Spatial-Aware Collaborative Representation for Hyperspectral Remote Sensing Image Classification

Size: px
Start display at page:

Download "Spatial-Aware Collaborative Representation for Hyperspectral Remote Sensing Image Classification"

Transcription

1 Spatial-Aware Collaborative Representation for Hyperspetral Remote Sensing Image ifiation Junjun Jiang, Member, IEEE, Chen Chen, Member, IEEE, Yi Yu, Xinwei Jiang, and Jiayi Ma Member, IEEE Representation-residual based lassifiers have attrated muh attention in reent years in hyperspetral image (HSI) lassifiation. How to obtain the optimal representation oeffiients for the lassifiation task is the key problem of these methods. In this letter, spatial-aware ollaborative representation (SaCR) is proposed for HSI lassifiation. In order to make full use of the spatial-spetral information, we propose a losed-form solution, in whih the spatial and spetral features are both utilized to indue the distane-weighted regularization terms. Different from traditional ollaborative representation based HSI lassifiation algorithms, whih model the spatial feature in a preproessing or post-proessing stage, we diretly inorporate the spatial information by adding a spatial regularization term to the representation objetive funtion. Experimental results on three HSI datasets verify that our proposed approah outperforms the state-of-the-art lassifiers. Index Terms Hyperspetral image lassifiation, ollaborative representation (CR), spatial regularization, spetral spatial information. I. INTRODUCTION Hyperspetral remote sensing (HRS) allows the simultaneous aquisition of full portrayal of eah material s spetral refletane and inreases the possibility of disriminating ground objets more aurately [], [2], [3], [4]. Reently, representation-based lassifiation methods are of great interest in hyperspetral image (HSI) lassifiation due to their exellent performanes [5], [6], [7], [8], [9], [0], [], [2]. The ommon idea is to represent a test sample by the training samples and assign the lass that provides the lowest reonstrution residual. We term this strategy as representationresidual based lassifiation in this letter. For example, sparse representation (SR) lassifiation was first proposed in [3], and has been suessfully applied in various appliations [4], [5], [6], [7], [8], [9], [20]. Chen et al. [5] introdued SR to HSI lassifiation based on the assumption that HSI pixels that belong to the same lass approximately lie in a low-dimensional subspae. In [2], Zhang et al. argued that it is the ollaborative representation The researh was supported by the National Natural Siene Foundation of China (65043, , ), and by the Fundamental Researh Funds for the Central Universities, China University of Geosienes (Wuhan) under Grant CUGL6042. J. Jiang and X. Jiang are with the Shool of Computer Siene, China University of Geosienes, Wuhan 4074, China (junjun0595@63.om, ysjxw@hotmail.om). C. Chen is with the University of Central Florida, Orlando, USA (henhen87073@gmail.om). Y. Yu is with the Digital Content and Media Sienes Researh Division, National Institute of Informatis, Tokyo 0-84, Japan (yiyu@nii.a.jp). J. Ma is with the Eletroni Information Shool, Wuhan University, Wuhan 4072, China ( jiayima@whu.edu.n). (CR) rather than the omputationally expensive SR onstraint that atually determines the lassifiation performane. Inspired by this observation, Li et al. [8] developed a joint CR (JCR) lassifiation method with spatial and spetral features from surrounding pixels, and they further extended JCR to the kernel version and the weighted version in [9] and [0], respetively. In addition to the raw pixel feature, Gabor feature [] or multi-feature [7] has been proposed to improve the performane of JCR. Instead of exploring the neighbor pixels, Li et al. [6] onstruted a joint matrix using the nonloal pixels of a test pixel, and proposed a nonloal joint ollaborative representation lassifiation method. The essential of utilizing the spatial information of these ollaborative representation methods is to onstrut a joint vetor [8], [], [9], or matrix [5], [6] before performing sample representation. By inorporating the spatial information of HSI, one an expet to obtain a better representation than using spetral information only [22], [23], [24], [25]. To simultaneously inorporate the spetral and spatial information to the representation framework, in this letter we propose a spatial-aware ollaborative representation (SaCR). In SaCR, we design two expliit regularization terms: one is for modeling the spetral similarity onstraint and the other is for the spatial similarity onstraint. Based on these two regularization terms, we develop a losed-form solution to effetively fuse the spetral and spatial information. Experimental results on three HSI datasets demonstrate the proposed method outperforms the state-of-the-art spetral-spatial based CR lassifiation tehniques. II. RELATED WORK Suppose there are N training HSI pixels x i IR d (d dimensional feature spae), i =, 2,, N, hosen from C different lasses. The training set an be also denoted by a matrix X = [x, x 2,, x N ] IR d N. Let w i {, 2,, C} be the label of the i-th pixel and n l be the number of available training samples from the l-th lass, thus C l= n l = N. Given a test pixel y IR d, CR based methods utilize all the training samples to represent it: J(α) = y Xα λω(α). () Here, the regularization parameter λ balanes the trade-off between the reonstrution residual and the prior of α. After solving the optimal representation oeffiients α = arg min J(α), the lass label of the test pixel y is determined α aording to the minimum residual, lass(y) = arg min y X l α l 2 2, (2) l=,2,...,c

