Gabor-Filtering-Based Completed Local Binary Patterns for Land-Use Scene Classification

Size: px
Start display at page:

Download "Gabor-Filtering-Based Completed Local Binary Patterns for Land-Use Scene Classification"

Transcription

1 Gabor-Flterng-Based Completed Loal Bnary Patterns for Land-Use Sene Classfaton Chen Chen 1, Lbng Zhou 2,*, Janzhong Guo 1,2, We L 3, Hongjun Su 4, Fangda Guo 5 1 Department of Eletral Engneerng, Unversty of Texas at Dallas, TX, USA (E-mal: henhen870713@gmal.om) 2 Shool of Eletron and Eletral Engneerng, Wuhan Textle Unversty, Wuhan, Chna 3 College of Informaton Sene and Tehnology, Bejng Unversty of Chemal Tehnology, Bejng, Chna 4 Shool of Earth Senes and Engneerng, Hoha Unversty, Nanjng, Chna 5 Department of Eletral, Computer, and Bomedal Engneerng, Unversty of Pava, Pava, Italy Abstrat Remote sensng land-use sene lassfaton has a wde range of applatons nludng forestry, urban-growth analyss, and weather foreastng. Ths paper presents an effetve mage representaton method, Gabor-flterng-based ompleted loal bnary patterns (GCLBP), for land-use sene lassfaton. It employs the mult-orentaton Gabor flters to apture the global texture nformaton from an nput mage. Then, a loal operator alled ompleted loal bnary patterns (CLBP) s utlzed to extrat the loal texture features, suh as edges and orners, from the Gabor feature mages and the nput mage. The resultng CLBP hstogram features are onatenated to represent an nput mage. Expermental results on two datasets demonstrate that the proposed method s superor to several exstng methods for landuse sene lassfaton. Keywords-Gabor flterng; loal bnary patterns; land-use sene lassfaton; extreme learnng mahne I. INTRODUCTION Land-use sene lassfaton ams to assgn semant labels (e.g., buldng, rver, forest, mountan, et.) to aeral or satellte mages. It has a wde range of applatons nludng agrultural plannng, forestry, urban-growth analyss, and land use management. Wth the rapd development n sensor tehnology, hgh-resoluton remote sensng mages an be obtaned usng the advaned spae-borne sensors. Hgh-resoluton remote sensng mages wth rh spatal and texture nformaton have made t possble to ategorze dfferent landuse sene lasses automatally [1]. There has been a great deal of effort n employng omputer vson tehnques for lassfyng aeral or satellte mages. The Bag-of-Words (BoW) model [2] s one of the most popular approahes n mage lassfaton and mage retreval applatons. In the BoW model, loal mage features suh as olor and texture are frst quantzed nto a set of vsual words usng some lusterng methods. An mage s then represented by frequenes of the set of vsual words. Although the BoW model has demonstrated the effetveness for the remotely sensed land-use sene lassfaton [1, 3], t gnores spatal relatonshps of the loal features. To norporate spatal ontext to the BoW model, a spatal pyramd mathng (SPM) framework was proposed n [4] by parttonng an mage nto subregons and omputng a BoW hstogram for eah subregon. Hstograms from all subregons were onatenated to form the SPM representaton of an mage. In [5], a mult-resoluton representaton was norporated nto the BoW model to mprove the SPM framework by onstrutng multple resoluton mages and extratng loal features from all the resoluton mages wth dense regons. Sne the SPM method uses the absolute spatal nformaton, t may not mprove the lassfaton performane for mages exhbt rotaton and translaton varatons due to rotated amera vews. To overome ths lmtaton, a pyramd-ofspatal-relatons (PSR) model was proposed n [6] to apture both absolute and relatve spatal relatonshps of loal features. The above-mentoned methods foused on mprovng the BoW framework by norporatng spatal nformaton for land-use sene lassfaton; however, extratng effetve loal features that an apture the rh texture nformaton of the hgh-resoluton remote sensng mages was not exploted. On the other hand, some works evaluated varous mage feature desrptors and ombnatons of feature desrptors for sene lassfaton. In [7], loal strutural texture desrptors and strutural texture smlarty wth nearest neghbor lassfer were utlzed for semant lassfaton of aeral mages. In [8], Gabor desrptor and Gst desrptor were evaluated ndvdually for the task of aeral mage lassfaton. In [9], a global feature desrptor named enhaned Gabor texture desrptor (EGTD) and a loal sale-nvarant feature transform (SIFT) [10] desrptor were ombned n a herarhal approah to mprove the remote sensng mage lassfaton performane. In [11], four types of features onsst of DAISY [12], geometr blur [13], SIFT [10], and self-smlarty [14] were used wthn the framework of multfeature jont sparse odng wth spatal relaton onstrant. Although fusng a set of dfferent features may enhane the dsrmnatve power, t requres parameter tunng for eah feature and the feature dmensonalty may be nreased sgnfantly. Gabor flters [15] and loal bnary patterns (LBP) [16] have been suessfully appled for a varety of mage proessng and mahne vson applatons (e.g., [17-19]). In ths paper, we present an effent mage representaton method usng Gabor-flterng-based ompleted loal bnary patterns (GCLBP). More spefally, multorentaton Gabor flters are frst appled to a remotely sensed nput mage to obtan multple Gabor feature mages whh apture dfferent orentaton nformaton of the nput mage. Completed loal bnary patterns (CLBP) [20] operator, a omplete modelng of the LBP operator, s then employed to extrat the rotaton nvarant texture features (hstograms) from the Gabor feature mages as well as the nput mage. The overall framework of the proposed representaton approah s llustrated n Fg. 1. For lassfaton, kernel-based extreme learnng mahne (KELM) [21] s utlzed due to ts effent omputaton and good lassfaton performane. The remander of ths paper s organzed as follows. Seton II provdes relevant bakground and related work. Seton III desrbes the detals of the proposed mage representaton approah. Seton IV presents the expermental data and setup as well as omparson of the lassfaton performane between the proposed method and the exstng methods. Fnally, Seton V makes several onludng remarks. * Correspondene to Lbng Zhou (lb_zhou@163.om). Ths researh was supported by the Key Program of Hube Provnal Department of Eduaton (Grant No. D ).

