprate curve scheme []-[3] s one of the mportant phases of capturng and vectorzng outlnes of mages. It plays a sgnfcant role n varous applcatons. The representaton of planar objects, n terms of curves, has many advantages. For example, scalng, shearng, translaton, rotaton and clppng operatons can be performed wthout any dffculty. Although a good amount of work has been done n the area [4]-[6], t s stll desred to proceed further to explore more advanced and nteractve strateges. Most of the up-to-date research has tackled ths knd of problem by curve subdvson or curve segmentaton. The proposed work s the extenson of the work n [7]. Ths work s a presentaton of two approaches usng lnear and conc nterpolatons. The lnear nterpolant approach s straght forward. However, the conc approach s nspred by an optmzaton algorthm based on smulated annealng (SA) by Krkpatrck et.al [8]. It motvates the author to an optmzaton technque proposed for the outlne capture of planar mages. In ths paper, the data pont set represents any Manuscrpt receved March 0, 0; revsed Aprl 6, 0. Ths work was supported by Kuwat Unversty, Research Grant No. [WI 05/0]. M. Sarfraz s wth the Department of Informaton Scence, Kuwat Unversty, Adalya Campus, Kuwat (e-mal: muhamad.sarfraz@ku.edu.ke; prof.m.sarfraz@gmal.com). generc shape whose outlne s requred to be captured. We present an teratve process to acheve our objectve. The algorthm comprses of varous phases to acheve the target. Frst of all, t fnds the contour [9] [] of the gray scaled btmap mages. Secondly, t uses the dea of corner ponts [3] [9] to detect corners. That s, t detects the corner ponts on the dgtal contour of the generc shape under consderaton. These phases are consdered as preprocessng steps. Lnear and conc nterpolants are then used to vectorze the outlne. The dea of smulated annealng (SA) s used to ft a conc splne whch passes through the corner ponts. It globally optmzes the shape parameters n the descrpton of the conc splnes to provde a good approxmaton to the dgtal curves. In case of poor approxmaton, the nsertons of ntermedate ponts are made as long as the desred approxmaton or ft s acheved. The organzaton of the paper s as follows, Secton dscusses about preprocessng steps whch nclude fndng the boundary of planar objects and detecton of corner ponts. Secton 3 s about the nterpolant forms of lnear and conc splne curves. Overall methodology of curve fttng s explaned n Secton 4, t ncludes the dea of knot nserton as well as the algorthm desgn for the proposed vectorzaton schemes. Demonstraton of the proposed schemes as well as comparatve study s presented n Secton 5. Fnally, the paper s concluded n Secton 6. II. PREPROCESSING The proposed schemes start wth fndng the boundary of the generc shape and then usng the output to fnd the corner ponts. The mage of the generc shapes can be acqured ether by scannng or by some other mean. The am of boundary detecton s to produce an object s shape n graphcal or non-scalar representaton. Chan codes [], n ths paper, have been used for ths purpose. Demonstraton of the method can be seen n Fg. whch s the contour of the btmap mage shown n Fg.. Corners, n dgtal mages, gve mportant clues for the shape representaton and analyss. These are the ponts that partton the boundary nto varous segments. The strategy of gettng these ponts s based on the method proposed n [3]. The demonstraton of the algorthm s made on Fg.. The corner ponts of the mage are shown n Fg.. III. CURVE FITTING AND SPLINE The motve of fndng the corner ponts, n Secton, was to dvde the contours nto peces. Each pece contans the data ponts n between two subsequent corners nclusve. Ths means that f there are m corner ponts cp, cp,, cp m then there wll be m peces p, p,, p m. We treat each pece separately and ft the splne to t. In general, the th pece 30
2 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 contans all the data ponts between cp and cp + nclusve. After breakng the contour of the mage nto dfferent peces, we ft the splne curve to each pece. To construct the parametrc splne nterpolant on the nterval t, t ], we have m [ 0 n F R, = 0,,..., n, as nterpolaton data, at knots t, = 0,,..., n. Obvously, the parameters u 's, when equal to, provde the specal case of quadratc splne. Otherwse, these parameters can be used to loose or tghten the curve. Ths paper proposes an evolutonary technque, namely smulated annealng (SA), to optmze these parameters so that the curve ftted s optmal. For the detals of SA approach, the reader s referred to [30]. Fg.. Pre-processng steps: Orgnal mage, Outlne of the mage, Corner ponts acheved. A. Lnear Splne The curve ftted by a lnear splne s a canddate of best ft, but t may not be a desred ft. Ths leads to the need of ntroducng some extra treatment n the methodology. Ths secton deals wth a form of lnear splne. It ntroduces parameters t s n the descrpton of lnear splne defned as follows: P t) P ( θ ) + P θ () ( = + ( t t ) θ [ t t ( t), ) =, h + = t + t, h and P and P + are corner ponts of the th pece. B. Fnal Stage The curve ftted by a conc splne s a canddate of best ft, but t may not be a desred ft. Ths leads to the need of ntroducng some shape parameters n the descrpton of the conc splne. Ths secton deals wth a form of conc splne. It ntroduces shape parameters u s n the descrpton of conc splne defned as follows: P ( θ ) + uu θ ( θ ) + P + θ = ( θ ) + uθ ( θ ) + θ P ( t), () U ( V + W ) h D =, V = P +, u = h