A Shadow Detection Method for Remote Sensing Images Using Affinity Propagation Algorithm

Size: px
Start display at page:

Download "A Shadow Detection Method for Remote Sensing Images Using Affinity Propagation Algorithm"

Transcription

1 Proceedngs of the 009 IEEE Internatonal Conference on Systems, Man, and Cybernetcs San Antono, TX, USA - October 009 A Shadow Detecton Method for Remote Sensng Images Usng Affnty Propagaton Algorthm Huayng Xa 1, Xnyu Chen 1 1 Image Processng and Pattern Recognton Laboratory Bejng Normal Unversty Bejng, , Chna xa_huayng@163.com, xychen@bnu.edu.cn Abstract Shadow detecton n hgh spatal resoluton remote sensng mage s very crtcal for locatng geographcal targets. In ths paper, we proposed a new shadow detecton method usng Affnty Propagaton (AP) algorthm n the Hue-Saturaton Intensty (HSI) color space. Because the pxel matrx s a largescale matrx, f we apply AP algorthm drectly on the raw pxel space, t wll be computaton ntensve to calculate the smlarty matrx. To solve ths problem, we propose to dvde the matrx nto several blocs and then applyng AP to detect shadows n H, S and I components respectvely. Then, three detected mages are fused to obtan a fnal shadow detecton result. Comparatve experments are performed for K-means and threshold segmentaton methods. The expermental results show that hgher detecton accuracy of the proposed approach s obtaned, and t can solve the problems of false dsmssals of K-means and threshold segmentaton method. Keywords Affnty Propagaton, Shadow Detecton, Remote Sensng Image, HSI Color Space, K-means I. INTRODUCTION In hgh spatal resoluton remote sensng mages, shadows are usually cast by elevated objects such as buldngs, brdges, and towers, whch s especally obvous n urban regons. Shadows can provde geometrc and semantc nformaton contaned n mages, ncludng cues about shapes and relatve postons of objects, as well as the characterstcs of surfaces and lght sources. However, shadows may also cause loss of feature nformaton, false color tone, and objects shape dstortons, whch affect the qualty of mages serously, and nfluence the effects of mage processng drectly, such as object recognton, change detecton and scene matchng [1] [] [3]. Hence, t s mportant to segment shadow regons and restore ther nformaton for mage nterpretaton. To process shadows or to use the nformaton provded by shadows, we must detect shadows accurately frst. It s not dffcult for humans to dentfy shadow n remote sensng mages, because shadow tself s one of the fundamental elements n vsual photo nterpretaton for obtanng nformaton about the shape, relatve poston, and surface characterstcs of objects n the scene. However, dentfyng shadows n dgtal mages by computers nvolves developng effectve algorthms n solvng many dffcult problems. Many technques for shadow detecton are developed for vdeo mages. However, n remote sensng mages feld, few technques are developed, whch manly based on model and property []. The approach based on model employs a pror nowledge of the llumnaton and the 3D geometry of the Png Guo 1, School of Computer Scence and Technology Bejng Insttute of Technology Bejng, , Chna pguo@eee.org scene beng maged to calculate postons of shadows. However, ths method has rarely been used because the pror nowledge s not always avalable. The method based on property s generally used by analyss of lghtness, geometry structure and color character [3]. Recent exstng shadow detecton methods are commonly based on property, whch can be summarzed nto three types: threshold segmentaton method, color space ratos and photometrc color nvarants, and homomorphc flterng [1] [3]. Those methods get some achevements. However, none of them alone acheves common acceptablty to all nds of mages. The man reason s the complexty of mage shadow formaton mechansm. Shadow areas are beleved to be of lower ntensty than surroundng areas. For gray mages, shadows could be detected by approprate ntensty threshold. However, for color mages, there exst no-shadowed areas wth low ntensty (e.g. areas wth darer colors), threshold technques, such as hstogram threshold method, Otsu s method, maxmum entropy threshold, may msclassfy these areas as shadows [4] [5]. To overcome ths drawbac, we propose a novel method based on the Affnty Propagaton (AP) clusterng algorthm n the HSI color space for shadow detecton. Comparatve experments are performed for K-means [6] and hstogram threshold methods [7]. These methods are comparable because they are actually mage segmentaton method. Expermental results show that the proposed method s better than K-means and hstogram threshold n terms of accuracy, stablty and robustness. Ths paper s organzed as follows: In Secton II, the AP clusterng method and HSI color space are revewed. Secton III presents the developed shadow detecton approach. In Secton IV, expermental results are presented and analyzed. And fnally, some dscussons and conclusons are gven n Secton V. II. RELATED WORK A. Affnty Propagaton The AP clusterng technque was presented by Brendan J. Frey and Delbert Duec [8]. AP clusterng begns wth a collecton of real-valued smlartes between pars of data ponts, and teratvely exchanges the real-valued messages between data ponts so as to produce a hgh-qualty set of centers and correspondng clusters. There are several ndcators n AP. The smlarty s(, ) ndcates how well the data pont wth ndex s sutable to be the center for data pont. The /09/$ IEEE 305