2 Fg. 1. The framework of the proposed GCLBP mage representaton approah. II. RELATED WORK A. Gabor Flterng A Gabor wavelet s a flter whose mpulse response s defned by a snusodal wave multpled by a Gaussan funton. In the 2-D spatal doman, a Gabor flter, nludng a real omponent and an magnary term, an be represented as G a b a,,,, a, b exp exp j 2 2 where (1) a aos bsn (2) b asn bos. (3) Here, a and b denote the pxel postons, represents the wavelength of the snusodal fator, represents the orentaton of the Gabor wavelet (e.g., 8, 4, 2, et.). Note that we only o o need to onsder [0,180 ] sne symmetry makes other dretons redundant. s the phase offset and s the spatal aspet rato (the default value s 0.5 [17, 18]) spefyng the ellptty of the support of the Gabor funton. 0 and 2 return the real and magnary parts of the Gabor flter, respetvely. Parameter s the standard devaton of the Gaussan funton and t s determned by and spatal frequeny bandwdth bw as bw ln bw A vsualzaton of Gabor flters for four orentatons s presented n Fg. 2. (4) ( rsn(2 m), ros(2 m)). The LBP s omputed by thresholdng 1 the neghbors {} m t 0 wth the enter pxel t to generate an m -bt bnary number. The resultng LBP for t an be expressed n demal form as follows: m1 m1 2 2, (5) LBP t s t t s d m, r 0 0 where d ( t t ) s the dfferene between the enter pxel and eah neghbor, sd ( ) 1 f d 0 and sd ( ) 0 f d 0. The LBP only uses the sgn nformaton of d whle gnorng the magntude nformaton. However, the sgn and magntude are omplementary and they an be used to exatly reonstrut the dfferene d. In the CLBP sheme, the mage loal dfferenes are deomposed nto two omplementary omponents: the sgns and magntudes (absolute values of d,.e., d ). Fg. 3 shows an example of the sgn and magntude omponents of the CLBP extrated from a sample blok. Note that 0 s oded as -1 n CLBP [see Fg. 3 ()]. Two operators, namely CLBP-Sgn (CLBP_S) and CLBP-Magntude (CLBP_M), are used to ode these two omponents. CLBP_S s equvalent to the tradtonal LBP operator. The CLBP_M operator s defned as follows: m1 1, u CLBP _ M m, r p d, 2, pu, 0 0, u (6) where s a threshold that s set to the mean value of d from the whole mage. The CLBP-Center part whh odes the values of the enter pxels s not used here. Fg. 2. Two-dmensonal Gabor kernels wth four orentatons, from left to rght: 0, 4, 2, and 3 4. Typally, the Gabor texture feature mage n a spef orentaton s the magntude part of onvolvng the nput mage wth the Gabor funton G( a, b ). B. CLBP LBP [16] s a smple yet effent operator to summarze loal gray-level struture of an mage. Gven a enter pxel t, ts neghborng pxels are equally spaed on a rle of radus r ( r 0 ) wth the enter at t. If the oordnates of t are (0,0) and m 1 neghbors {} m t 0 are onsdered, the oordnates of t are Fg. 3. (a) 3 3 sample blok; (b) the loal dfferenes; () the sgn omponent of CLBP; and (d) the magntude omponent of CLBP. C. Extreme Learnng Mahne (ELM) ELM [22] s an effent learnng algorthm for sngle-hddenlayer feed-forward neural networks (SLFNs). The hdden node parameters n ELM are randomly generated leadng to a muh faster learnng rate. Let y [ y1,..., y,..., ] T C k yc be the lass to whh a sample belongs, where yk {1, 1} ( 1k C ) and C s the number of lasses. Gven n tranng samples {, } n M x y 1, where x and y C, the model of a sngle hdden layer neural network havng L hdden nodes an be expressed as

3 L j1 β jh w j x ej y, 1,..., n, (7) where h() s a nonlnear atvaton funton (e.g., Sgmod funton), C β j denotes the weght vetor onnetng the j th hdden node M to the output nodes, w j denotes the weght vetor onnetng the j th hdden node to the nput nodes, and e j s the bas of the j th hdden node. The above n equatons an be wrtten ompatly as: Hβ Y, (8) T T LC T T nc where β [ β1 ;...; β L], Y [ y1 ;...; y n ], and H s the hdden layer output matrx of the neural network expressed as h( x1) h( w1 x1 e1 ) h( w L x1 el) H h( x ) h( w x e ) h( w x e ) n 1 n 1 L n L nl. (9) CLBP_M). Eah Gabor feature mage results n one CLBP_S oded mage (equvalent to an LBP oded mage) and one CLBP_M oded mage. Fg. 4 (a1) - (e1) show the CLBP_S oded mages for the Gabor feature mages and Fg. 4 (a2) - (e2) show the CLBP_M oded mages for the Gabor feature mages. It s obvous that the detaled loal spatal texture features, suh as edges, orners, and knots, are enhaned n the CLBP_S and CLBP_M oded mages. Moreover, CLBP_S and CLBP_M oded mages ontan omplementary texture nformaton whh motvates us to use CLBP n our mage representaton method to enhane the dsrmnatve power. The CLBP operator s also appled to the nput mage. Hstogram s omputed from eah CLBP_S and CLBP_M oded mages. Fnally, all the hstograms are onatenated or staked as a omposte feature vetor before t s fed nto a KELM lassfer. The overall framework of the proposed mage representaton approah (GCLBP) s llustrated n Fg. 1. Note that we use rotaton nvarant pattern n CLBP to aheve mage rotaton nvarane. h( x ) [ h( w x e ),..., h( w x e )] s the output of the hdden 1 1 L L nodes n response to the nput x. A least-squares soluton ˆβ of the lnear system Hβ Y s found to be ˆ, β HY (10) where H s the Moore-Penrose generalzed nverse of matrx H. As a result, the output funton of the ELM lassfer an be expressed as T I T fl( x) h( x) β h( x) H HH Y, (11) where 1 s a regularzaton term. A kernel matrx h( x ) h( x ) K( x, x ) s onsdered f the feature mappng ELM j j hx ( ) s unknown. Therefore, the output funton of KELM s gven by 1 K( x, x1) 1 I fl( x) ELM Y. K(, n) x x T (12) The label of a test sample s assgned to the ndex of the output nodes wth the largest value. III. PROPOSED IMAGE REPRESENTATION APPROACH Inspred by the suess of Gabor flters and LBP n omputer vson applatons, we propose an effent mage representaton approah for land-use sene lassfaton usng Gabor-flterng-based CLBP. The Gabor flter belongs to a global operator whle LBP s a loal one. As a onsequene, Gabor features and LBP features represent texture nformaton from dfferent perspetves. An nput land-use sene mage s frst onvolved wth the Gabor flters wth dfferent orentatons to generate the Gabor-fltered mages. The magntudes of the Gabor-fltered mages are used as the Gabor texture feature mages. Fg. 4(b) - (e) are the Gabor feature mages obtaned by the Gabor flters wth four orentatons ( =0, = 4, = 2, and =3 4 ). As we an see the Gabor feature mages reflet the global sgnal power n dfferent orentatons. In order to enhane the nformaton n the Gabor feature mages, we enode the Gabor feature mages wth the CLBP operator (.e., CLBP_S and Fg. 4. Examples of Gabor feature mages and the orrespondng CLBP oded mages. (a) Input mage. (b) - (e) are the Gabor feature mages obtaned by the Gabor flters wth =0, = 4, = 2, and =3 4 (wavelength 8 and bandwdth bw 4 ). (a1) - (e1) are CLBP_S oded mages orrespondng to (a) - (e). (a2) - (e2) are CLBP_M oded mages orrespondng to (a) - (e). The pxel values of the CLBP_S (CLBP_M) oded mages are CLBP_S (CLBP_M) odes (bnary strngs) n demal form. IV. EXPERIMENT To evaluate the effay of our proposed mage representaton method for remote sensng land-use sene lassfaton, we ondut experments usng two publly avalable datasets. The lassfaton performane of the proposed method s ompared wth the state-ofthe-art performane reported n the lteratures. In our experments, the radal bass funton (RBF) kernel was employed n KELM. A. Expermental Data and Setup The frst dataset s the 21-lass land-use dataset wth ground truth labelng [3]. The dataset onssts of mages of 21 land-use lasses seleted from aeral orthomagery. Eah lass ontans 100 mages wth szes of pxels. Ths s a hallengng dataset due to a varety of spatal patterns n those 21 lasses. Sample mages of eah land-use lass are shown n Fg. 5. To faltate a far omparson, the same expermental settng reported n [3] was followed. Fve-fold ross-valdaton s performed n whh the dataset s randomly parttoned nto fve equal subsets. There are 20 mages from eah land-use lass n a subset. Four subsets are used for tranng and the remanng subset s used for testng. The lassfaton auray s the average over the fve ross-valdaton evaluatons. The seond dataset used n our experments s the 19-lass satellte sene dataset [23]. It onssts of 19 lasses of hgh-resoluton