D. + W P + u D and D + are the correspondng tangents at corner ponts P and P + of the th pece. The tangent vectors are calculated as follows: ( P P0 ) D0 = ( P P0 ) D = a ( P P ) + ( a )( P + P ), (3) ( P n Pn ) Dn = ( Pn Pn ) P + P a =. P P + P P + IV. SIMULATED ANNEALING (SA) Smulated annealng (SA) [9], [30] s a global optmzaton method based on the Monte Carlo method. It works on the analogy of the energy n an n-body system the materal s cooled to lower temperatures gradually to result n a perfect crystal structure. The perfect crystal structure s attaned by havng mnmum energy n the materal. Ths analogy translates to the optmzaton done n smulated annealng n fndng a soluton that has the lowest objectve functon value. The soluton space s all the possble solutons. The current soluton s the present state of the materal. The algorthm teratvely tres to change the state of the materal and check whether t has mproved. The materal s state s changed slghtly to fnd a neghborng state.e. a close soluton value n the soluton space. It s possble that all neghborng states of current states are worse solutons. The algorthm allows gong to a worse state wth a certan probablty. Ths probablty decreases as the algorthm teratons proceed. Fnally, t only allows a change n state f t s strctly better than the current soluton. Detals of SA theory can be found n [9], [30] and an example applet can be seen n [7]. A detaled descrpton of the mappng of the SA technque on the proposed problem s gven n the next secton. V. PROPOSED APPROACH The proposed approach to the curve problem s descrbed here n detal. It ncludes the phases of problem matchng wth SA usng conc splnes, descrpton of parameters used for SA, curve fttng, and the overall desgns of algorthms A. Problem Mappng Ths secton descrbes about the SA formulaton of the current problem n detal. Our nterest s to optmze the values of conc curve parameters u such that the defned curve fts as close to the orgnal contour segments as possble. We use SA for the optmzaton of these parameters for the ftted curves. Hence the dmensonalty of the soluton space s for conc curves. Each state n the SA soluton space represents a value of u for concs. We start wth an ntal state that s a gven value of u for concs. A startng temperature s also chosen arbtrarly. Ths temperature s an nherent nternal parameter of SA and has no sgnfcance or mappng on our problem. The algorthm mantans a record of the best state ever reached throughout the algorthm run. Ths s the value of u for concs that has gven the best curve fttng so far. Ths best soluton gets updated whenever the algorthm fnds a better soluton. The algorthm teratvely looks for neghborng states that may or may not be better than the current one. These neghborng 30
3 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 states are values of u for concs that are slghtly dfferent from the values of u for concs. The coolng rate n SA s the factor affectng the lkelhood of selectng neghborng values of u for concs that gve a curve fttng worse than the values of u for concs. Note that we apply SA ndependently for each segment of a contour that we have dentfed usng corner ponts. SA s appled sequentally on each of the segments, generatng an optmzed ftted curve for each segment. The algorthm s run untl the maxmum allowed tme s reached, or an optmal curve fttng s attaned. B. Intalzaton Once we have the btmap mage of a generc shape, the boundary of the mage can be extracted usng the method descrbed n Secton. After the boundary ponts of the mage are found, the next step s to detect corner ponts as explaned n Secton. Ths corner detecton technque assgns a measure of corner strength to each of the ponts on the boundary of the mage. Ths step helps to dvde the boundary of the mage nto n segments. Each of these segments s then approxmated by nterpolatng splne descrbed n Sectons 3.. The ntal soluton of splne parameters u values for concs are randomly selected wthn the range [-, ]. C. Curve Fttng After an ntal approxmaton for the segment s obtaned, better approxmatons are obtaned through SA to reach the optmal soluton. We experment wth our system by approxmatng each segment of the boundary usng the conc splnes of Secton 3.. The conc splne method s a varaton of the quadratc splne. It provdes greater control on the shape of the curve and also effcent to compute. The tangents, n the descrpton of the splne, are computed usng the arthmetc mean method descrbed n Eqn. (3). Each boundary segment s approxmated by the splne. The shape parameter u, n the conc splne, provdes greater flexblty over the shape of the curve. These parameters are adjusted usng SA to get the optmal ft. Snce, the objectve of the paper s to come up wth optmal technques whch can provde decent curve ft to the dgtal data. Therefore, the nterest would be to compute the curve n such a way that the sum square error of the computed curve wth the actual curve (dgtzed contour) s mnmzed. Mathematcally, the sum squared dstance s gven by: S [ P u ) P ], t [ t, t ], = 0,,..., n m = (, j, j, j + j=, (4) P,j = (x,j, y,j ), j =,,,m, (5) are the data ponts of the th segment on the dgtzed contour. The parameterzaton over t's s n accordance wth the chord length parameterzaton. Thus the curve ftted n ths way wll be a canddate of best ft. Once an ntal ft for a partcular segment s obtaned, the parameters of the ftted curve u s for concs are adjusted to get better ft. Here, we try to mnmze the