2 smlarty s the negatve squared error for mnmzng the squared error, thus for ponts x and x, s (, ) = x x. (1) When the value of s(, ) s nfnte (INF), messages wll not be exchanged between ponts x and x. In partcular, a real number s(, ) for each data pont s assgned a common value so that data ponts wth larger values of s(, ) are more lely to be chosen as centers after the message-passng procedure. These values are referred to as preferences, whch drectly decdes the number of clusters. The bgger number of clusters s, the larger values of the nput preferences are. There are two nds of message exchanged between data ponts, the frst one s the responsblty r(, ), whch s sent from data pont to pont, reflectng the accumulated evdence for how well-suted pont s to serve as the center for pont, consderng other potental centers for pont. In partcular, the self-responsblty reflects accumulated evdence that pont s a center, based on ts nput preference tempered by how ll-suted t s to be assgned to another center. The second one s the avalablty a(, ), whch s sent from canddate center pont to pont, reflectng the accumulated evdence for how approprate t would be for pont to choose pont as ts center, consderng the support from other pont that pont should be a center. In partcular, the self-avalablty a(, ) reflects accumulated evdence that pont s a center, based on the postve responsbltes sent to canddate center from other ponts. The whole clusterng procedure can be dvded nto the followng steps: 1) The avalabltes are ntalzed to zero: a(, ) = 0. The smlarty s computed and s(, ) s assgned a common value based on the dataset s value range. In our experment, we ntalze s(, ) to be the mnmum of nput smlartes. ) The responsbltes are computed usng the rule (), r (, ) s (, ) max { a (, ') + s (, ')}. () ': ' 3) The avalabltes are computed usng the rule (3), a (, ) mn{0, r (, ) + max{0, r ( ', )}}. (3) ': ' {, } 4) The self-avalablty a(, ) s updated dfferently: a (, ) max{0, r ( ', )}. (4) ': ' 5) If any of the followng stuatons occurs: after a fxed number of teratons, after changes n the messages fall below a threshold, or after the local decsons stay constant for some number of teratons, the clusterng procedure s termnated, else go to step. 6) Determne the center and ther ponts. For pont, the value of that maxmzes a(, ) + r(, ) ether dentfes pont as a center f =, or dentfes the data pont that s the center for pont. In order to avod numercal oscllatons n the procedure of exchangng message, a dampng factor λ s ntroduced, whch s between 0 and 1. Each message s set to λ tmes ts value from the prevous teraton plus 1-λ tmes ts prescrbed updated value. For example, f the value of a(, ) by the message-passng procedure s a(, ) cur, the old value of a(, ) s a(, ) old, then the new value of a(, ) new s (1-λ) a(, ) cur + λ a(, ) old. In our experments, we set dumpng parameter λ as 0.5, ntalze the s(, ) to be the mnmum of the nput smlarty matrx and fx the cluster number to be. Unle other methods for whch the number of clusters must be specfed, and whch are qute senstve to the ntal selecton of centers, AP taes as nput a real number s(, ) for each pont. Experment done by B. J. Frey and D. Duec has shown that AP fnds clusters wth much lower error. More detals and proof about the AP algorthm can be found n [8]. B. K-means The K-means [9] algorthm wors as follows. Frstly, t randomly selects of the objects, each of whch ntally represents a cluster mean. For each of the remanng objects, an object s assgned to the cluster to whch s the most smlar based on the dstance between the object and the cluster mean. Then t computes the new mean of each cluster. Ths procedure terates untl the crteron functon converges. The squarederror crteron s defned as expresson (5): E = p m. (5) = 1 p C Where E s the sum of square-error for all objects n the database, p s the pont n the space representng a gven object, and m s the mean of cluster C. The algorthm attempts to determne parttons that mnmze the squared-error functon. From these two clusterng algorthms, we can see that the classcal K-means clusterng result s related to ts ntal cluster means value whle that of AP s not. C. HSI Color Space The dffculty of usng the RGB color space s that t does not model the psychologcal understandng of color closely. The HSI model, whch follows the human vsual percepton closely, s a better color model. Ths color model separates the color components n terms of chromatc and achromatc nformaton [10]. The HSI model manpulates color mages wth the followng transformaton from the RGB model [9]: I R V 1 G = V B , (6) 306