2 2 where X l and α l are the subsets of X and α, respetively. Different priors Ω(α) have been proposed to regularize the least squares problem. In SR lassifiation, a test sample is sparsely represented by an l 0 norm regularization. In [2], Zhang et al. argued that it is the CR nature (i.e., using all the training samples) rather than the sparsity that improves lassifiation auray. To make the representation more flexible, nearest regularized CR method [26] introdues a loality onstraint to regularize the solution of () by giving different freedom to training samples aording to their Eulidean distanes from y: J(α) = y Xα λ Γα 2 2 (3) where Γ is a biasing Tikhonov matrix defined by with Γ ii = y x i 2, i =, 2,..., N. If the distane between a training sample x i and the test sample y is large, x i will be given a small ontribution (i.e., the orresponding representation oeffiient α i is small), and vie versa. In HSI, neighboring pixels usually onsist of similar materials with high probability. Thus, their spetral harateristis are highly orrelated. The spatial orrelation aross neighboring pixels an be indiretly inorporated through a joint model. For example, Xiong et al. [8] proposed to simultaneously represent a test pixel and its neighbors by spatially averaging the test and training pixels: J(α) = ỹ X l α l λ Γ l α l 2 2 (4) where ỹ denotes the average spetral features for the test pixel y entered in a window with m neighbors, and X l is the averaged value for eah element in matrix x l. In [0], they further developed an improved version to utilize more appropriate weights for surrounding pixels. A. SaCR III. THE PROPOSED METHOD In this setion, we introdue our proposed CR model by expliitly modeling the spetral and spatial feature. Speifially, we develop a losed-form solution based on spatial-aware ollaborative representation (SaCR), in whih the spetral and spatial information is used together to indue regularization terms. Different from traditional CR models, whih use neighbor pixels to onstrut a joint vetor by averaging [8], [0] or matrix by ombing [7], [6], [5] (they all an be seen as a predefining stage), we diretly inorporate the spatial feature into the objetive funtion (6) by adding a spatial feature indued regularization term: J(α) = y Xα λ Γα γ diag(s)α 2 2, (5) where s = [s, s 2,, s N ], s i is assoiated with eah training samples whih enourages representation oeffiients that are spatially oherent with respet to the training data, and diag(s) returns a square diagonal matrix with the elements of vetor s on the main diagonal. Here, the regularization parameters λ and γ ontrol the ontributions of the loality prior (seond term) and spatial prior (third term), respetively. For more details about the effets of these two parameters, please refer to the Setion IV-B. Analogous to the role of the Tikhonov matrix Γ, diag(s) ats similar effets. If one training sample x i is neighbor to the test pixel, i.e., s i is small (the penalty on representation oeffiient α i is small), then α i is likely to be a relatively large value and x i ontributes signifiantly to the reonstrution of the test pixel, and vie versa. Denoting the pixel oordinate of sample x i and y as (p i, q i ) and (p y, q y ) respetively, the spatial oherent between x i and y an be measured as s i = [dist((p i, q i ), (p y, q y ))], (6) where dist( ) denotes Eulidean distane and is a smooth parameter adjusting the distane deay speed for the spatial prior. Usually we further normalize s to be between (0, ] by dividing max(s) from s. The introdution of the smooth parameter gives the model more flexibility. It allows to emphasize more on neighbor pixels with better disriminability. When the value of is very large, our proposed model will heavily penalize pixels that are far away from the test pixel y by assigning weights lose to 0 to them. From Eq. (5), we learn that the proposed SaCR model onsists of three parts: the first part is the data reonstrution term to ensure the reonstruted sample (xα ) being similar to y, the seond part is the spetral indued penalty term that enfores similar training pixels to the test pixel to have large representation oeffiients and vie versa, and the last part is the spatial indued penalty term that enfores the neighbor training pixels of the test pixel (i.e., training pixels that are spatially lose to the test pixel) to have large representation oeffiients and vie versa. λ and γ are two regularization parameters to balane the ontributions of the three terms. The optimization of (5) is similar to (4), whih an be derived analytially as: B. α = (x T X+λΓ + γdiag(s))x T y. (7) To take into onsideration of the ontextual information of enter pixels, we further extend our SaCR method to a joint version (named for short): J(α) = ỹ Xα λ Γα γ diag( s)α 2 2, (8) where ỹ is defined as in JCR [], X is the average value for eah element in matrix x, i.e., x j = (/m) m i= x i, j =, 2,, N, Γ and s are defined by X and ỹ. When ompared with SaCR and, we learn that an be summarized as the following two steps: (i) average filtering and (ii) performing SaCR on the filtered image. Note that the average filtering usually an smooth the random noise in HSI image, so an be expeted to have better results than SaCR. C. Relation to Existing Methods It is worth mentioning that our proposed method aims to simultaneously inorporate the spetral and spatial information to the HSI lassifiation task, where spatial and