sum squared error of Eqn. (4). Usng SA, we try to obtan the optmal values of the curve parameters. We choose ths technque because t s powerful, yet smple to mplement and as shown n Secton 6, performs well for our purpose. D. Segmentaton Usng Intermedate For some segments, the best ft obtaned through teratve mprovement may not be satsfactory. In that case, we subdvde the segment nto smaller segments at ponts the dstance between the boundary and parametrc curve exceeds some predefned threshold. Such ponts are termed as ntermedate ponts. A new parametrc curve s ftted for each new segment. VI. OVERALL APPROACHES AND ALGORITHMS We can summarze all the phases from dgtzaton to optmzaton dscussed n the prevous sectons. The algorthms of the proposed schemes are contaned on varous steps. Algorthm of Secton 6. explans the mechansm for the computaton of lnear curve. Curve manpulaton methodology wth concs, usng SA, has been lad down n Algorthm of Secton 6.. A more detaled descrpton for concs, descrbng the whole system wth step by step flow, s shown n the flowchart demonstrated n Fg.. A. Algorthm for Lnear Interpolant The summary of the algorthm, desgned for optmal curve desgn usng lnear nterpolant, s as follows: Step AG.: Input the mage. Step AG.: Extract the contours from the mage n Step AG.. Step AG.3: Compute the corner ponts from the contour ponts n Step AG. usng the method n Secton. Step AG.4: Ft the lnear splne curve method of Secton 3. to the corner ponts acheved n Step AG.3. Step AG.5: IF the curve, acheved n Step AG.4, s optmal then GO To Step AG.8, ELSE locate the approprate ntermedate ponts (ponts wth hghest devaton) n the undesred curve peces. Step AG.6: Enhance and order the lst of corner and ntermedate ponts acheved n Step AG.3 and AG.5. Step AG.7: GO TO Step AG.4. Step AG.8: STOP. B. Algorthm for Conc Interpolant The summary of the algorthm, desgned for optmal curve desgn usng conc nterpolant, s as follows: Step AG.: Input the mage. Step AG.: Extract the contours from the mage n Step AG.. Step AG.3: Compute the corner ponts from the contour ponts n Step AG. usng the method n Secton 3. for concs. Step AG.4: Compute the dervatve values at the corner / ntermedate ponts. Step AG.5: Compute the best optmal values of the shape parameters u s for concs usng SA. Step AG.6: Ft the splne curve method of Secton 3. for concs to the corner / ntermedate ponts acheved n Step AG.. Step AG.7: IF the curve, acheved n Step AG.6, s optmal then GO To Step AG.0, ELSE locate the approprate ntermedate ponts (ponts wth hghest 303
4 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 devaton) n the undesred curve peces. Step AG.8: Enhance and order the lst of the corner / ntermedate ponts acheved n Step AG.3 and AG.7. Step AG.9: GO TO Step AG.4. Step AG.0: STOP. Start of SA to get Optmzed values for u for ftted curve on gven segment Compute Tangent Vectors for segment usng Arthmetc Mean Method Fg.. Flowchart of the system computaton of conc curves usng SA. 304
5 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 Fg. 3. Results of lnear scheme: Ftted outlne of the mage, Ftted outlne of the mage wth ntermedate ponts. Results of conc scheme: Ftted outlne of the mage, (d) Ftted outlne of the mage wth ntermedate ponts. (d) Fg. 6. Pre-processng steps for curve fttng Image of a plane, Extracted outlne Intal corner ponts. Fg. 4. Pre-processng Steps: Orgnal Image, Outlne of the mage, Corner ponts acheved, (d) Ftted Outlne of the mage. Fg. 7. Results of lnear scheme : Ftted outlne of the mage, Ftted outlne of the mage wth ntermedate ponts. Results of conc scheme: Ftted outlne of the mage, (d) Ftted outlne of the mage wth ntermedate ponts. The above mentoned schemes and the algorthms have been mplemented and tested for varous mages. Reasonably qute elegant results have been observed as can be seen n the followng Secton of demonstratons. (d) Fg. 5. Results of curve fttng. lnear curve fttng: Ftted outlne of the mage, Ftted outlne of the mage wth ntermedate ponts. Conc curve fttng: Ftted outlne of the mage, (d) Ftted outlne of the mage wth ntermedate ponts (d) VII. DEMONSTRATIONS The proposed curve scheme has been mplemented successfully n ths secton. We evaluate the performance of the system by fttng parametrc curves to dfferent bnary mages. Fg. 3 shows the mplementaton results of the two algorthms for the mage Lllah of Fg.. Fgs. 3 and 3 are the results for the lnear scheme, respectvely, wthout and wth nserton of ntermedate ponts. Smlarly, Fgs. 3 and 3(d) are the results for the conc scheme, respectvely, wthout and wth nserton of ntermedate 305
6 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 ponts. Fgs. 4 and 5 show the mplementaton results of a Tua mage. Fgs. 4, 4, 4 are respectvely the orgnal mage of the Plane, ts outlne, outlne together wth the corner ponts detected. Fg. 5 shows the mplementaton results of the two algorthms for the Tua mage n Fg. 4. Fgs. 5 and 5 are the results for the lnear scheme, respectvely, wthout and wth nserton of ntermedate ponts. Smlarly, Fgs. 5 and 5(d) are the results for the conc scheme, respectvely, wthout and wth nserton of ntermedate ponts. Fgs. 6 and 7 show the mplementaton results of a Fork mage. Fgs. 6, 6, 6 are, respectvely, the orgnal mage of the Fork, ts outlne, outlne together wth the corner ponts detected. Fg. 7 shows the mplementaton results of the two algorthms for the mage n Fg. 6. Fgs. 7 and 7 are the results for the lnear