3 S ( V V ) 1 = +, (7) 1 V H = tan ( )( f V 0). (8) V 1 1 Note that hue and saturaton taen together are called chromatcty and the brghtness of a chromatc lght embodes the achromatc noton of ntensty [11]. It has been observed that shadowed regons n HSI space hold the followng propertes [14] [15]: 1) Lower ntensty: because the electro-magnetc radance from the Sun s obstructed. ) Hgher saturaton wth short blue-volet wavelength: due to the atmospherc Raylegh scatterng effect. 3) Increased hue values: because the change of ntensty of an area when shadowed and no-shadowed s postve proportonal to the wavelength. Once the mage s converted from RGB color space to HSI color space, the aforementoned propertes can be used to detect shadows. III. METHODOLOGY A. Clusterng n HSI Color Space In a sense, shadow detecton can be treated as a problem of mage segmentaton, whch s to separate an mage nto two regons. However, mage segmentaton can be vewed as a clusterng process [6] [1] [16]. The goal of clusterng s to group pxels together that exhbts some type of smlarty such as color, texture, or brghtness to form shadowed regon and no-shadowed regon. The clusterng algorthm s based upon pxel smlarty, and the locaton of boundares between regons comes very naturally to the human observer [6]. We now that shadows hold large hue values; however, n colored remote sensng mages, there are objects not shadowed wth large hue values, such as blue buldngs, rvers, grasslands, and so on, whch should be dstngushed out from shadows. For blush objects, whch always have hgh ntensty values whle shadows have low ones. Therefore, shadows could be descrbed as regons wth large hue values, low ntensty values. However, there stll exst objects not shadowed n colored remote sensng mages wth low ntensty values, for example, the presence of water and hgh reflectve regons, etc., we should remove them from shadows by usng other characterstcs of shadows, such as ncreased hue values and hgher saturaton. As a result, usng a sngle band of data usually does not gve us enough nformaton to dstngush between shadows and other dar objects. Therefore, we employ a set of color nvarant ndces n order to dscrmnate between shadow regons and other dar areas n remote sensng mages. Followng the analyss from above, we use the AP clusterng algorthm to detect shadows by fusng the features of ncreased hue, hgh saturaton, and lower lumnance of the shadow regon n the HSI color space. When usng AP, we should set smlarty matrx frst. In the hue space, we redefne the smlarty s(, ) for ponts H and H as expresson (9): H H H H π π H H H H > π sh (, H ) =. (9) In the saturaton and ntensty space, smlarty s(, ) for ponts x and x s defned as expresson (10): s (, ) = x x. (10) AP clusterng method consders all data ponts as potental exemplars smultaneously at frst. As we nown, raw pxel matrx for a gven mage usually s a large-scale matrx. If we apply AP algorthm drectly on t, t wll consume a large amount of system resources and spend a lot of tme when calculate the smlarty matrx. Therefore, before clusterng, we can dvde the mage matrx nto several blocs. We can dvde matrx by row, column or blocs accordng to the requrements. Thus, the number of the sample ponts may be reduced and the effcency of the algorthm wll be mproved a lot. B. Fuson Frstly, we calculate the hstogram of the H component. By applyng AP clusterng, the centers of two classes H c1, H c and the membershp functons of the two classes are obtaned [15]. Each pxel s grades of membershp for each class can be gven as expresson (11): μ ( H( xy, )) ( Hxy (, )) Hc1 μ Hc, (11) H(x, y) s the H component of the pxel at (x, y). These two values usually add up to 1. Secondly, we deal wth the S and I components usng the same method as the H component respectvely. Each pxel s grades of membershp for each class can be expressed as expresson (1) and (13): μ ( Sxy (, )) ( Sxy (, )) Sc1 μ Sc, (1) μ ( I( xy, )) ( Ixy (, )) Ic1 μ Ic. (13) Now we obtan sx grades of membershp for each pxel n the mage. Snce the pars add up to 1. Hc1 (H(x, y)), Sc1 (S(x, y)) and Ic1 (I(x, y)) are chosen to represent the overall color characterstcs of the pxel. Fusng these three grades of membershp to form a three-dmensonal feature vector as expresson (14): C = ( μ H ( (, )), ( (, )), ( (, ))) 1 H x y μ S x y μ c Sc Ic I x y. (14) Fnally, by applyng the AP algorthm on the fused feature space, we obtan the fnal detecton result for remote sensng mages. C. Algorthm Flow of the Proposed Method The proposed method ncludes fve major steps as follow: 1) Input a remote sensng mage F(x, y). ) Space converson from RGB color space nto HSI space, and F(x, y) s converted nto G(x, y). 307

4 3) The AP clusterng algorthm s utlzed to detect shadows n the H, S, and I components, respectvely. Frstly, we dvde the orgnal mages by column, then use AP to each column and obtan representatve ponts of every column, and we can get the fnal clusterng results by usng AP to these representatve ponts of every column. AP can group mage pxels nto any number of clusters. In our experments, we choose the cluster number to be two, whch are shadow regon and no-shadowed regon. 4) Three detected result mages are fused to obtan a fnal shadow detecton mage R 0 (x, y). Concrete procedure of fuson has been dscrped n subsecton B of Secton III. 5) Enhance outlne of the shadow area by applyng operatons n mathematcal morphology [0]. The purpose of ths step s to elmnate any outler and sland pxel wthn the boundary of shadow. The operaton steps as shown n expresson (15): R( xy, ) = fc( fo( R0( xy, ), g), g) (15) where f c denotes close operaton, f o denotes open operaton, g denotes structural elements. The shape sze of the structural elements s the ey to remove solated ponts to fll the empty area. For dfferent mages we need to utlze dfferent structural elements. In order to observe the effect of detecton and compensate the nformaton of shadow regon later, we adopt a bnary mage whch has the same sze wth the orgnal mage to dentfy the detecton results. The pxel value whch s zero on the bnary mage represents that the pxel belongs to shadow regon; and the pxel value whch s 55 on the bnary mage represents that the pxel belongs to no-shadowed regon. The algorthm flow s shown n Fg. 1. IV. EXPERIMENTAL RESULTS In ths experment, we also compared K-means and hstogram threshold method, whch were mplemented n MATLAB R007a under Mcrosoft Wndows XP envronment. In the proposed method, n order to use the ndex value of the whole remote sensng mage easly, we dvde the mage by column and apply AP for each column. Thus, we get the representatve ponts of every column, than apply AP to these representatve ponts. Through teratons, we get the fnal (a) Fgure. Shadow detecton results for mage one. (a) Orgnal Image, The proposed method, K-means, and Orgnal Image Space Converson RGB to HSI Clusterng of Hue Clusterng of Saturaton Clusterng of Intensty (a) Three Components Fuson Mathematcal Morphology Shadow Detected Images Fgure 1. Flowchart of the proposed method Fgure 3. Shadow detecton results for mage two. (a) Orgnal Image, The proposed method, K-means, and 308