4 satellte senes olleted from Google Earth (Google In.). There are 50 mages wth szes of pxels for eah lass. The mages are extrated from large satellte mages. An example of eah lass s shown n Fg. 6. The same expermental setup n [24] was used. We randomly selet 30 mages per lass as tranng data and the remanng mages as testng data. The experment s repeated 10 tmes wth dfferent realzatons of randomly seleted tranng and testng mages and lassfaton auray s averaged over the 10 trals. Fg. 5. Examples from the 21-lass land-use dataset: (1) agrultural, (2) arplane, (3) baseball damond, (4) beah, (5) buldngs, (6) haparral, (7) dense resdental, (8) forest, (9) freeway, (10) golf ourse, (11) harbor, (12) nterseton, (13) medum densty resdental, (14) moble home park, (15) overpass, (16) parkng lot, (17) rver, (18) runway, (19) sparse resdental, (20) storage tanks, (21) tenns ourts. [0, 6, 3, 2,2 3,5 6], and eght orentatons nlude [0, 8, 4,3 8, 2,5 8,3 4,7 8]. Fg. 9 llustrates the lassfaton performane of GCLBP wth dfferent orentatons. Thus, four orentatons nlude [0, 4, 2,3 4] were hosen for the experments. Then, we assgn approprate values for the parameter set ( mr, ) of the CLBP operator. The lassfaton results wth varous CLBP parameter sets are lsted n Tables I and II for the two datasets, respetvely. Note that the dmensonalty of the CLBP hstogram features s dependent on the number of neghbors ( m ). Therefore, larger m wll nrease the feature dmensonalty and omputatonal omplexty. In our experments, we hoose ( mr, ) (10,3) for the 21- lass land-use dataset and ( mr, ) (8,3) for the 19-lass satellte sene dataset n terms of lassfaton auray and omputatonal omplexty, makng the dmensonaltes of the GCLBP features for the 21-lass land-use dataset and the 19-lass satellte sene dataset 1080 and 360, respetvely. Furthermore, n all the experments, the parameters for KELM (RBF kernel parameters) were hosen as the ones that maxmzed the tranng auray by means of a 5-fold ross-valadaton. Fg. 6. Examples from the 19-lass satellte sene dataset: (1) arport, (2) beah, (3) brdge, (4) ommeral, (5) desert, (6) farmland, (7) football feld, (8) forest, (9) ndustral, (10) meadow, (11) mountan, (12) park, (13) parkng, (14) pond, (15) port, (16) ralway staton, (17) resdental, (18) rver, (19) vadut. B. Parameter Tunng Frst of all, we study the Gabor flter parameters for land-use sene lassfaton. Aordng to (4), the parameters of Gabor flter wth dfferent and bw are nvestgated. Four Gabor orentatons ( =0, = 4, = 2, and =3 4 ) are used. The parameters for the CLBP operator are set as: m =10 and r =3. For the 21-lass landuse dataset, we randomly selet four subsets for tranng and the remanng subset for testng. For the 19-lass satellte sene dataset, 30 mages per lass are randomly seleted for tranng and the remanng mages for testng. Fg. 7 and 8 show the lassfaton results for the two datasets, respetvely. From the results, the optmal for the 21-lass land-use dataset s 8 and the optmal bw s 4. The optmal for the 19-lass satellte sene dataset s 6 and the optmal bw s 2. Therefore, we fx these parameters n our subsequent experments. We further examne dfferent hoes of orentatons for the Gabor flter. Two orentatons nlude [0, 2], four orentatons nlude [0, 4, 2,3 4], sx orentatons nlude Fg. 7. Classfaton auray (%) versus varyng and bw for the proposed GCLBP method for the 21-lass land-use dataset. Fg. 8. Classfaton auray (%) versus varyng and bw for the proposed GCLBP method for the 19-lass satellte sene dataset.

5 the land-use sene lasses lsted n Fg. 5. The dagonal elements of the matrx denote the mean lass-spef lassfaton auray (%). TABLE III. COMPARISON OF CLASSIFICATION ACCURACY (MEAN STD) ON THE 21-CLASS LAND-USE SCENE DATASET Fg. 9. Classfaton auray (%) versus dfferent Gabor flter orentatons for the proposed GCLBP. Method Auray (%) BoW [3] 76.8 SPM [3] 75.3 BoW+Spatal Co-ourrene Kernel [3] 77.7 Color Gabor [3] 80.5 Color hstogram (HLS) [3] 81.2 Strutural texture smlarty [7] 86.0 Wavelet BoW [25] 87.4 Conentr rle-strutured multsale BoW [27] 86.6 Multple feature fuson [26] 89.5 Pyramd-of-Spatal-Relatons (PSR) [6] 89.1 CLBP 85.5 Ours (GCLBP) 90.0± 2.1 TABLE I. CLASSIFICATION ACCURACY (%) OF GCLBP WITH DIFFERENT PARAMETERS ( mr, ) OF THE CLBP OPERATOR ON THE 21-CLASS LAND-USE DATASET 21-lass land-use dataset r m m m m m TABLE II. CLASSIFICATION ACCURACY (%) OF GCLBP WITH DIFFERENT PARAMETERS ( mr, ) OF THE CLBP OPERATOR ON THE 19-CLASS SATELLETE SCENE DATASET 19-lass satellte sene dataset r m m m m m C. Comparson Wth the State of the Art To evalute the effetveness of the proposed GCLBP representaton method, a omparson of ts performane wth prevsouly reported performane n the lteratures was arred out on the 21-lass land-use dataset under the same expermental setup (.e., 80% of the mages from eah lass are used as tranng, and the remanng mages are used as testng). Sne the mages n the dataset are olor mages, we onvert the mages from the RGB olor spae to the YCbCr olor spae and use the Y omponent (lumnane) to obtan the gray sale mages. The GCLBP features are extrated from the gray sale mages. We also mplement the method whh uses the CLBP operator on the nput mage only, denoted as CLBP. The omparson results are reported n Table III, whh demonstrates that our method aheves superor lassfaton performane over the other methods. Espeally, our method aheved better performane than the popular BoW lassfaton framework, whh demonstrates the effetveness of the proposed GCLBP approah for remote sensng land-use sene lassfaton. Moreover, the proposed GCLBP has 4.5% mprovement over the CLBP method sne the mult-orentaton Gabor flters aptured the global texture nformaton n dfferent dretons. We also present the onfuson matrx of our method for the 21- lass land-use dataset n Fg. 10. For a ompat representaton, numbers along the x-axs and y-axs n ths fgure are used to ndate Fg. 10. Confuson matrx of our method for the 21-lass land-use dataset. The omparson results for the 19-lass satellte sene dataset are lsted n Table IV. Although the multple features fuson method desrbed n [24] aheved hgher lassfaton auray than our method, three dfferent sets of features nludng SIFT features, Loal Ternary Pattern Hstogram Fourer (LTP-HF) features, and olor hstogram features were used, thus leadng to nreased omputatonal omplexty. The onfuson matrx of our method for the 19-lass satellte sene dataset s shown n Fg. 11. The numbers along the x- axs and y-axs n ths fgure are used to ndate the land-use sene lasses lsted n Fg. 6. TABLE IV. COMPARISON OF CLASSIFICATION ACCURACY (MEAN STD) ON THE 19-CLASS SATELLETE SCENE DATASET Method Auray Bag of olors [26] 70.6 Tree of -shapes [26] 80.4 Bag of SIFT [26] 85.5 Multfeature onatenaton [26] 90.8 Loal Ternary Pattern Hstogram Fourer (LTP-HF) [24] 77.6 SIFT+LTP-HF+Color hstogram [24] 93.6 CLBP 86.7 Ours (GCLBP) 91.0 ± 1.5