3 3 TABLE I THE PARAMETER SETTINGS OF OUR PROPOSED SACR AND JSACR METHODS FOR THE THREE HSI DATASETS. Parameters Pine University of Pavia SaCR SaCR SaCR e-06 e+04 e+06 e spetral features are both utilized to indue the distaneweighted regularization terms, and this makes different from the existing spetral and spatial features based HSI lassifiation methods. Speifially, CR [2] an be seen as a speial ase of the proposed SaCR method when we set Γ to the identity matrix and γ to zero (see Eq. () and Eq. (5)); When we set γ to zero, the proposed SaCR method will redue to WCR [0] (see Eq. (3) and Eq. (5)); Our proposed method will redue to JCR [8] when we set γ to zero, please refer to the objetive funtions (4) and (8). When ompared with the traditional CR based methods, e.g., WCR and JCR, our proposed SaCR and both have the spetral penalization fator and spatial penalization fator, thus the proposed algorithm will take muh time to alulate the similarity. IV. EXPERIMENTS AND ANALYSIS In this setion, we investigate the effetiveness of the proposed SaCR lassifiation algorithm and its joint version () using three HSI datasets. The lassifiers inluding support vetor mahine (SVM) [27], [28], SVM with omposite kernel that ombines the spetral and spatial information via a weighted kernel summation (denoted by SVM-CK) [28], SR lassifiation [3], JSR lassifiation [5], CR lassifiation [2], weighted ollaborative representation (WCR) lassifiation [0] and JCR lassifiation [8] are used for omparison in this letter. The lassifiation performane is measured by overall auray () on the three HSI datasets. A. Experimental Datasets The first HSI dataset is the Pine, aquired by National Aeronautis and Spae Administrations (NASA) Airborne Visible/Infrared Imaging Spetrometer (AVIRIS) sensor, whih generates pixels and 220 bands in the m region, of whih 20 noisy bands are removed before lassifiation. It ontains 6 ground-truth lasses, and the lass-speifi numbers of test and training samples are shown in Table I. The seond dataset is the University of Pavia, whih is olleted by the Refletive Optis System Imaging Spetrometer (ROSIS) sensor and ontains a spatial overage of pixels. It generates 5 spetral bands, of whih 2 noisy bands are removed. There are nine ground-truth lasses of the dataset. The third dataset is the, olleted by the 224-band Airborne Visible Infrared Imaging Spetrometer (AVIRIS) sensor over Valley, California, whih generates pixels is the number of orretly predited pixel/total of pixel to predit SaCR SaCR Fig.. ifiation auray with varying regularization parameters λ and γ of SaCR and on Pine (top row), University of Pavia (middle row), and ( bottom row), respetively Fig. 2. ifiation auray with varying regularization parameter of SaCR and on Pine (left olumn), University of Pavia (middle olumn), and (right olumn), respetively. and 204 bands over m with spatial resolution of 3.7 m, of whih 20 water absorption bands are removed before lassifiation. For the above three datasets, the test and training data is randomly seleted from the available ground truth maps. The lass-speifi numbers of test and training samples are shown in Table II, Table III, and Table IV. To avoid any bias, all the experiments are repeated 0 times, and we report the average lassifiation auray. B. Parameter Settings To demonstrate the effetiveness of our proposed approah, we study the effet of the three regularization parameters λ, γ and. In general, the fivefold ross-validation strategy based on training samples is onsidered for parameter tuning. Fig. plots the urves of the values on the three HSI datasets as a funtion of the regularization λ and γ. It is worth noting that eah left subfigure shows the values aording to γ when λ is set to the optimal value, and eah right subfigure presents the values aording to λ when