scheme, respectvely, wthout and wth nserton of ntermedate ponts. Smlarly, Fgs. 7 and 7(d) are the results for the conc scheme, respectvely, wthout and wth nserton of ntermedate ponts. One can see that the approxmaton s not satsfactory when t s acheved over the corner ponts only. Ths s specfcally due to those segments whch are bgger n sze and hghly curvy n nature. Thus, some more treatment s requred for such outlnes. Ths s the reason that the dea to nsert some ntermedate ponts s demonstrated n the algorthms. It provdes excellent results. The dea of how to nsert ntermedate ponts s not explaned here due to lmtaton of space. It wll be explaned n a subsequent paper. TABLE I: NAMES AND CONTOUR DETAILS OF IMAGES Image Name # of Contours # of Contour # of Intal Corner Lllah [5+6] 4 Tua [045+85] nterpolaton, and total tme taken for conc nterpolaton. TABLE III: COMPARISON OF NUMBER OF INITIAL CORNER POINTS, INTERMEDIATE POINTS AND TOTAL TIME TAKEN (IN SECONDS) FOR CONIC INTERPOLATION APPROACHES Image # of Intermedate n Conc Interpolaton Total Tme Taken for Conc Interpolaton Wthout Wth Intermedate Intermedate Lllah.bmp Tua.bmp Fork.bmp VIII. CONCLUSION Two optmzaton technques are proposed for the outlne capture of planar mages. Frst technque uses smply a lnear nterpolant and a straght forward method based on dstrbuton of corner and ntermedate ponts. Second technque uses the smulated annealng to optmze a conc splne to the dgtal outlne of planar mages. By startng a search from certan good ponts (ntally detected corner ponts), an mproved convergence result s obtaned. The overall technque has varous phases ncludng extractng outlnes of mages, detectng corner ponts from the detected outlne, curve fttng, and addton of extra knot ponts f needed. The dea of smulated annealng has been used to optmze the shape parameters n the descrpton of a conc splne ntroduced. The two methods ultmately produce optmal results for the approxmate vectorzaton of the dgtal contours obtaned from the generc shapes. The schemes provde an optmal ft wth an effcent computaton cost as far as curve fttng s concerned. The proposed algorthms are fully automatc and requre no human nterventon. The author s also thnkng to apply the proposed methodology for another model curve namely cubc. It mght mprove the approxmaton process. Ths work s n progress to be publshed as a subsequent work. Fork [693] 0 ACKNOWLEDGMENT M. Sarfraz thanks Kuwat Unversty for supportng ths work through Project# [WI 05/0]. TABLE II: COMPARISON OF NUMBER OF INITIAL CORNER POINTS, INTERMEDIATE POINTS AND TOTAL TIME TAKEN (IN SECONDS) FOR CONIC INTERPOLATION APPROACHES Image # of Intermedate n Lnear Interpolaton Total Tme Taken For Lnear Interpolaton Wthout Wth Intermedate Intermedate Lllah.bmp Tua.bmp Fork.bmp Tables I, II and III summarze the expermental results for dfferent btmap mages. These results hghlght varous nformaton ncludng contour detals of mages, corner ponts, ntermedate ponts, total tme taken for lnear REFERENCES [] X. Yang, Curve Fttng and Farng usng Conc Spnes, Computer Aded Desgn, vol. 6, no. 5, pp , 004. [] X. N. Yang and G. Z. Wang, Planar Pont Set Farng and Fttng by Arc Splnes, Computer Aded Desgn, vol. 33(), pp , 00. [3] M. Sarfraz, Desgnng Objects wth a Splne, Computer Mathematcs, vol. 87, no. 4, pp , 00. [4] M. Sarfraz, Representng Shapes by Fttng Data usng an Evolutonary Approach, Computer-Aded Desgn & Applcatons, vol., no. -4, pp 79-86, 004. [5] M. Sarfraz and M. A. Khan, An Automatc Algorthm for Approxmatng Boundary of Btmap Characters, Future Generaton Computer Systems, vol. 0, no. 8, pp , 004. [6] M. Sarfraz, Some Algorthms for Curve Desgn and Automatc Outlne Capturng of Images, Image and Graphcs, vol. 4, no., pp , 004. [7] Z. J. Hou and G. W. We, A New Approach to Edge Detecton, Pattern Recognton, vol. 35, no. 7, pp ,
7 Internatonal Journal of Machne Learnng and Computng, Vol., No. 3, June 0 [8] M. Sarfraz, Computer-Aded Reverse Engneerng usng Smulated Evoluton on NURBS, Vrtual & Physcal Prototypng, vol., no. 4, pp , 006. [9] M. Sarfraz, M. Ryazuddn, and M. H. Bag, Capturng Planar Shapes by Approxmatng ther Outlnes, Computatonal and Appled Mathematcs, vol. 89, no. -, pp , 006. [0] M. Sarfraz, A. Rasheed, A Randomzed Knot Inserton Algorthm for Outlne Capture of Planar Images usng Cubc Splne, n Proc. nd ACM Symposum on Appled Computng (ACM SAC-07), Seoul, Korea, pp. 7 75, 007. [] H. Kano, H. Nakata, C. F. Martn, Optmal Curve Fttng and Smoothng usng Normalzed Unform B-Splnes: A Tool for Studyng Complex Systems, Appled Mathematcs and Computaton, vol.69, no., pp. 96-8, 005. [] Z. Yang, J. Deng, F. Chen, Fttng Unorganzed Pont Clouds wth Actve Implct B-Splne Curves, Vsual Computer, vol., no. 8-0, pp (005). [3] G. Lavoue, F. Dupont, A. Baskurt, A New Subdvson Based Approach for Pecewse Smooth Approxmaton of 3D Polygonal Curves, Pattern Recognton, vol. 38, pp. 39-5, 005. [4] H. Yang, W. Wang, and J. Sun, Control Pont Adjustment for B-Splne Curve Approxmaton, Computer Aded Desgn, vol. 36, pp , 004. [5] J. H. Horng, An Adaptve Smoothng Approach for Fttng Dgtal Planar Curves wth Lne Segments and Crcular Arcs, Pattern Recognton Letters, vol. 4, no. -3, pp , 003. [6] B. Sarkar, L. K. Sngh, and D. Sarkar, Approxmaton of Dgtal Curves wth Lne Segments and Crcular Arcs usng Genetc Algorthms, Pattern Recognton Letters, vol. 4, pp , 003. [7] M. Sarfraz, Vectorzng Image Outlnes usng Splne Computng Approach, n Proc. 4th Internatonal Conf. Machne