6 Fg. 11. Confuson matrx of our method for the 19-lass satellte sene dataset. The dmensonalty of the GCLBP features an be farly hgh, e.g., t s 1080 for the 21-lass land-use dataset, f a large m s used for the CLBP operator. To gan omputatonal effeny, dmensonalty reduton tehnques suh as prnpal omponent analyss (PCA) [28] an be appled to the GCLBP features to redue the dmensonalty. V. CONCLUSION In ths paper, an effetve mage representaton method for remote sensng land-use sene lassfaton was ntrodued. Ths representaton method was derved from the Gabor flters and the ompleted loal bnary patterns (CLBP) operator. Gabor flters were employed to apture the global texture nformaton from dfferent dretons of an nput mage, whereas CLBP hstogram features were extrated from the Gabor feature mages to enhane the texture nformaton (e.g., edges and orners). The ombnaton of a global operator (Gabor flters) and a loal operator (CLBP) greatly enhaned the representaton power of the spatal hstogram. The expermental results on two datasets demonstrated that our proposed Gaborflterng-based CLBP (GCLBP) representaton method aheved superor lassfaton performane over the exstng methods for landuse sene lassfaton. REFERENCES [1] Y. Yang, and S. Newsam, Spatal pyramd o-ourrene for mage lassfaton, n ICCV, Barelona, Span, pp , November [2] G. Csurka, C. R. Dane, L. Fan, J. Wllamowsk, and C. Bray, Vsual ategorzaton wth bags of keyponts, n Proeedngs of ECCV Workshops on Statstal Learnng n Computer Vson, [3] Y. Yang, and S. Newsam, Bag-of-vsual-words and spatal extensons for land-use lassfaton, n Proeedngs ofthe 18th SIGSPATIAL Internatonal Conferene on Advanes n Geograph Informaton Systems, San Jose, CA, pp , November [4] S. Lazebnk, C. Shmd, and J. Pone, Beyond bags of features: Spatal pyramd mathng for reognzng natural sene ategores, n CVPR, New York, NY, pp , June [5] L. Zhou, Z. Zhou, and D. Hu, Sene lassfaton usng a mult-resoluton bag-offeatures model, Pattern Reognton, vol. 46, no. 1, pp , January [6] S. Chen, and Y. Tan, Pyramd of spatal relatons for sene-level land use lassfaton, IEEE Transatons on Geosene and Remote Sensng, vol. 53, no. 4, pp , Aprl [7] V. Rsojev, and Z. Bab, Aeral mage lassfaton usng strutureal texture smlarty, n Proeedngs of IEEE Internatonal Symposum on Sgnal Proessng and Informaton Tehnology, Blbao, Span, pp , Deember [8] V. Rsojev, S. Mom, and Z. Bab, Gabor desrptors for aeral mage lassfaton, n Proeedngs of 10th Internatonal Conferene on Adaptve and Natural Computng Algorthms, Ljubljana, Slovena, pp , Aprl [9] V. Rsojev, and Z. Bab, Fuson of global and loal desrptors for remote sensng mage lassfaton, IEEE Geosene and Remote Sensng Letters, vol. 10, no. 4, pp , July [10] D. G. Lowe, Dstntve mage features from sale-nvarant keyponts, Internatonal Journal of Computer Vson, vol. 60, no. 2, pp , November [11] X. Zheng, X. Sun, K. Fu, and H. Wang, Automat annotaton of satellte mages va multfeature jont sparse odng wth spatal relaton onstrant, IEEE Geosene and Remote Sensng Letters, vol. 10, no. 4, pp , July [12] E. Tola, V. Lepett, and P. Fua, A fast loal desrptor for dense mathng, n CVPR, Anhorage, AK, pp. 1-8, June [13] A. C. Berg, and J. Malk, Geometr blur for template mathng, n CVPR, Kaua, HI, vol. 1, pp. I-607-I-614, Deember [14] E. Shehtman, and M. Iran, Mathng loal self-smlartes aross mages and vdeos, n CVPR, Mnneapols, MN, pp. 1-8, June [15] I. Fogel, and D. Sag, Gabor ftlers as texture dsrmnator, Bologal Cybernets, vol. 61, no. 2, pp , June1989. [16] T. Ojala, M. Petkanen, and T. T. Maenpaa, Multresoluton gray-sale and rotaton nvarant texture lassfaton wth loal bnary patterns, IEEE Transatons on Pattern Analyss and Mahne Intellgene, vol. 24, no. 7, pp , July [17] C. Chen, W. L, H. Su, and K. Lu, Spetral-spatal lassfaton of hyperspetral mage based on kernel extreme learnng mahne, Remote Sensng, vol. 6, no. 6, pp , June [18] W. L, C. Chen, H. Su, and Q. Du, Loal bnary patterns for spatal-spetral lassfaton of hyperspetral magery, IEEE Transatons on Geosene and Remote Sensng, vol. 53, no. 7, pp , July [19] C. Chen, R. Jafar, and N. Kehtarnavaz, Aton reognton from depth sequenes usng depth moton maps-based loal bnary patterns, n WACV, Wakoloa Beah, HI, pp , January, [20] Z. Guo, L. Zhang, and D. Zhang, A ompleted modelng of loal bnary pattern operator for texture lassfaton, IEEE Transatons on Image Proessng, vol. 19, no. 6, pp , June [21] G.-B. Huang, H. Zhou, X. Dng, and R. Zhang, Extreme learnng mahne for regresson and multlass lassfaton, IEEE Transatons on Systems, Man, and Cybernets, Part B: Cybernets, vol. 42, no. 2, pp , Aprl [22] G.-B. Huang, Q.-Y. Zhu, and C.-K. Sew, Extreme learnng mahne: theory and applatons, Neuroomputng, vol. 70, no.1-3, pp , Deember [23] D. Da, and W. Yang, Satellte mage lassfaton va two-layer sparse odng wth based mage representaton, IEEE Geosene and Remote Sensng Letters, vol. 8, no. 1, pp , January [24] G. Sheng, W. Yang, T. Xu, and H. Sun, Hgh-resoluton satellte sene lassfaton usng a sparse odng based multple feature ombnaton, Internatonal Journal of Remote Sensng, vol. 33, no. 8, pp , Otober [25] L. Zhao, P. Tang, and L. Huo, A 2-D wavelet deomposton-based bag-of-vsualwords model for land-use sene lassfaton, Internatonal Journal of Remote Sensng, vol. 35, no. 6, pp , Marh [26] W. Shao, W. Yang, G.-S. Xa, and G. Lu, A herarhal sheme of multple feature fuson for hgh-resoluton satellte sene ategorzaton, n Proeedngs of the 9th Internatonal Conferene on Computer Vson Systems, St. Petersburg, Russa, pp , July [27] L. Zhao, P. Tang, and L. Huo, Land-Use sene lassfaton usng a onentr rle-strutured multsale bag-of-vsual-words model, IEEE Journal of Seleted Tops n Appled Earth Observatons and Remote Sensng, vol. 7, no. 12, pp , Deember [28] J. Ren, J. Zabalza, S. Marshall, and J. Zheng, Effetve feature extraton and data reduton n remote sensng usng hyperspetral magng, IEEE Sgnal Proessng Magazne, vol. 31, no. 4, pp , July 2014.