5 (a) Fgure 4. Shadow detecton results for mage three. (a) Orgnal Image, The proposed method, K-means, and (a) Fgure 5. Shadow detecton results for mage four. (a) Orgnal Image, The proposed method, K-means, and detecton result. Expermental mages wth heavy shadows were downloaded from Google Earth. Four comparatve experment results for shadow detecton are shown n Fg., Fg. 3, Fg. 4 and Fg. 5 respectvely. Snce mages used n the experments are real remote sensng mages downloaded from Google Earth, we cannot evaluate the algorthm performance by objectve numercal values because lac of crteron. Here the only way to evaluate the algorthm performance s by comparng the vsual effects. In these fgures, the orgnal color remote sensng mages are shown n subfgure (a). Subfgure s the result of applyng the AP clusterng n the HSI color space; Subfgure shows the result usng K-means; and subfgure s the detecton result usng hstogram threshold method [5]. Fg. s a remote sensng mage wth heavy shadowed buldng, hgh reflectve regons, and dar green lawn. We observe that the proposed method solves the problems of false dsmssals, and t mproves the accuracy of shadow detecton. Fg. 3 demonstrates a qute dfferent example wth dar road and blue water whch also exhbt hgher hue and lower lumnance as the same as shadow regons. It s easy to see that the proposed method can obtan the shadow regons more precsely. Fg. 4 and Fg. 5 are typcal examples wth the presence of water area, dar green lawn and hgh reflectve regons, whch have the smlar hue wth shadow regon. We also observe that the proposed method can exclude water area from shadows as well. The comparson results show that the proposed method can dstngush dar objects from shadows, and the shape of the segmented shadows s preserved well, t has a hgher detecton precson than that of K-means and hstogram threshold method. For K-means, the clusterng result s related to ts ntal cluster mean value, whle that of AP s not. Threshold method s manly sutable for gray mages. Meanwhle, there s no unversal method to determne threshold for all mages. Besdes, repeated experments show that the proposed method has better stablty than K-means. As for the executon speed of the proposed method, t s not optmzed n ths wor. The computatonal complexty of AP s O(N ), whle those of K-means and threshold method both are O(N). To speed up the algorthm, one of the solutons s to tae the strategy of dvde and conquer. In the experments, when we dvde the mage feature matrx nto several blocs, the number of the sample ponts may be reduced n each bloc and the effcency of the algorthm wll be mproved a lot. In partcular, we dvde the orgnal mages by column, and the sze of the mages used n our experment s In AP algorthm, we set dumpng parameter λ to be 0.5, the cluster number to be, and fxed the number of teratons s 3. Table I shows runtme of dfferent methods for mage F1, F, F3, and F4, tme unt s n Second. The tme shown n table refers to the average runtme after mplementng four tmes clusterng. Although the executon speed of AP s not optmal, t has hgher detecton precson than other clusterng algorthms, such as K-means or threshold method. The hgher detecton accuracy and better stablty proved that the proposed method can be well appled to shadow detecton for remote sensng mages when there s lac of pror nowledge. Besdes, detecton procedure does not requre manual nterventon. TABLE I. RUN TIME OF DIFFERENT ALGORITHMS AP K-means Threshold Image F Image F Image F Image F