4 4 TABLE II CLASSIFICATION ACCURACY (%) FOR THE INDIAN PINE DATASET. Alfalfa Corn-notill Corn-mintill Corn Grass-pasture Grass-trees Grass-pasture-mowed Hay-windrowed Oats Soybean-notill Soybean-mintill Soybean-lean Wheat Woods Buildings-Grass-Trees-Drives Stone-Steel-Towers # samples ifiation Algorithms Train Test SVM SVM-CK SR JSR CR WCR JCR SaCR Overall Auray (%) γ is set to the optimal value. From Fig., we an see that: i) by setting proper values of λ or γ, is better than SaCR, whih implies the effetiveness of utilizing ontextual information of enter pixels; ii) when γ is set to the optimal value, the inrease of λ brings small gains. However, when λ is set to the optimal value, the inrease of γ brings relatively large gains. This indiates that the spatial indued penalty term plays a relatively more important role than the spetral indued penalty term does in the sample representation; iii) when γ = 0, the proposed SaCR method redues to the WCRC method, the performane of SaCR is restrited. This an be explained by that the spatial indued onstraint is essential for HSI lassifiation task. Table I tabulates the parameter settings for the three HSI datasets when our proposed SaCR and ahieve the best performanes. In addition to the analysis of λ and γ, we also evaluate the performane of our proposed method with different smooth parameter (as shown in Fig. 2). The smooth parameter has an important influene on the lassifiation auray. It annot apture the spatial struture information if the smooth parameter is set too large or too small. To obtain the best performanes, the Pines and University of Pavia datasets employ larger values of than the dataset. This is mainly beause that the former two datasets have a lot of disonneted lasses, while the latter exhibits more spatial homogeneity. From the objetive funtion (5), we learn that large values of γ and mean that spatial onstraint aount for main ontribution, and SaCR method tends to selet a small number of neighbor pixels. This point ould be learned from Table I. SaCR uses relatively small values of parameters γ and for the Pine dataset and the dataset (γ is e+4 or 0, is 4 or 2), and large values for the dataset (γ is e+6 and is 9). C. ifiation Performane The performanes of SaCR and are shown in Table II, Table III and Table IV. From these results, we an onlude that the introdution of the ontextual information greatly improves the performane of the original pixel based method, e.g., as for the Pine dataset, SVM-CK has 23.48% gain over SVM, JSR has 9.8% gain over SR, JCR has 35.23% gain over CR, and has.03% gain over SaCR. Similar results an be also observed from the other two datasets. The differene between JCR and our proposed is that additionally imposes a spatial feature indued regularization term. From the reported results, we an see that this spatial regularization is important in the representation residual based HSI lassifiation method. The improvements of over JCR are 0.5%, 5.9%, and 3.63% on the Pine dataset, the University of Pavia dataset and the dataset, respetively. V. CONCLUSIONS In this letter, we proposed a novel CR HSI lassifiation method based SaCR. It has a losed-form solution to inorporate the spatial and spetral information simultaneously. Meanwhile, we further developed a joint SaCR () modeling that takes into onsideration of the ontextual information of the enter pixel. Extensive experimental results on three benhmark HSI datasets verified the effetiveness of inorporating the spatial feature indued regularization term. Comparison results demonstrated that our proposed algorithm an obtain better performane than the state-of-the-art spetralspatial HSI lassifiation methods. REFERENCES [] J. Lin, Q. Wang, and Y. Yuan, In defense of iterated onditional mode for hyperspetral image lassifiation, in ICME, July 204, pp. 6. [2] Q. Wang, J. Lin, and Y. Yuan, Salient band seletion for hyperspetral image lassifiation via manifold ranking, IEEE Trans. Neural Netw. Learn. Syst., vol. 27, no. 6, pp , June 206. [3] C. Chen, W. Li, H. Su, and K. Liu, Spetral-spatial lassifiation of hyperspetral image based on kernel extreme learning mahine, Remote Sensing, vol. 6, no. 6, pp , 204. [4] B. Du, M. Zhang, L. Zhang, R. Hu, and D. Tao, Pltd: Path-based lowrank tensor deomposition for hyperspetral images, IEEE Transations on Multimedia, vol. 9, no., pp , Jan 207. [5] Y. Chen, N. M. Nasrabadi, and T. D. Tran, Hyperspetral image lassifiation using ditionary-based sparse representation, IEEE Trans. Geosi. Remote Sensing, vol. 49, no. 0, pp , 20.