Color Texture Classification using Modified Local Binary Patterns based on Intensity and Color Information

Color Texture Classification using Modified Local Binary Patterns based on Intensity and Color Information Color Texture Classfaton usng Modfed Loal Bnary Patterns based on Intensty and Color Informaton Shvashankar S. Department of Computer Sene Karnatak Unversty, Dharwad-580003 Karnataka,Inda shvashankars@kud.a.n

More information

LOCAL BINARY PATTERNS AND ITS VARIANTS FOR FACE RECOGNITION

LOCAL BINARY PATTERNS AND ITS VARIANTS FOR FACE RECOGNITION IEEE-Internatonal Conferene on Reent Trends n Informaton Tehnology, ICRTIT 211 MIT, Anna Unversty, Chenna. June 3-5, 211 LOCAL BINARY PATTERNS AND ITS VARIANTS FOR FACE RECOGNITION K.Meena #1, Dr.A.Suruland

More information

Avatar Face Recognition using Wavelet Transform and Hierarchical Multi-scale LBP

Avatar Face Recognition using Wavelet Transform and Hierarchical Multi-scale LBP 2011 10th Internatonal Conferene on Mahne Learnng and Applatons Avatar Fae Reognton usng Wavelet Transform and Herarhal Mult-sale LBP Abdallah A. Mohamed, Darryl D Souza, Naouel Bal and Roman V. Yampolsky

More information

Multilabel Classification with Meta-level Features

Multilabel Classification with Meta-level Features Multlabel Classfaton wth Meta-level Features Sddharth Gopal Carnege Mellon Unversty Pttsburgh PA 523 sgopal@andrew.mu.edu Ymng Yang Carnege Mellon Unversty Pttsburgh PA 523 ymng@s.mu.edu ABSTRACT Effetve

More information

Scale Selective Extended Local Binary Pattern For Texture Classification

Scale Selective Extended Local Binary Pattern For Texture Classification Scale Selectve Extended Local Bnary Pattern For Texture Classfcaton Yutng Hu, Zhlng Long, and Ghassan AlRegb Multmeda & Sensors Lab (MSL) Georga Insttute of Technology 03/09/017 Outlne Texture Representaton

More information

TAR based shape features in unconstrained handwritten digit recognition

TAR based shape features in unconstrained handwritten digit recognition TAR based shape features n unonstraned handwrtten dgt reognton P. AHAMED AND YOUSEF AL-OHALI Department of Computer Sene Kng Saud Unversty P.O.B. 578, Ryadh 543 SAUDI ARABIA shamapervez@gmal.om, yousef@s.edu.sa

More information

Computing Cloud Cover Fraction in Satellite Images using Deep Extreme Learning Machine

Computing Cloud Cover Fraction in Satellite Images using Deep Extreme Learning Machine Computng Cloud Cover Fraton n Satellte Images usng Deep Extreme Learnng Mahne L-guo WENG, We-bn KONG, Mn XIA College of Informaton and Control, Nanjng Unversty of Informaton Sene & Tehnology, Nanjng Jangsu

More information

Steganalysis of DCT-Embedding Based Adaptive Steganography and YASS

Steganalysis of DCT-Embedding Based Adaptive Steganography and YASS Steganalyss of DCT-Embeddng Based Adaptve Steganography and YASS Qngzhong Lu Department of Computer Sene Sam Houston State Unversty Huntsvlle, TX 77341, U.S.A. lu@shsu.edu ABSTRACT Reently well-desgned

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

Matrix-Matrix Multiplication Using Systolic Array Architecture in Bluespec

Matrix-Matrix Multiplication Using Systolic Array Architecture in Bluespec Matrx-Matrx Multplaton Usng Systol Array Arhteture n Bluespe Team SegFault Chatanya Peddawad (EEB096), Aman Goel (EEB087), heera B (EEB090) Ot. 25, 205 Theoretal Bakground. Matrx-Matrx Multplaton on Hardware

More information

Performance Evaluation of TreeQ and LVQ Classifiers for Music Information Retrieval

Performance Evaluation of TreeQ and LVQ Classifiers for Music Information Retrieval Performane Evaluaton of TreeQ and LVQ Classfers for Mus Informaton Retreval Matna Charam, Ram Halloush, Sofa Tsekerdou Athens Informaton Tehnology (AIT) 0.8 km Markopoulo Ave. GR - 19002 Peana, Athens,

More information

Boosting Weighted Linear Discriminant Analysis

Boosting Weighted Linear Discriminant Analysis . Okada et al. / Internatonal Journal of Advaned Statsts and I&C for Eonoms and Lfe Senes Boostng Weghted Lnear Dsrmnant Analyss azunor Okada, Arturo Flores 2, Marus George Lnguraru 3 Computer Sene Department,

More information

AVideoStabilizationMethodbasedonInterFrameImageMatchingScore

AVideoStabilizationMethodbasedonInterFrameImageMatchingScore Global Journal of Computer Sene and Tehnology: F Graphs & vson Volume 7 Issue Verson.0 Year 207 Type: Double Blnd Peer Revewed Internatonal Researh Journal Publsher: Global Journals In. (USA) Onlne ISSN:

More information

Land-use scene classification using multi-scale completed local binary patterns

Land-use scene classification using multi-scale completed local binary patterns DOI 10.1007/s11760-015-0804-2 ORIGINAL PAPER Land-use scene classification using multi-scale completed local binary patterns Chen Chen 1 Baochang Zhang 2 Hongjun Su 3 Wei Li 4 Lu Wang 4 Received: 25 April

More information

FULLY AUTOMATIC IMAGE-BASED REGISTRATION OF UNORGANIZED TLS DATA

FULLY AUTOMATIC IMAGE-BASED REGISTRATION OF UNORGANIZED TLS DATA FULLY AUTOMATIC IMAGE-BASED REGISTRATION OF UNORGANIZED TLS DATA Martn Wenmann, Bors Jutz Insttute of Photogrammetry and Remote Sensng, Karlsruhe Insttute of Tehnology (KIT) Kaserstr. 12, 76128 Karlsruhe,

More information

Research on Neural Network Model Based on Subtraction Clustering and Its Applications

Research on Neural Network Model Based on Subtraction Clustering and Its Applications Avalable onlne at www.senedret.om Physs Proeda 5 (01 ) 164 1647 01 Internatonal Conferene on Sold State Deves and Materals Sene Researh on Neural Networ Model Based on Subtraton Clusterng and Its Applatons

More information

Adaptive Class Preserving Representation for Image Classification

Adaptive Class Preserving Representation for Image Classification Adaptve Class Preservng Representaton for Image Classfaton Jan-Xun M,, Qankun Fu,, Wesheng L, Chongqng Key Laboratory of Computatonal Intellgene, Chongqng Unversty of Posts and eleommunatons, Chongqng,

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

arxiv: v3 [cs.cv] 31 Oct 2016

arxiv: v3 [cs.cv] 31 Oct 2016 Unversal Correspondene Network Chrstopher B. Choy Stanford Unversty hrshoy@a.stanford.edu JunYoung Gwak Stanford Unversty jgwak@a.stanford.edu Slvo Savarese Stanford Unversty sslvo@stanford.edu arxv:1606.03558v3

More information

Pattern Classification: An Improvement Using Combination of VQ and PCA Based Techniques

Pattern Classification: An Improvement Using Combination of VQ and PCA Based Techniques Ameran Journal of Appled Senes (0): 445-455, 005 ISSN 546-939 005 Sene Publatons Pattern Classfaton: An Improvement Usng Combnaton of VQ and PCA Based Tehnques Alok Sharma, Kuldp K. Palwal and Godfrey

More information

Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification

Multi-scale and Discriminative Part Detectors Based Features for Multi-label Image Classification Proeedngs of the wenty-seventh Internatonal Jont Conferene on Artfal Intellgene (IJCAI-8) Mult-sale and Dsrmnatve Part Detetors Based Features for Mult-lael Image Classfaton Gong Cheng, Deheng Gao, Yang

More information

An Adaptive Filter Based on Wavelet Packet Decomposition in Motor Imagery Classification