Learnng and Computng (ICMLC 0), Hong Kong, Chna, March 0, 0, ASME. [8] S. Krkpatrck, C. D. Gelatt Jr., M. P. Vecch, "Optmzaton by Smulated Annealng", Scence, Vol. 0, no. 4598, pp , 983. [9] M. Sarfraz, and M. I. Sarfraz, Capturng Image Outlnes usng Splne Computng Approach, n Proc. 5th Internatonal Conf. Sgnal-Image Technology & Internet Based Systems (SITIS-009), November 30 December 03, 009, Marrakech, Morocco, pp. 6-3, 009, IEEE Computer Socety Press. [0] R. C. Gonzalez, R. E. Woods, and S. L. Eddns, Dgtal Image Processng Usng MATLAB, nd Ed., Gatesmark Publshng, 009. [] M. S. Nxon, A. S. Aguado, Feature extracton and mage processng, Elsever, 008. [] M. Sarfraz, Outlne Capture of Images by Multlevel Coordnate Search on Cubc Splnes, Lecture Notes n Artfcal Intellgence, A. Ncholson and X. L (Eds.): LNAI 5866, Sprnger-Verlag Berln Hedelberg, pp , 009. [3] D. Chetrkov and S. Zsabo, A Smple and Effcent Algorthm for Detecton of Hgh Curvature n Planar Curves, n Proc. 3 rd Workshop of the Australan Pattern Recognton Group, pp , 999. [4] A. A. Goshtasby Groupng and Parameterzng Irregularly Spaced for Curve Fttng, ACM Transactons on Graphcs, vol. 9, no. 3, pp , 000. [5] P. Reche, C. Urdales, A. Bandera, C. Trazegnes, and F. Sandoval, Corner Detecton by Means of Contour Local Vectors, Electronc Letters, vol. 38, no. 4, 00. [6] M. Marj and P. Sv, A New Algorthm for Domnant Detecton and Polygonzaton of Dgtal Curves, Pattern Recognton, vol. 36, no. 0, pp. 39-5, 003. [7] Wu-Chh Hu, Multprmtve Segmentaton Based on Meanngful Breakponts for Fttng Dgtal Planar Curves wth Lne Segments and Conc Arcs, Image and Vson Computng, vol. 3, no. 9, pp , 005. [8] H. Freeman, L. S. Davs, A corner fndng algorthm for chan-coded curves, IEEE Trans. Computers, Vol. 6, pp , 977. [9] N. Rchardand T. Glbert, Extracton of Domnant by estmaton of the contour fluctuatons, Pattern Recognton, vol. 35, pp , 00. [30] M. Sarfraz, Vectorzng Outlnes of Generc Shapes by Cubc Splne usng Smulated Annealng, Computer Mathematcs, Vol. 87, no. 8, pp , 00. Muhammad Sarfraz s a Professor n Kuwat Unversty, Kuwat. He receved hs Ph. D. from Brunel Unversty, UK, n 990. Hs research nterests, n general, are Computer Graphcs, Pattern Recognton, Computer Vson, Image Processng, and Soft Computng. He s currently workng on varous projects related to academa and ndustry. Prof. Sarfraz has advsed/supervsed more than 50 students for ther MSc and PhD theses. He s the Head of Research Commttee n Informaton Scence Department, Kuwat Unversty. He has publshed more than 00 publcatons n the form of varous Books, Book Chapters, journal papers and conference papers. Prof. Sarfraz s member of varous professonal socetes ncludng IEEE, ACM, IVS, IACSIT, Pattern Recognton Socety, and ISOSS. He s a Char, member of the Internatonal Advsory Commttees and Organzng Commttees of varous nternatonal conferences, Symposums and Workshops. He s the revewer, for many nternatonal Journals, Conferences, meetngs, and workshops around the world. He s the Edtor-n-Chef of three nternatonal journals. He s also Edtor/Guest Edtor of varous Internatonal Conference Proceedngs, Books, and Journals. He has acheved varous awards n educaton, research, and admnstratve servces. 307
Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm
01 Internatonal Conference on Image, Vson and Computng (ICIVC 01) IPCSIT vol. 50 (01) (01) IACSIT Press, Sngapore DOI: 10.776/IPCSIT.01.V50.4 Vectorzaton of Image Outlnes Usng Ratonal Splne and Genetc
More informationVectorizing Image Outlines using Spline Computing Approaches with Simulated Annealing
Vectorzng Image Outlnes usng Splne Computng Approaches wth Smulated Annealng MUHAMMAD SARFRAZ Department of Informaton Scence Kuwat Unversty Adalya Campus, P.O. Box 5969, Safat 1060 KUWAIT prof.m.sarfraz@gmal.com
More informationCurve Representation for Outlines of Planar Images using Multilevel Coordinate Search
Curve Representaton for Outlnes of Planar Images usng Multlevel Coordnate Search MHAMMAD SARFRAZ and NAELAH AL-DABBOUS Department of Informaton Scence Kuwat Unversty Adalya Campus, P.O. Box 5969, Safat
More informationReverse Engineering of the Digital Curve Outlines using Genetic Algorithm
Issue, Volume 7, 03 Reverse Engneerng of the Dgtal Curve Outlnes usng Genetc Algorthm Muhammad Sarfraz, Malk Zawwar Hussan, Msbah Irshad Abstract A scheme, whch conssts of an teratve approach for the recovery
More informationA Binarization Algorithm specialized on Document Images and Photos
A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a
More informationImprovement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration
Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,
More informationParallelism for Nested Loops with Non-uniform and Flow Dependences
Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr
More informationOutline. 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 informationAn Optimal Algorithm for Prufer Codes *
J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,
More informationLearning the Kernel Parameters in Kernel Minimum Distance Classifier
Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department
More informationActive Contours/Snakes
Actve Contours/Snakes Erkut Erdem Acknowledgement: The sldes are adapted from the sldes prepared by K. Grauman of Unversty of Texas at Austn Fttng: Edges vs. boundares Edges useful sgnal to ndcate occludng
More informationThe Shortest Path of Touring Lines given in the Plane