5 5 TABLE III CLASSIFICATION ACCURACY (%) FOR THE UNIVERSITY OF PAVIA DATASET. Asphalt Bare soil Bitumen Briks Gravel Meadows Metal sheets Shadows Trees # samples ifiation Algorithms Train Test SVM SVM-CK SR JSR CR WCR JCR SaCR Overall Auray (%) TABLE IV CLASSIFICATION ACCURACY (%) FOR THE SALINAS DATASET. Brooli_green_weeds_ Brooli_green_weeds_2 Fallow Fallow_rough_plow Fallow_smooth Stubble Celery Grapes_untrained Soil_vinyard_develop Corn_senesed_green_weeds Lettue_romaine_4wk Lettue_romaine_5wk Lettue_romaine_6wk Lettue_romaine_7wk Vinyard_untrained Vinyard_vertial_trellis # samples ifiation Algorithms Train Test SVM SVM-CK SR JSR CR WCR JCR SaCR Overall Auray (%) [6] J. Li, H. Zhang, Y. Huang, and L. Zhang, Hyperspetral image lassifiation by nonloal joint ollaborative representation with a loally adaptive ditionary, IEEE Trans. Geosi. Remote Sensing, vol. 52, no. 6, pp , 204. [7] J. Li, H. Zhang, L. Zhang, X. Huang, and L. Zhang, Joint ollaborative representation with multitask learning for hyperspetral image lassifiation, IEEE Trans. Geosi. Remote Sensing, vol. 52, no. 9, pp , 204. [8] W. Li and Q. Du, Joint within-lass ollaborative representation for hyperspetral image lassifiation, IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens., vol. 7, no. 6, pp , 204. [9] W. Li, Q. Du, and M. Xiong, Kernel ollaborative representation with tikhonov regularization for hyperspetral image lassifiation, IEEE Geosi. Remote Sens. Lett., vol. 2, no., pp , 205. [0] M. Xiong, Q. Ran, W. Li, J. Zou, and Q. Du, Hyperspetral image lassifiation using weighted joint ollaborative representation, IEEE Geosi. Remote Sens. Lett., vol. 2, no. 6, pp , 205. [] S. Jia, L. Shen, and Q. Li, Gabor feature-based ollaborative representation for hyperspetral imagery lassifiation, IEEE Trans. Geosi. Remote Sensing, vol. 53, no. 2, pp. 8 29, 205. [2] J. Jiang, C. Chen, X. Song, and Z. Cai, Hyperspetral image lassifiation using set-to-set distane, in ICASSP, Marh 206, pp [3] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, Robust fae reognition via sparse representation, IEEE Trans. Pattern Anal. Mah. Intell., vol. 3, no. 2, pp , [4] J. Ma, J. Zhao, J. Tian, X. Bai, and Z. Tu, Regularized vetor field learning with sparse approximation for mismath removal, Pattern Reognition, vol. 46, no. 2, pp , 203. [5] L. Wang, K. Lu, P. Liu, R. Ranjan, and L. Chen, Ik-svd: ditionary learning for spatial big data via inremental atom update, Computing in Siene & Engineering, vol. 6, no. 4, pp. 4 52, 204. [6] J. Jiang, X. Ma, Z. Cai, and R. Hu, Sparse support regression for image super-resolution, IEEE Photonis Journal, vol. 7, no. 5, pp., Ot 205. [7] J. Ma, C. Chen, C. Li, and J. Huang, Infrared and visible image fusion via gradient transfer and total variation minimization, Inf. Fusion, vol. 3, pp , 206. [8] J. Jiang, J. Ma, C. Chen, X. Jiang, and Z. Wang, Noise robust fae image super-resolution through smooth sparse representation, IEEE Trans. on Cybern., vol. PP, no. 99, pp. 2, 206. [9] W. Song, P. Liu, and L. Wang, Sparse representation-based orrelation analysis of non-stationary spatiotemporal big data, International Journal of Digital Earth, vol. 9, no. 9, pp , 206. [20] J. Wei, Y. Huang, K. Lu, and L. Wang, Nonloal low-rank-based ompressed sensing for remote sensing image reonstrution, IEEE Geosiene and Remote Sensing Letters, vol. 3, no. 0, pp , 206. [2] L. Zhang, M. Yang, and X. Feng, Sparse representation or ollaborative representation: Whih helps fae reognition? in ICCV, 20, pp [22] Y. Yuan, J. Lin, and Q. Wang, Hyperspetral image lassifiation via multitask joint sparse representation and stepwise MRF optimization, IEEE Trans. Cybernetis, vol. PP, no. 99, pp. 2, 205. [23] J. Liu, Z. Wu, J. Li, A. Plaza, and Y. Yuan, Probabilisti-kernel ollaborative representation for spatial-spetral hyperspetral image lassifiation, IEEE Trans. Geosi. Remote Sensing, vol. 54, no. 4, pp , April 206. [24] H. Pu, Z. Chen, B. Wang, and G. M. Jiang, A novel spatial-spetral similarity measure for dimensionality redution and lassifiation of hyperspetral imagery, IEEE Trans. Geosi. Remote Sensing, vol. 52, no., pp , Nov 204. [25] C. Li, Y. Ma, X. Mei, C. Liu, and J. Ma, Hyperspetral image lassifiation with robust sparse representation, IEEE Geosi. Remote Sens. Lett., vol. 3, no. 5, pp , May 206. [26] W. Li, E. W. Tramel, S. Prasad, and J. E. Fowler, Nearest regularized subspae for hyperspetral lassifiation, IEEE Trans. Geosi. Remote Sensing, vol. 52, no., pp , 204. [27] R. Arhibald and G. Fann, Feature seletion and lassifiation of hyperspetral images with support vetor mahines, IEEE Geosi. Remote Sens. Lett., vol. 4, no. 4, pp , [28] G. Camps-Valls, L. Gomez-Chova, J. Muñoz-Marí, J. Vila-Franés, and J. Calpe-Maravilla, Composite kernels for hyperspetral image lassifiation, IEEE Geosi. Remote Sens. Lett., vol. 3, no., pp , 2006.