An Adaptive Filter Based on Wavelet Packet Decomposition in Motor Imagery Classification An Adaptve Flter Based on Wavelet Paket Deomposton n Motor Imagery Classfaton J. Payat, R. Mt, T. Chusak, and N. Sugno Abstrat Bran-Computer Interfae (BCI) s a system that translates bran waves nto eletral

More information

MULTIPLE OBJECT DETECTION AND TRACKING IN SONAR MOVIES USING AN IMPROVED TEMPORAL DIFFERENCING APPROACH AND TEXTURE ANALYSIS

MULTIPLE OBJECT DETECTION AND TRACKING IN SONAR MOVIES USING AN IMPROVED TEMPORAL DIFFERENCING APPROACH AND TEXTURE ANALYSIS U.P.B. S. Bull., Seres A, Vol. 74, Iss. 2, 2012 ISSN 1223-7027 MULTIPLE OBJECT DETECTION AND TRACKING IN SONAR MOVIES USING AN IMPROVED TEMPORAL DIFFERENCING APPROACH AND TEXTURE ANALYSIS Tudor BARBU 1

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

Pixel-Based Texture Classification of Tissues in Computed Tomography

Pixel-Based Texture Classification of Tissues in Computed Tomography Pxel-Based Texture Classfaton of Tssues n Computed Tomography Ruhaneewan Susomboon, Danela Stan Rau, Jaob Furst Intellgent ultmeda Proessng Laboratory Shool of Computer Sene, Teleommunatons, and Informaton

More information

Fuzzy Modeling for Multi-Label Text Classification Supported by Classification Algorithms

Fuzzy Modeling for Multi-Label Text Classification Supported by Classification Algorithms Journal of Computer Senes Orgnal Researh Paper Fuzzy Modelng for Mult-Label Text Classfaton Supported by Classfaton Algorthms 1 Beatrz Wlges, 2 Gustavo Mateus, 2 Slva Nassar, 2 Renato Cslagh and 3 Rogéro

More information

Link Graph Analysis for Adult Images Classification

Link Graph Analysis for Adult Images Classification Lnk Graph Analyss for Adult Images Classfaton Evgeny Khartonov Insttute of Physs and Tehnology, Yandex LLC 90, 6 Lev Tolstoy st., khartonov@yandex-team.ru Anton Slesarev Insttute of Physs and Tehnology,

More information

ON THE USE OF THE SIFT TRANSFORM TO SELF-LOCATE AND POSITION EYE-IN-HAND MANIPULATORS USING VISUAL CONTROL

ON THE USE OF THE SIFT TRANSFORM TO SELF-LOCATE AND POSITION EYE-IN-HAND MANIPULATORS USING VISUAL CONTROL XVIII Congresso Braslero de Automáta / a 6-setembro-00, Bonto-MS ON THE USE OF THE SIFT TRANSFORM TO SELF-LOCATE AND POSITION EYE-IN-HAND MANIPULATORS USING VISUAL CONTROL ILANA NIGRI, RAUL Q. FEITOSA

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

Combination of Color and Local Patterns as a Feature Vector for CBIR

Combination of Color and Local Patterns as a Feature Vector for CBIR Internatonal Journal of Computer Applcatons (975 8887) Volume 99 No.1, August 214 Combnaton of Color and Local Patterns as a Feature Vector for CBIR L.Koteswara Rao Asst.Professor, Dept of ECE Faculty

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

Performance Analysis of Hybrid (supervised and unsupervised) method for multiclass data set

Performance Analysis of Hybrid (supervised and unsupervised) method for multiclass data set IOSR Journal of Computer Engneerng (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 4, Ver. III (Jul Aug. 2014), PP 93-99 www.osrjournals.org Performane Analyss of Hybrd (supervsed and

More information

Bottom-Up Fuzzy Partitioning in Fuzzy Decision Trees

Bottom-Up Fuzzy Partitioning in Fuzzy Decision Trees Bottom-Up Fuzzy arttonng n Fuzzy eson Trees Maej Fajfer ept. of Mathemats and Computer Sene Unversty of Mssour St. Lous St. Lous, Mssour 63121 maejf@me.pl Cezary Z. Janow ept. of Mathemats and Computer

More information

Multiscale Heterogeneous Modeling with Surfacelets

Multiscale Heterogeneous Modeling with Surfacelets 759 Multsale Heterogeneous Modelng wth Surfaelets Yan Wang 1 and Davd W. Rosen 2 1 Georga Insttute of Tehnology, yan.wang@me.gateh.edu 2 Georga Insttute of Tehnology, davd.rosen@me.gateh.edu ABSTRACT Computatonal

More information

Minimize Congestion for Random-Walks in Networks via Local Adaptive Congestion Control

Minimize Congestion for Random-Walks in Networks via Local Adaptive Congestion Control Journal of Communatons Vol. 11, No. 6, June 2016 Mnmze Congeston for Random-Walks n Networks va Loal Adaptve Congeston Control Yang Lu, Y Shen, and Le Dng College of Informaton Sene and Tehnology, Nanjng

More information

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face Recognition University at Buffalo CSE666 Lecture Slides Resources: Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural

More information

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

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

The Simulation of Electromagnetic Suspension System Based on the Finite Element Analysis

The Simulation of Electromagnetic Suspension System Based on the Finite Element Analysis 308 JOURNAL OF COMPUTERS, VOL. 8, NO., FEBRUARY 03 The Smulaton of Suspenson System Based on the Fnte Element Analyss Zhengfeng Mng Shool of Eletron & Mahanal Engneerng, Xdan Unversty, X an, Chna Emal:

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

Local Tri-directional Weber Rhombus Co-occurrence Pattern: A New Texture Descriptor for Brodatz Texture Image Retrieval

Local Tri-directional Weber Rhombus Co-occurrence Pattern: A New Texture Descriptor for Brodatz Texture Image Retrieval ISS: 2278 323 Internatonal Journal of Advanced Research n Computer Engneerng & Technology (IJARCET) Local Tr-drectonal Weber Rhombus Co-occurrence Pattern: A ew Texture Descrptor for Brodatz Texture Image

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

Optimal shape and location of piezoelectric materials for topology optimization of flextensional actuators

Optimal shape and location of piezoelectric materials for topology optimization of flextensional actuators Optmal shape and loaton of pezoeletr materals for topology optmzaton of flextensonal atuators ng L 1 Xueme Xn 2 Noboru Kkuh 1 Kazuhro Satou 1 1 Department of Mehanal Engneerng, Unversty of Mhgan, Ann Arbor,

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

A Fast Way to Produce Optimal Fixed-Depth Decision Trees

A Fast Way to Produce Optimal Fixed-Depth Decision Trees A Fast Way to Produe Optmal Fxed-Depth Deson Trees Alreza Farhangfar, Russell Grener and Martn Znkevh Dept of Computng Sene Unversty of Alberta Edmonton, Alberta T6G 2E8 Canada {farhang, grener, maz}@s.ualberta.a

More information

A Robust Algorithm for Text Detection in Color Images

A Robust Algorithm for Text Detection in Color Images A Robust Algorthm for Tet Deteton n Color Images Yangng LIU Satosh GOTO Takesh IKENAGA Abstrat Tet deteton n olor mages has beome an atve researh area sne reent deades. In ths paper we present a novel

More information

REGISTRATION OF TERRESTRIAL LASER SCANNER DATA USING IMAGERY INTRODUCTION

REGISTRATION OF TERRESTRIAL LASER SCANNER DATA USING IMAGERY INTRODUCTION EGISTATION OF TEESTIAL LASE SCANNE DATA USING IMAGEY Khall Al-Manasr, Ph.D student Clve S. Fraser, Professor Department of Geomats Unversty of Melbourne Vtora 3010 Australa k.al-manasr@pgrad.unmelb.edu.au.fraser@unmelb.edu.au