Send Orders for Reprnts to reprnts@benthamscence.ae 262 The Open Cybernetcs & Systemcs Journal, 2015, 9, 262-267 The Shortest Path of Tourng Lnes gven n the Plane Open Access Ljuan Wang 1,2, Dandan He
More informationA 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 informationUnsupervised 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 informationNUMERICAL 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 informationA B-Snake Model Using Statistical and Geometric Information - Applications to Medical Images
A B-Snake Model Usng Statstcal and Geometrc Informaton - Applcatons to Medcal Images Yue Wang, Eam Khwang Teoh and Dnggang Shen 2 School of Electrcal and Electronc Engneerng, Nanyang Technologcal Unversty
More informationS1 Note. Basis functions.
S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type
More informationSmoothing Spline ANOVA for variable screening
Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory
More informationThe Codesign Challenge
ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.
More information2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements
Module 3: Element Propertes Lecture : Lagrange and Serendpty Elements 5 In last lecture note, the nterpolaton functons are derved on the bass of assumed polynomal from Pascal s trangle for the fled varable.
More informationRange images. Range image registration. Examples of sampling patterns. Range images and range surfaces
Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples
More informationSkew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach
Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research
More informationSupport Vector Machines
/9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.
More informationA Fast Content-Based Multimedia Retrieval Technique Using Compressed Data
A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,
More informationRelated-Mode Attacks on CTR Encryption Mode
Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory
More informationA Newton-Type Method for Constrained Least-Squares Data-Fitting with Easy-to-Control Rational Curves
A Newton-Type Method for Constraned Least-Squares Data-Fttng wth Easy-to-Control Ratonal Curves G. Cascola a, L. Roman b, a Department of Mathematcs, Unversty of Bologna, P.zza d Porta San Donato 5, 4017
More informationProblem 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 informationInvariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm
Proceedngs of the 5th WSEAS Int. Conf. on Sgnal Processng, Robotcs and Automaton, Madrd, Span, February 5-7, 6 (pp4-45) Invarant Shape Obect Recognton Usng B-Splne, Cardnal Splne, and Genetc Algorthm PISIT
More informationCluster Analysis of Electrical Behavior
Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School
More informationInterpolation of the Irregular Curve Network of Ship Hull Form Using Subdivision Surfaces
7 Interpolaton of the Irregular Curve Network of Shp Hull Form Usng Subdvson Surfaces Kyu-Yeul Lee, Doo-Yeoun Cho and Tae-Wan Km Seoul Natonal Unversty, kylee@snu.ac.kr,whendus@snu.ac.kr,taewan}@snu.ac.kr
More information2-Dimensional Image Representation. Using Beta-Spline
Appled Mathematcal cences, Vol. 7, 03, no. 9, 4559-4569 HIKARI Ltd, www.m-hkar.com http://dx.do.org/0.988/ams.03.3359 -Dmensonal Image Representaton Usng Beta-plne Norm Abdul Had Faculty of Computer and
More informationSum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints
Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan
More informationType-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data
Malaysan Journal of Mathematcal Scences 11(S) Aprl : 35 46 (2017) Specal Issue: The 2nd Internatonal Conference and Workshop on Mathematcal Analyss (ICWOMA 2016) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES
More informationTN348: Openlab Module - Colocalization
TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages
More informationDetermining 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 informationConstrained Shape Modification of B-Spline curves
Constraned Shape Modfcaton of B-Splne curves Mukul Tul, N. Venkata Reddy and Anupam Saxena Indan Insttute of Technology Kanpur, mukult@tk.ac.n, nvr@tk.ac.n, anupams@tk.ac.n ABSTRACT Ths paper proposes
More informationMULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION
MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and
More informationThe Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique
//00 :0 AM Outlne and Readng The Greedy Method The Greedy Method Technque (secton.) Fractonal Knapsack Problem (secton..) Task Schedulng (secton..) Mnmum Spannng Trees (secton.) Change Money Problem Greedy
More informationHigh-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 informationSolving 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 informationA 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 informationCompiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz
Compler Desgn Sprng 2014 Regster Allocaton Sample Exercses and Solutons Prof. Pedro C. Dnz USC / Informaton Scences Insttute 4676 Admralty Way, Sute 1001 Marna del Rey, Calforna 90292 pedro@s.edu Regster
More informationFitting: Deformable contours April 26 th, 2018
4/6/08 Fttng: Deformable contours Aprl 6 th, 08 Yong Jae Lee UC Davs Recap so far: Groupng and Fttng Goal: move from array of pxel values (or flter outputs) to a collecton of regons, objects, and shapes.