6 V. CONCLUSIONS AND FUTURE WORKS In ths paper, we analyzed the shadow propertes n HSI color space, and presented an effcent method to detect shadows for remote sensng mages, whch usng AP clusterng algorthm and fusng the detected results n the H, S and I components. Test mages contan the areas whch are manly heavy shadowed buldngs. The proposed method to detect shadow of remote sensng mages as presented here manly concerned about the smlarty between colors. Further study s to fnd a better smlarty measure when usng AP clusterng algorthm. Two aspects of spatal nformaton and color components wll be taen nto consderaton. It s the fact that AP can automatcally choose the clusters number f we do not manually fx t. However, whether the two clusters are sutable to the applcaton of color mage segmentaton s an nterestng problem. For example, f there are varous regons n remote sensng mages wth heavy shadows, whch are smlar to shadowed regon, how to group them nto shadowed regon and no-shadowed regon automatcally wthout fxng the cluster number beforehand should be nvestgated. ACKNOWLEDGMENT The research wor descrbed n ths paper was fully supported by the grants from the Natonal Natural Scence Foundaton of Chna (Project No , ). Prof. Png Guo s the author to whom the correspondence should be addressed, hs e-mal address s pguo@eee.org. REFERENCES [1] E. Salvador, A. Cavallaro, and T. Ebrahm, Cast shadow segmentaton usng nvarant color features, Computer Vson and Image Understandng, vol. 95, no., pp , 004. [] E. Salvador, A. Cavallaro and T. Ebrahm, Shadow dentfcaton and cassfcaton usng nvarant color models, Proceedngs of the IEEE Internatonal Conference on Acoustcs, Speech and Sgnal Processng, vol. 3, pp , 001. [3] G. D. Fnlayson, S. D. Hordley, C. Lu, and M. S. Drew, On the removal of shadows from mages, IEEE Trans. on Pattern Analyss and Machne Intellgence, vol. 8, no. 1, pp , 006. [4] J. L. Wang, The research of shadow detecton algorthms based on color aeral mages, M.S. thess, Department of Remote Sensng Informaton Engneerng, Wuhan Unversty, Wuhan, Chna, 005 (n Chnese). [5] F. C. Cheng, Y. K. Chen, and K. T. Lu, An effcent gray-level clusterng algorthm for mage segmentaton, Proceedngs of the IEEE Internatonal Conference on Informatcs n Control, Automaton and Robotcs, vol., no. 6, pp. 59-6, 009. [6] A. Wees and G. Erc Hague, Color segmentaton n the HSI color space usng the K-means algorthm, Proceedngs of SPIE Symposum on Electronc Imagng, vol. 306, pp , [7] S. U. Lee, S. Y. Chung and R. H. Par, A comparatve performance study of several global thresholdng technques for segmentaton, Computer Vson, Graphcs and Image Processng, vol. 5, no., pp , [8] B. J. Frey and D. Duec, Clusterng by Passng Messages between data ponts, Scence, vol. 315, no. 5814, pp , 007. [9] T. Kanungo, D. M. Mount, and N. S. Netanyahu, An effcent K-means clusterng algorthm: analyss and mplementaton, IEEE Trans. on Pattern Analyss and Machne Intellqence, vol. 4, no. 7, pp , 00. [10] Vctor J. D. Tsa, A comparatve study on shadow compensaton of color aeral mages n nvarant color models, IEEE Trans. on Geoscence and Remote Sensng, vol. 44, no. 6, pp , 006. [11] J. Huang, W. Xe and L. Tang, Detecton of and compensaton for shadows n colored urban aeral mages, Proceedngs of the 5th Word Congr. Intellgent Control and Automaton, vol. 4, pp , 004. [1] P. Guo and Lyu MR, A study on space selecton for determnng mage segmentaton regon number, Proceedngs of Internatonal Conference on Artfcal Intelgence, vol. 1, no. 3, pp , 000. [13] J. Yao and Z. F. Zhang. Herarchcal shadow detecton for color aeral mages, Computer Vson and Image Understandng, vol. 10, no. 1, pp , 006. [14] V. Arévalo, J. González, and G. Ambroso, Shadow detecton n colour hgh-resoluton satellte mages, Internatonal Journal of Remote Sensng, vol. 9, no. 7, pp , 008. [15] J. Yang and Z. M. Zhao, A shadow removal method for hgh resoluton Remote Sensng mage, Journal of Wuhan Unversty (Informaton Scence). vol. 33, no. 1, pp.17-0, 008(n Chnese). [16] B. Rao, G. Zheng, T. M. Chen, J. Huang, and X. Shao, An effcent herarchcal method for mage shadow detecton, Proceedngs of nd Internatonal Worshop on Knowledge Dscovery Date Mnng, vol., no., pp. 6-67, 009. [17] W. Zhang, F. X. Zang, and X. K. Yang, Movng cast shadows detecton usng rato edge, IEEE Trans. on Multmeda, vol. 9, no. 6, pp , 007. [18] P. Guo and H. Q. Lu, A study on Bayesan Probablstc mage automatc segmentaton, Acta Optca Snca, vol., no. 1, pp , 00 (n Chnese). [19] K. L. Chung, Y. R. Ln, and Y. H. Huang, Effcent shadow detecton of color aeral mages based on successve thresholdng scheme, IEEE Trans. On Geoscence and Remote Sensng, vol. 47, no., pp , 009. [0] S. Nomura, K. Yamanaa, T. Shose, H. Kawaam, and O. Kata, Morphologcal preprocessng method to thresholdng degraded word mage, Pattern Recognton Letters, vol. 30, no. 8, pp , 009. [1] J. H. Guo, P. Gong, and L. Lang, Removng shadows from Google Earth satellte mages, Proceedngs of SPIE, vol. 675, no., pp. 1-1,

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

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

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

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

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

More information

BRDPHHC: A Balance RDF Data Partitioning Algorithm based on Hybrid Hierarchical Clustering

BRDPHHC: A Balance RDF Data Partitioning Algorithm based on Hybrid Hierarchical Clustering 015 IEEE 17th Internatonal Conference on Hgh Performance Computng and Communcatons (HPCC), 015 IEEE 7th Internatonal Symposum on Cyberspace Safety and Securty (CSS), and 015 IEEE 1th Internatonal Conf

More information

Hierarchical clustering for gene expression data analysis

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

More information

An Improved Image Segmentation Algorithm Based on the Otsu Method

An 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 information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

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

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

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

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

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

An Image Fusion Approach Based on Segmentation Region

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

More information

Lecture 13: High-dimensional Images

Lecture 13: High-dimensional Images Lec : Hgh-dmensonal Images Grayscale Images Lecture : Hgh-dmensonal Images Math 90 Prof. Todd Wttman The Ctadel A grayscale mage s an nteger-valued D matrx. An 8-bt mage takes on values between 0 and 55.