More information

Discriminative Dictionary Learning with Pairwise Constraints

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

More information

Connectivity in Fuzzy Soft graph and its Complement

Connectivity in Fuzzy Soft graph and its Complement IOSR Journal of Mathemats (IOSR-JM) e-issn: 2278-5728, p-issn: 2319-765X. Volume 1 Issue 5 Ver. IV (Sep. - Ot.2016), PP 95-99 www.osrjournals.org Connetvty n Fuzzy Soft graph and ts Complement Shashkala

More information

DETECTING AND ANALYZING CORROSION SPOTS ON THE HULL OF LARGE MARINE VESSELS USING COLORED 3D LIDAR POINT CLOUDS

DETECTING AND ANALYZING CORROSION SPOTS ON THE HULL OF LARGE MARINE VESSELS USING COLORED 3D LIDAR POINT CLOUDS ISPRS Annals of the Photogrammetry, Remote Sensng and Spatal Informaton Senes, Volume III-3, 2016 XXIII ISPRS Congress, 12 19 July 2016, Prague, Czeh Republ DETECTING AND ANALYZING CORROSION SPOTS ON THE

More information

Lecture 5: Multilayer Perceptrons

Lecture 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 information

A Novel Dynamic and Scalable Caching Algorithm of Proxy Server for Multimedia Objects

A Novel Dynamic and Scalable Caching Algorithm of Proxy Server for Multimedia Objects Journal of VLSI Sgnal Proessng 2007 * 2007 Sprnger Sene + Busness Meda, LLC. Manufatured n The Unted States. DOI: 10.1007/s11265-006-0024-7 A Novel Dynam and Salable Cahng Algorthm of Proxy Server for

More information

International Journal of Pharma and Bio Sciences HYBRID CLUSTERING ALGORITHM USING POSSIBILISTIC ROUGH C-MEANS ABSTRACT

International Journal of Pharma and Bio Sciences HYBRID CLUSTERING ALGORITHM USING POSSIBILISTIC ROUGH C-MEANS ABSTRACT Int J Pharm Bo S 205 Ot; 6(4): (B) 799-80 Researh Artle Botehnology Internatonal Journal of Pharma and Bo Senes ISSN 0975-6299 HYBRID CLUSTERING ALGORITHM USING POSSIBILISTIC ROUGH C-MEANS *ANURADHA J,

More information

Progressive scan conversion based on edge-dependent interpolation using fuzzy logic

Progressive scan conversion based on edge-dependent interpolation using fuzzy logic Progressve san onverson based on edge-dependent nterpolaton usng fuzzy log P. Brox brox@mse.nm.es I. Baturone lum@mse.nm.es Insttuto de Mroeletróna de Sevlla, Centro Naonal de Mroeletróna Avda. Rena Meredes

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

Action Recognition Using Completed Local Binary Patterns and Multiple-class Boosting Classifier

Action Recognition Using Completed Local Binary Patterns and Multiple-class Boosting Classifier Acton Recognton Usng ompleted Local Bnary Patterns and Multple-class Boostng lassfer Yun Yang, Baochang Zhang, Lnln Yang School of Automaton Scence and Electrcal Engneerng Behang Unversty Beng, hna {yangyun,bczhang,yangln}@buaa.edu.cn

More information

Machine Learning 9. week

Machine Learning 9. week Machne Learnng 9. week Mappng Concept Radal Bass Functons (RBF) RBF Networks 1 Mappng It s probably the best scenaro for the classfcaton of two dataset s to separate them lnearly. As you see n the below

More information

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

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

More information

A 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

Improved Accurate Extrinsic Calibration Algorithm of Camera and Two-dimensional Laser Scanner

Improved Accurate Extrinsic Calibration Algorithm of Camera and Two-dimensional Laser Scanner JOURNAL OF MULTIMEDIA, VOL. 8, NO. 6, DECEMBER 013 777 Improved Aurate Extrns Calbraton Algorthm of Camera and Two-dmensonal Laser Sanner Janle Kong, Le Yan*, Jnhao Lu, Qngqng Huang, and Xaokang Dng College

More information

GPU Accelerated Elevation Map based Registration of Aerial Images

GPU Accelerated Elevation Map based Registration of Aerial Images GPU Aelerated Elevaton Map based Regstraton of Aeral Images Joseph Frenh, Student Member, IEEE, Wllam Turr, Joseph Fernando, Member, IEEE and Er Balster Senor Member IEEE {joseph.frenh, Wllam.turr, joseph.fernando}@udr.udayton.edu,

More information

A Flexible Solution for Modeling and Tracking Generic Dynamic 3D Environments*

A Flexible Solution for Modeling and Tracking Generic Dynamic 3D Environments* A Flexble Soluton for Modelng and Trang Gener Dynam 3D Envronments* Radu Danesu, Member, IEEE, and Sergu Nedevsh, Member, IEEE Abstrat The traff envronment s a dynam and omplex 3D sene, whh needs aurate

More information

A Model-Based Approach for Automated Feature Extraction in Fundus Images

A Model-Based Approach for Automated Feature Extraction in Fundus Images A Model-Based Approah for Automated Feature Extraton n Fundus Images Huq L Shool of Computng Natonal Unversty of Sngapore dslhq@nus.edu.sg Opas Chutatape Shool of Eletral and Eletron Engneerng Nanyang

More information

3D Scene Reconstruction System from Multiple Synchronized Video Images

3D Scene Reconstruction System from Multiple Synchronized Video Images 3D Sene Reonstruton Sstem from Multple Snhronzed Vdeo Images aewoo Han 1, Juho Lee 2, Hung S. Yang 3 AIM Lab., EE/CS Dept., KAIS 1,2,3 373-1, Guseong-dong, Yuseong-gu, Daejon, Republ of Korea { bluebrd

More information

COMPLEX WAVELET TRANSFORM-BASED COLOR INDEXING FOR CONTENT-BASED IMAGE RETRIEVAL

COMPLEX WAVELET TRANSFORM-BASED COLOR INDEXING FOR CONTENT-BASED IMAGE RETRIEVAL COMPLEX WAVELET TRANSFORM-BASED COLOR INDEXING FOR CONTENT-BASED IMAGE RETRIEVAL Nader Safavan and Shohreh Kasae Department of Computer Engneerng Sharf Unversty of Technology Tehran, Iran skasae@sharf.edu

More information

Microprocessors and Microsystems

Microprocessors and Microsystems Mroproessors and Mrosystems 36 (2012) 96 109 Contents lsts avalable at SeneDret Mroproessors and Mrosystems journal homepage: www.elsever.om/loate/mpro Hardware aelerator arhteture for smultaneous short-read

More information

A MPAA-Based Iterative Clustering Algorithm Augmented by Nearest Neighbors Search for Time-Series Data Streams

A MPAA-Based Iterative Clustering Algorithm Augmented by Nearest Neighbors Search for Time-Series Data Streams A MPAA-Based Iteratve Clusterng Algorthm Augmented by Nearest Neghbors Searh for Tme-Seres Data Streams Jessa Ln 1, Mha Vlahos 1, Eamonn Keogh 1, Dmtros Gunopulos 1, Janwe Lu 2, Shouan Yu 2, and Jan Le

More information

Interval uncertain optimization of structures using Chebyshev meta-models

Interval uncertain optimization of structures using Chebyshev meta-models 0 th World Congress on Strutural and Multdsplnary Optmzaton May 9-24, 203, Orlando, Florda, USA Interval unertan optmzaton of strutures usng Chebyshev meta-models Jngla Wu, Zhen Luo, Nong Zhang (Tmes New

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

Pairwise Identity Verification via Linear Concentrative Metric Learning

Pairwise Identity Verification via Linear Concentrative Metric Learning Parwse Identty Verfaton va Lnear Conentratve Metr Learnng Lle Zheng, Stefan Duffner, Khald Idrss, Chrstophe Gara, Atlla Baskurt To te ths verson: Lle Zheng, Stefan Duffner, Khald Idrss, Chrstophe Gara,

More information

Cluster ( Vehicle Example. Cluster analysis ( Terminology. Vehicle Clusters. Why cluster?