More informationContent Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers
IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth
More informationFast Computation of Shortest Path for Visiting Segments in the Plane
Send Orders for Reprnts to reprnts@benthamscence.ae 4 The Open Cybernetcs & Systemcs Journal, 04, 8, 4-9 Open Access Fast Computaton of Shortest Path for Vstng Segments n the Plane Ljuan Wang,, Bo Jang
More informationLocal Quaternary Patterns and Feature Local Quaternary Patterns
Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents
More informationEnhanced AMBTC for Image Compression using Block Classification and Interpolation
Internatonal Journal of Computer Applcatons (0975 8887) Volume 5 No.0, August 0 Enhanced AMBTC for Image Compresson usng Block Classfcaton and Interpolaton S. Vmala Dept. of Comp. Scence Mother Teresa
More informationSubspace 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 informationHermite 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 informationShape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram
Shape Representaton Robust to the Sketchng Order Usng Dstance Map and Drecton Hstogram Department of Computer Scence Yonse Unversty Kwon Yun CONTENTS Revew Topc Proposed Method System Overvew Sketch Normalzaton
More informationMathematics 256 a course in differential equations for engineering students
Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the
More informationA 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 informationCS 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 informationA Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems
A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty
More informationAn Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation
17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed
More informationFace Recognition University at Buffalo CSE666 Lecture Slides Resources:
Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural
More informationOutline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1
4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:
More informationReading. 14. Subdivision curves. Recommended:
eadng ecommended: Stollntz, Deose, and Salesn. Wavelets for Computer Graphcs: heory and Applcatons, 996, secton 6.-6., A.5. 4. Subdvson curves Note: there s an error n Stollntz, et al., secton A.5. Equaton
More informationTerm 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 informationA PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION
1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute
More informationModeling, Manipulating, and Visualizing Continuous Volumetric Data: A Novel Spline-based Approach
Modelng, Manpulatng, and Vsualzng Contnuous Volumetrc Data: A Novel Splne-based Approach Jng Hua Center for Vsual Computng, Department of Computer Scence SUNY at Stony Brook Talk Outlne Introducton and
More informationQuality 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 informationUser Authentication Based On Behavioral Mouse Dynamics Biometrics
User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA
More informationFace Recognition Based on SVM and 2DPCA
Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty
More informationCSCI 104 Sorting Algorithms. Mark Redekopp David Kempe
CSCI 104 Sortng Algorthms Mark Redekopp Davd Kempe Algorthm Effcency SORTING 2 Sortng If we have an unordered lst, sequental search becomes our only choce If we wll perform a lot of searches t may be benefcal
More informationCS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15
CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc
More informationMulti-objective Design Optimization of MCM Placement
Proceedngs of the 5th WSEAS Int. Conf. on Instrumentaton, Measurement, Crcuts and Systems, Hangzhou, Chna, Aprl 6-8, 26 (pp56-6) Mult-objectve Desgn Optmzaton of MCM Placement Chng-Ma Ko ab, Yu-Jung Huang
More informationMaximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation
Internatonal Conference on Logstcs Engneerng, Management and Computer Scence (LEMCS 5) Maxmum Varance Combned wth Adaptve Genetc Algorthm for Infrared Image Segmentaton Huxuan Fu College of Automaton Harbn
More informationA mathematical programming approach to the analysis, design and scheduling of offshore oilfields
17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and
More information3D Virtual Eyeglass Frames Modeling from Multiple Camera Image Data Based on the GFFD Deformation Method
NICOGRAPH Internatonal 2012, pp. 114-119 3D Vrtual Eyeglass Frames Modelng from Multple Camera Image Data Based on the GFFD Deformaton Method Norak Tamura, Somsangouane Sngthemphone and Katsuhro Ktama
More informationThe 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 informationEdge Detection in Noisy Images Using the Support Vector Machines
Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona
More informationFEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur
FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents
More informationCourse Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms
Course Introducton Course Topcs Exams, abs, Proects A quc loo at a few algorthms 1 Advanced Data Structures and Algorthms Descrpton: We are gong to dscuss algorthm complexty analyss, algorthm desgn technques
More informationSignature and Lexicon Pruning Techniques
Sgnature and Lexcon Prunng Technques Srnvas Palla, Hansheng Le, Venu Govndaraju Centre for Unfed Bometrcs and Sensors Unversty at Buffalo {spalla2, hle, govnd}@cedar.buffalo.edu Abstract Handwrtten word
More informationMachine Learning. Topic 6: Clustering
Machne Learnng Topc 6: lusterng lusterng Groupng data nto (hopefully useful) sets. Thngs on the left Thngs on the rght Applcatons of lusterng Hypothess Generaton lusters mght suggest natural groups. Hypothess
More informationShape Preserving Positive and Convex Data Visualization using Rational Bi-cubic Functions
Shape Preservng Postve and Conve Data Vsualzaton usng Ratonal B-cubc unctons Muhammad Sarfraz Malk Zawwar Hussan 3 Tahra Sumbal Shakh Department of Informaton Scence Adala Campus Kuwat Unverst Kuwat E-mal:
More informationModule Management Tool in Software Development Organizations
Journal of Computer Scence (5): 8-, 7 ISSN 59-66 7 Scence Publcatons Management Tool n Software Development Organzatons Ahmad A. Al-Rababah and Mohammad A. Al-Rababah Faculty of IT, Al-Ahlyyah Amman Unversty,
More informationUsing Fuzzy Logic to Enhance the Large Size Remote Sensing Images
Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract
More informationLoop Transformations, Dependences, and Parallelization
Loop Transformatons, Dependences, and Parallelzaton Announcements Mdterm s Frday from 3-4:15 n ths room Today Semester long project Data dependence recap Parallelsm and storage tradeoff Scalar expanson
More informationImage Alignment CSC 767
Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances
More informationSLAM Summer School 2006 Practical 2: SLAM using Monocular Vision
SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,
More informationGSLM Operations Research II Fall 13/14
GSLM 58 Operatons Research II Fall /4 6. Separable Programmng Consder a general NLP mn f(x) s.t. g j (x) b j j =. m. Defnton 6.. The NLP s a separable program f ts objectve functon and all constrants are
More informationAssignment # 2. Farrukh Jabeen Algorithms 510 Assignment #2 Due Date: June 15, 2009.