KERNEL-based methods, such as support vector machines

KERNEL-based methods, such as support vector machines 48 IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 12, NO. 1, JANUARY 2015 Kernel Collaborative Representation With Tikhonov Regularization for Hyperspectral Image Classification Wei Li, Member, IEEE,QianDu,Senior

More information

A Novel Validity Index for Determination of the Optimal Number of Clusters

A Novel Validity Index for Determination of the Optimal Number of Clusters IEICE TRANS. INF. & SYST., VOL.E84 D, NO.2 FEBRUARY 2001 281 LETTER A Novel Validity Index for Determination of the Optimal Number of Clusters Do-Jong KIM, Yong-Woon PARK, and Dong-Jo PARK, Nonmembers

More information

NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION. Ken Sauer and Charles A. Bouman

NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION. Ken Sauer and Charles A. Bouman NONLINEAR BACK PROJECTION FOR TOMOGRAPHIC IMAGE RECONSTRUCTION Ken Sauer and Charles A. Bouman Department of Eletrial Engineering, University of Notre Dame Notre Dame, IN 46556, (219) 631-6999 Shool of

More information

Hyperspectral Images Classification Using Energy Profiles of Spatial and Spectral Features

Hyperspectral Images Classification Using Energy Profiles of Spatial and Spectral Features journal homepage: www.elsevier.om Hyperspetral Images Classifiation Using Energy Profiles of Spatial and Spetral Features Hamid Reza Shahdoosti a a Hamedan University of ehnology, Department of Eletrial