Cluster (  Vehicle Example. Cluster analysis (  Terminology. Vehicle Clusters. Why cluster? Why luster? referene funton R R Although R and R both somewhat orrelated wth the referene funton, they are unorrelated wth eah other Cluster (www.m-w.om) A number of smlar ndvduals that our together as

More information

Clustering Data. Clustering Methods. The clustering problem: Given a set of objects, find groups of similar objects

Clustering Data. Clustering Methods. The clustering problem: Given a set of objects, find groups of similar objects Clusterng Data The lusterng problem: Gven a set of obets, fnd groups of smlar obets Cluster: a olleton of data obets Smlar to one another wthn the same luster Dssmlar to the obets n other lusters What

More information

Visual Thesaurus for Color Image Retrieval using Self-Organizing Maps

Visual Thesaurus for Color Image Retrieval using Self-Organizing Maps Vsual Thesaurus for Color Image Retreval usng Self-Organzng Maps Chrstopher C. Yang and Mlo K. Yp Department of System Engneerng and Engneerng Management The Chnese Unversty of Hong Kong, Hong Kong ABSTRACT

More information

Measurement and Calibration of High Accuracy Spherical Joints

Measurement and Calibration of High Accuracy Spherical Joints 1. Introduton easurement and Calbraton of Hgh Auray Spheral Jonts Ale Robertson, Adam Rzepnewsk, Alexander Sloum assahusetts Insttute of Tehnolog Cambrdge, A Hgh auray robot manpulators are requred for

More information

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram

Shape 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 information

A Toolbox for Easily Calibrating Omnidirectional Cameras

A Toolbox for Easily Calibrating Omnidirectional Cameras A oolbox for Easly Calbratng Omndretonal Cameras Davde Saramuzza, Agostno Martnell, Roland Segwart Autonomous Systems ab Swss Federal Insttute of ehnology Zurh EH) CH-89, Zurh, Swtzerland {davdesaramuzza,

More information

A GENETIC APPROACH FOR THE AUTOMATIC ADAPTATION OF SEGMENTATION PARAMETERS

A GENETIC APPROACH FOR THE AUTOMATIC ADAPTATION OF SEGMENTATION PARAMETERS A GENETIC APPROACH FOR THE AUTOMATIC ADAPTATION OF SEGMENTATION PARAMETERS R. Q. Fetosa a, *, G. A. O. P. Costa a, T. B. Cazes a, B. Fejo b a Dept. of Eletral Engneerng, b Dept of Informats, Cathol Unversty

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

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

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

A Real-Time Detecting Algorithm for Tracking Community Structure of Dynamic Networks

A Real-Time Detecting Algorithm for Tracking Community Structure of Dynamic Networks A Real-Tme Detetng Algorthm for Trakng Communty Struture of Dynam Networks Jaxng Shang*, Lanhen Lu*, Feng Xe, Zhen Chen, Jaa Mao, Xueln Fang, Cheng Wu* Department of Automaton, Tsnghua Unversty, Beng,,

More information

Hyperspectral Image Classification Based on Local Binary Patterns and PCANet

Hyperspectral Image Classification Based on Local Binary Patterns and PCANet Hyperspectral Image Classfcaton Based on Local Bnary Patterns and PCANet Huzhen Yang a, Feng Gao a, Junyu Dong a, Yang Yang b a Ocean Unversty of Chna, Department of Computer Scence and Technology b Ocean

More information

IMAGE FUSION TECHNIQUES

IMAGE FUSION TECHNIQUES Int. J. Chem. Sc.: 14(S3), 2016, 812-816 ISSN 0972-768X www.sadgurupublcatons.com IMAGE FUSION TECHNIQUES A Short Note P. SUBRAMANIAN *, M. SOWNDARIYA, S. SWATHI and SAINTA MONICA ECE Department, Aarupada

More information

Elsevier Editorial System(tm) for NeuroImage Manuscript Draft

Elsevier Editorial System(tm) for NeuroImage Manuscript Draft Elsever Edtoral System(tm) for NeuroImage Manusrpt Draft Manusrpt Number: Ttle: Comparson of ampltude normalzaton strateges on the auray and relablty of group ICA deompostons Artle Type: Tehnal Note Seton/Category:

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

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

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

Support Vector Machines

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

More information

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECT- ORIENTED CLASSIFICATION Lng Dng 1, Hongy L 2, *, Changmao Hu 2, We Zhang 2, Shumn Wang 1 1 Insttute of Earthquake Forecastng, Chna Earthquake

More information

Smoothing Spline ANOVA for variable screening

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

More information

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

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

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

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

Learning Ensemble of Local PDM-based Regressions. Yen Le Computational Biomedicine Lab Advisor: Prof. Ioannis A. Kakadiaris

Learning Ensemble of Local PDM-based Regressions. Yen Le Computational Biomedicine Lab Advisor: Prof. Ioannis A. Kakadiaris Learnng Ensemble of Local PDM-based Regressons Yen Le Computatonal Bomedcne Lab Advsor: Prof. Ioanns A. Kakadars 1 Problem statement Fttng a statstcal shape model (PDM) for mage segmentaton Callosum segmentaton

More information

A Symbolic Representation of Time Series, with Implications for Streaming Algorithms

A Symbolic Representation of Time Series, with Implications for Streaming Algorithms A Symbol Representaton of Tme Seres, th Implatons for Streamng Algorthms Jessa Ln Eamonn Keogh Stefano Lonard Bll Chu Unversty of Calforna - Rversde Computer Sene & Engneerng Department Rversde, CA 9252,

More information

Mixture Models and the Segmentation of Multimodal Textures. Roberto Manduchi. California Institute of Technology.

Mixture Models and the Segmentation of Multimodal Textures. Roberto Manduchi. California Institute of Technology. Mxture Models and the Segmentaton of Multmodal Textures oberto Manduh Jet ropulson Laboratory Calforna Insttute of Tehnology asadena, CA 91109 manduh@pl.nasa.gov 1 Introduton Abstrat Aproblem wth usng

More information

Clustering incomplete data using kernel-based fuzzy c-means algorithm

Clustering incomplete data using kernel-based fuzzy c-means algorithm Clusterng noplete data usng ernel-based fuzzy -eans algorth Dao-Qang Zhang *, Song-Can Chen Departent of Coputer Sene and Engneerng, Nanjng Unversty of Aeronauts and Astronauts, Nanjng, 210016, People

More information

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14 Computer Aded Draftng, Desgn and Manufacturng Volume 5, Number, June 015, Page 14 CADDM Face Recognton Algorthm Fusng Monogenc Bnary Codng and Collaboratve Representaton FU Yu-xan, PENG Lang-yu College

More information

Bit-level Arithmetic Optimization for Carry-Save Additions

Bit-level Arithmetic Optimization for Carry-Save Additions Bt-leel Arthmet Optmzaton for Carry-Sae s Ke-Yong Khoo, Zhan Yu and Alan N. Wllson, Jr. Integrated Cruts and Systems Laboratory Unersty of Calforna, Los Angeles, CA 995 khoo, zhanyu, wllson @sl.ula.edu

More information