More information

Local Quaternary Patterns and Feature Local Quaternary Patterns

Local 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 information

A new segmentation algorithm for medical volume image based on K-means clustering

A new segmentation algorithm for medical volume image based on K-means clustering Avalable onlne www.jocpr.com Journal of Chemcal and harmaceutcal Research, 2013, 5(12):113-117 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCRC5 A new segmentaton algorthm for medcal volume mage based

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

A fast algorithm for color image segmentation

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

More information

1. Introduction. Abstract

1. Introduction. Abstract Image Retreval Usng a Herarchy of Clusters Danela Stan & Ishwar K. Seth Intellgent Informaton Engneerng Laboratory, Department of Computer Scence & Engneerng, Oaland Unversty, Rochester, Mchgan 48309-4478

More information

Object-Based Techniques for Image Retrieval

Object-Based Techniques for Image Retrieval 54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge 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 information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

A Clustering Algorithm for Key Frame Extraction Based on Density Peak

A Clustering Algorithm for Key Frame Extraction Based on Density Peak Journal of Computer and Communcatons, 2018, 6, 118-128 http://www.scrp.org/ournal/cc ISSN Onlne: 2327-5227 ISSN Prnt: 2327-5219 A Clusterng Algorthm for Key Frame Extracton Based on Densty Peak Hong Zhao

More information

A Deflected Grid-based Algorithm for Clustering Analysis

A Deflected Grid-based Algorithm for Clustering Analysis A Deflected Grd-based Algorthm for Clusterng Analyss NANCY P. LIN, CHUNG-I CHANG, HAO-EN CHUEH, HUNG-JEN CHEN, WEI-HUA HAO Department of Computer Scence and Informaton Engneerng Tamkang Unversty 5 Yng-chuan

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

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

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

More information

A Background Subtraction for a Vision-based User Interface *

A Background Subtraction for a Vision-based User Interface * A Background Subtracton for a Vson-based User Interface * Dongpyo Hong and Woontack Woo KJIST U-VR Lab. {dhon wwoo}@kjst.ac.kr Abstract In ths paper, we propose a robust and effcent background subtracton

More information

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng, Natonal Unversty of Sngapore {shva, phanquyt, tancl }@comp.nus.edu.sg

More information

A Gradient Difference based Technique for Video Text Detection

A Gradient Difference based Technique for Video Text Detection 2009 10th Internatonal Conference on Document Analyss and Recognton A Gradent Dfference based Technque for Vdeo Text Detecton Palaahnakote Shvakumara, Trung Quy Phan and Chew Lm Tan School of Computng,

More information

PROF. J. K. PATIL. Engineering, Kolhapur, India,

PROF. J. K. PATIL. Engineering, Kolhapur, India, DETECTION AND REMOVAL OF SHADOW USING OJECT ORIENTED TECHNIQUE MISS. SUJATA. KALE Department of Electroncs and Telecommuncaton Engneerng, harat Vdyapeeth s College of Engneerng, Kolhapur, Inda, sujatakale92@gmal.com

More information

Research and Application of Fingerprint Recognition Based on MATLAB

Research 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 information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

MULTISPECTRAL REMOTE SENSING IMAGE CLASSIFICATION WITH MULTIPLE FEATURES

MULTISPECTRAL REMOTE SENSING IMAGE CLASSIFICATION WITH MULTIPLE FEATURES MULISPECRAL REMOE SESIG IMAGE CLASSIFICAIO WIH MULIPLE FEAURES QIA YI, PIG GUO, Image Processng and Pattern Recognton Laboratory, Bejng ormal Unversty, Bejng 00875, Chna School of Computer Scence and echnology,

More information

A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION

A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION A NEW FUZZY C-MEANS BASED SEGMENTATION STRATEGY. APPLICATIONS TO LIP REGION IDENTIFICATION Mhaela Gordan *, Constantne Kotropoulos **, Apostolos Georgaks **, Ioanns Ptas ** * Bass of Electroncs Department,

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

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

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

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

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Course Introduction. Algorithm 8/31/2017. COSC 320 Advanced Data Structures and Algorithms. COSC 320 Advanced Data Structures and Algorithms

Course 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 information

Maximum Variance Combined with Adaptive Genetic Algorithm for Infrared Image Segmentation

Maximum 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 information

Load Balancing for Hex-Cell Interconnection Network

Load 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 information

Module Management Tool in Software Development Organizations

Module 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 information

An Optimal Algorithm for Prufer Codes *

An 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 information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An 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 information