Farrukh Jabeen Algorthms 51 Assgnment #2 Due Date: June 15, 29. Assgnment # 2 Chapter 3 Dscrete Fourer Transforms Implement the FFT for the DFT. Descrbed n sectons 3.1 and 3.2. Delverables: 1. Concse descrpton
More informationAn Improved Image Segmentation Algorithm Based on the Otsu Method
3th ACIS Internatonal Conference on Software Engneerng, Artfcal Intellgence, Networkng arallel/dstrbuted Computng An Improved Image Segmentaton Algorthm Based on the Otsu Method Mengxng Huang, enjao Yu,
More informationAn Image Fusion Approach Based on Segmentation Region
Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua
More informationNAG Fortran Library Chapter Introduction. G10 Smoothing in Statistics
Introducton G10 NAG Fortran Lbrary Chapter Introducton G10 Smoothng n Statstcs Contents 1 Scope of the Chapter... 2 2 Background to the Problems... 2 2.1 Smoothng Methods... 2 2.2 Smoothng Splnes and Regresson
More informationCorner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity
Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent
More informationResearch and Application of Fingerprint Recognition Based on MATLAB
Send Orders for Reprnts to reprnts@benthamscence.ae The Open Automaton and Control Systems Journal, 205, 7, 07-07 Open Access Research and Applcaton of Fngerprnt Recognton Based on MATLAB Nng Lu* Department
More informationBoundary Detection Using Open Spline Curve Based on Mumford-Shah Model
Vol. 35, o. 2 ACTA AUTOMATICA SIICA February, 2009 Boundary Detecton Usng Open Splne Curve Based on Mumford-Shah Model LI ao-mao 1, 2 ZHU Ln-Ln 1, 2 TAG Yan-Dong 1 Abstract Inspred by Cremers s work, ths
More informationOptimizing Document Scoring for Query Retrieval
Optmzng Document Scorng for Query Retreval Brent Ellwen baellwe@cs.stanford.edu Abstract The goal of ths project was to automate the process of tunng a document query engne. Specfcally, I used machne learnng
More informationRefinement to the Chamfer matching for a center-on fit
Refnement to the Chamfer matchng for a center-on ft Jngyng Chen Paul Tan Terence Goh Sngapore Technologes Dynamcs 249 Jalan Boon Lay Sngapore 69523 Abstract Matchng s a central problem n mage analyss and
More informationF Geometric Mean Graphs
Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 1932-9466 Vol. 10, Issue 2 (December 2015), pp. 937-952 Applcatons and Appled Mathematcs: An Internatonal Journal (AAM) F Geometrc Mean Graphs A.
More informationObstacle-Aware Routing Problem in. a Rectangular Mesh Network
Appled Mathematcal Scences, Vol. 9, 015, no. 14, 653-663 HIKARI Ltd, www.m-hkar.com http://dx.do.org/10.1988/ams.015.411911 Obstacle-Aware Routng Problem n a Rectangular Mesh Network Norazah Adzhar Department
More informationComputer Animation and Visualisation. Lecture 4. Rigging / Skinning
Computer Anmaton and Vsualsaton Lecture 4. Rggng / Sknnng Taku Komura Overvew Sknnng / Rggng Background knowledge Lnear Blendng How to decde weghts? Example-based Method Anatomcal models Sknnng Assume
More informationImage Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline
mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and
More informationLoad Balancing for Hex-Cell Interconnection Network
Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,
More informationLecture 5: Multilayer Perceptrons
Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented
More informationPerformance Evaluation of an ANFIS Based Power System Stabilizer Applied in Multi-Machine Power Systems
Performance Evaluaton of an ANFIS Based Power System Stablzer Appled n Mult-Machne Power Systems A. A GHARAVEISI 1,2 A.DARABI 3 M. MONADI 4 A. KHAJEH-ZADEH 5 M. RASHIDI-NEJAD 1,2,5 1. Shahd Bahonar Unversty
More informationTsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance
Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for
More information