PERFORMANCE EVALUATION FOR SCENE MATCHING ALGORITHMS BY SVM

PERFORMANCE EVALUATION FOR SCENE MATCHING ALGORITHMS BY SVM PERFORMACE EVALUAIO FOR SCEE MACHIG ALGORIHMS BY SVM Zhaohu Yang a, b, *, Yngyng Chen a, Shaomng Zhang a a he Research Center of Remote Sensng and Geomatc, ongj Unversty, Shangha 200092, Chna - yzhac@63.com

More information

An Entropy-Based Approach to Integrated Information Needs Assessment

An Entropy-Based Approach to Integrated Information Needs Assessment Dstrbuton Statement A: Approved for publc release; dstrbuton s unlmted. An Entropy-Based Approach to ntegrated nformaton Needs Assessment June 8, 2004 Wllam J. Farrell Lockheed Martn Advanced Technology

More information

Efficient Content Representation in MPEG Video Databases

Efficient Content Representation in MPEG Video Databases Effcent Content Representaton n MPEG Vdeo Databases Yanns S. Avrths, Nkolaos D. Doulams, Anastasos D. Doulams and Stefanos D. Kollas Department of Electrcal and Computer Engneerng Natonal Techncal Unversty

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

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

More information

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS P.G. Demdov Yaroslavl State Unversty Anatoly Ntn, Vladmr Khryashchev, Olga Stepanova, Igor Kostern EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS Yaroslavl, 2015 Eye

More information

Feature-Area Optimization: A Novel SAR Image Registration Method

Feature-Area Optimization: A Novel SAR Image Registration Method Feature-Area Optmzaton: A Novel SAR Image Regstraton Method Fuqang Lu, Fukun B, Lang Chen, Hao Sh and We Lu Abstract Ths letter proposes a synthetc aperture radar (SAR) mage regstraton method named Feature-Area

More information

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION

A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION 1 FENG YONG, DANG XIAO-WAN, 3 XU HONG-YAN School of Informaton, Laonng Unversty, Shenyang Laonng E-mal: 1 fyxuhy@163.com, dangxaowan@163.com, 3 xuhongyan_lndx@163.com

More information

An efficient method to build panoramic image mosaics

An efficient method to build panoramic image mosaics An effcent method to buld panoramc mage mosacs Pattern Recognton Letters vol. 4 003 Dae-Hyun Km Yong-In Yoon Jong-Soo Cho School of Electrcal Engneerng and Computer Scence Kyungpook Natonal Unv. Abstract

More information

The Research of Support Vector Machine in Agricultural Data Classification

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

More information

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

College of Information & Computer, Anhui Agricultural University, Hefei, Anhui, , China

College of Information & Computer, Anhui Agricultural University, Hefei, Anhui, , China 4th Internatonal Conference on Mechatroncs Materals Chemstry and Computer Engneerng (ICMMCCE 15) Improved retnex mage enhancement algorthm based on blateral flterng Ya nan Yang 1 a Zhaohu Jang 1 b * Chunhe

More information

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes

R s s f. m y s. SPH3UW Unit 7.3 Spherical Concave Mirrors Page 1 of 12. Notes SPH3UW Unt 7.3 Sphercal Concave Mrrors Page 1 of 1 Notes Physcs Tool box Concave Mrror If the reflectng surface takes place on the nner surface of the sphercal shape so that the centre of the mrror bulges

More information

A Probabilistic Approach to Detect Urban Regions from Remotely Sensed Images Based on Combination of Local Features

A Probabilistic Approach to Detect Urban Regions from Remotely Sensed Images Based on Combination of Local Features A Probablstc Approach to Detect Urban Regons from Remotely Sensed Images Based on Combnaton of Local Features Berl Sırmaçek German Aerospace Center (DLR) Remote Sensng Technology Insttute Weßlng, 82234,

More information

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

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

More information

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

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

More information

Detection of an Object by using Principal Component Analysis

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

More information

Classifying Acoustic Transient Signals Using Artificial Intelligence

Classifying Acoustic Transient Signals Using Artificial Intelligence Classfyng Acoustc Transent Sgnals Usng Artfcal Intellgence Steve Sutton, Unversty of North Carolna At Wlmngton (suttons@charter.net) Greg Huff, Unversty of North Carolna At Wlmngton (jgh7476@uncwl.edu)

More information

Unsupervised Learning

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

More information

Pictures at an Exhibition

Pictures at an Exhibition 1 Pctures at an Exhbton Stephane Kwan and Karen Zhu Department of Electrcal Engneerng Stanford Unversty, Stanford, CA 9405 Emal: {skwan1, kyzhu}@stanford.edu Abstract An mage processng algorthm s desgned

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc.

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. [Type text] [Type text] [Type text] ISSN : 0974-74 Volume 0 Issue BoTechnology 04 An Indan Journal FULL PAPER BTAIJ 0() 04 [684-689] Revew on Chna s sports ndustry fnancng market based on market -orented

More information

Image Alignment CSC 767

Image Alignment CSC 767 Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

CS 534: Computer Vision Model Fitting

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

More information

Related-Mode Attacks on CTR Encryption Mode

Related-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 information

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

The 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 information

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour

6.854 Advanced Algorithms Petar Maymounkov Problem Set 11 (November 23, 2005) With: Benjamin Rossman, Oren Weimann, and Pouya Kheradpour 6.854 Advanced Algorthms Petar Maymounkov Problem Set 11 (November 23, 2005) Wth: Benjamn Rossman, Oren Wemann, and Pouya Kheradpour Problem 1. We reduce vertex cover to MAX-SAT wth weghts, such that the

More information

Hybrid Non-Blind Color Image Watermarking

Hybrid Non-Blind Color Image Watermarking Hybrd Non-Blnd Color Image Watermarkng Ms C.N.Sujatha 1, Dr. P. Satyanarayana 2 1 Assocate Professor, Dept. of ECE, SNIST, Yamnampet, Ghatkesar Hyderabad-501301, Telangana 2 Professor, Dept. of ECE, AITS,

More information

Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm

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 information

A high precision collaborative vision measurement of gear chamfering profile

A high precision collaborative vision measurement of gear chamfering profile Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) A hgh precson collaboratve vson measurement of gear chamferng profle Conglng Zhou, a, Zengpu Xu, b, Chunmng

More information

Remote Sensing Image Retrieval Algorithm based on MapReduce and Characteristic Information

Remote Sensing Image Retrieval Algorithm based on MapReduce and Characteristic Information Remote Sensng Image Retreval Algorthm based on MapReduce and Characterstc Informaton Zhang Meng 1, 1 Computer School, Wuhan Unversty Hube, Wuhan430097 Informaton Center, Wuhan Unversty Hube, Wuhan430097

More information

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

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

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

Programming in Fortran 90 : 2017/2018

Programming in Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Programmng n Fortran 90 : 2017/2018 Exercse 1 : Evaluaton of functon dependng on nput Wrte a program who evaluate the functon f (x,y) for any two user specfed values

More information

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures A Novel Adaptve Descrptor Algorthm for Ternary Pattern Textures Fahuan Hu 1,2, Guopng Lu 1 *, Zengwen Dong 1 1.School of Mechancal & Electrcal Engneerng, Nanchang Unversty, Nanchang, 330031, Chna; 2. School

More information

Robust Shot Boundary Detection from Video Using Dynamic Texture

Robust Shot Boundary Detection from Video Using Dynamic Texture Sensors & Transducers 204 by IFSA Publshng, S. L. http://www.sensorsportal.com Robust Shot Boundary Detecton from Vdeo Usng Dynamc Teture, 3 Peng Tale, 2 Zhang Wenjun School of Communcaton & Informaton

More information

A Robust Method for Estimating the Fundamental Matrix

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

More information

Background Removal in Image indexing and Retrieval

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

More information

Machine Learning: Algorithms and Applications

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

More information

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

Video Object Tracking Based On Extended Active Shape Models With Color Information CGIV'2002: he Frst Frst European Conference Colour on Colour n Graphcs, Imagng, and Vson Vdeo Object rackng Based On Extended Actve Shape Models Wth Color Informaton A. Koschan, S.K. Kang, J.K. Pak, B.

More information

DETECTION OF MOVING OBJECT BY FUSION OF COLOR AND DEPTH INFORMATION

DETECTION OF MOVING OBJECT BY FUSION OF COLOR AND DEPTH INFORMATION INTERNATIONAL JOURNAL ON SMART SENSING AN INTELLIGENT SYSTEMS VOL. 9, NO., MARCH 206 ETECTION OF MOVING OBJECT BY FUSION OF COLOR AN EPTH INFORMATION T. T. Zhang,G. P. Zhao and L. J. Lu School of Automaton

More information

Unsupervised Learning and Clustering

Unsupervised Learning and Clustering Unsupervsed Learnng and Clusterng Supervsed vs. Unsupervsed Learnng Up to now we consdered supervsed learnng scenaro, where we are gven 1. samples 1,, n 2. class labels for all samples 1,, n Ths s also

More information

Machine Learning. Topic 6: Clustering

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

More information

A Cluster Number Adaptive Fuzzy c-means Algorithm for Image Segmentation

A Cluster Number Adaptive Fuzzy c-means Algorithm for Image Segmentation , pp.9-204 http://dx.do.org/0.4257/jsp.203.6.5.7 A Cluster Number Adaptve Fuzzy c-means Algorthm for Image Segmentaton Shaopng Xu, Lngyan Hu, Xaohu Yang and Xaopng Lu,2 School of Informaton Engneerng,

More information

Face Recognition using 3D Directional Corner Points

Face Recognition using 3D Directional Corner Points 2014 22nd Internatonal Conference on Pattern Recognton Face Recognton usng 3D Drectonal Corner Ponts Xun Yu, Yongsheng Gao School of Engneerng Grffth Unversty Nathan, QLD, Australa xun.yu@grffthun.edu.au,

More information

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

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

More information

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A 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 information

Clustering Algorithm of Similarity Segmentation based on Point Sorting

Clustering Algorithm of Similarity Segmentation based on Point Sorting Internatonal onference on Logstcs Engneerng, Management and omputer Scence (LEMS 2015) lusterng Algorthm of Smlarty Segmentaton based on Pont Sortng Hanbng L, Yan Wang*, Lan Huang, Mngda L, Yng Sun, Hanyuan

More information