More information

KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION

KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION KERNEL SPARSE REPRESENTATION WITH LOCAL PATTERNS FOR FACE RECOGNITION Cuiui Kang 1, Shengai Liao, Shiming Xiang 1, Chunhong Pan 1 1 National Laboratory of Pattern Reognition, Institute of Automation, Chinese

More information

The Minimum Redundancy Maximum Relevance Approach to Building Sparse Support Vector Machines

The Minimum Redundancy Maximum Relevance Approach to Building Sparse Support Vector Machines The Minimum Redundany Maximum Relevane Approah to Building Sparse Support Vetor Mahines Xiaoxing Yang, Ke Tang, and Xin Yao, Nature Inspired Computation and Appliations Laboratory (NICAL), Shool of Computer

More information

the data. Structured Principal Component Analysis (SPCA)

the data. Structured Principal Component Analysis (SPCA) Strutured Prinipal Component Analysis Kristin M. Branson and Sameer Agarwal Department of Computer Siene and Engineering University of California, San Diego La Jolla, CA 9193-114 Abstrat Many tasks involving

More information

THE detailed spectral information of hyperspectral

THE detailed spectral information of hyperspectral 1358 IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 14, NO. 8, AUGUST 2017 Locality Sensitive Discriminant Analysis for Group Sparse Representation-Based Hyperspectral Imagery Classification Haoyang

More information

PoS(CENet2017)005. The Classification of Hyperspectral Images Based on Band-Grouping and Convolutional Neural Network. Speaker.

PoS(CENet2017)005. The Classification of Hyperspectral Images Based on Band-Grouping and Convolutional Neural Network. Speaker. The Classification of Hyperspectral Images Based on Band-Grouping and Convolutional Neural Network 1 Xi an Hi-Tech Institute Xi an 710025, China E-mail: dr-f@21cnl.c Hongyang Gu Xi an Hi-Tech Institute

More information

Exploiting Enriched Contextual Information for Mobile App Classification

Exploiting Enriched Contextual Information for Mobile App Classification Exploiting Enrihed Contextual Information for Mobile App Classifiation Hengshu Zhu 1 Huanhuan Cao 2 Enhong Chen 1 Hui Xiong 3 Jilei Tian 2 1 University of Siene and Tehnology of China 2 Nokia Researh Center

More information

Hyperspectral Image Classification Using Gradient Local Auto-Correlations

Hyperspectral Image Classification Using Gradient Local Auto-Correlations Hyperspectral Image Classification Using Gradient Local Auto-Correlations Chen Chen 1, Junjun Jiang 2, Baochang Zhang 3, Wankou Yang 4, Jianzhong Guo 5 1. epartment of Electrical Engineering, University

More information

Learning Convention Propagation in BeerAdvocate Reviews from a etwork Perspective. Abstract

Learning Convention Propagation in BeerAdvocate Reviews from a etwork Perspective. Abstract CS 9 Projet Final Report: Learning Convention Propagation in BeerAdvoate Reviews from a etwork Perspetive Abstrat We look at the way onventions propagate between reviews on the BeerAdvoate dataset, and

More information

A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR

A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR Malaysian Journal of Computer Siene, Vol 10 No 1, June 1997, pp 36-41 A DYNAMIC ACCESS CONTROL WITH BINARY KEY-PAIR Md Rafiqul Islam, Harihodin Selamat and Mohd Noor Md Sap Faulty of Computer Siene and

More information

An Optimized Approach on Applying Genetic Algorithm to Adaptive Cluster Validity Index

An Optimized Approach on Applying Genetic Algorithm to Adaptive Cluster Validity Index IJCSES International Journal of Computer Sienes and Engineering Systems, ol., No.4, Otober 2007 CSES International 2007 ISSN 0973-4406 253 An Optimized Approah on Applying Geneti Algorithm to Adaptive

More information

Abstract. Key Words: Image Filters, Fuzzy Filters, Order Statistics Filters, Rank Ordered Mean Filters, Channel Noise. 1.

Abstract. Key Words: Image Filters, Fuzzy Filters, Order Statistics Filters, Rank Ordered Mean Filters, Channel Noise. 1. Fuzzy Weighted Rank Ordered Mean (FWROM) Filters for Mixed Noise Suppression from Images S. Meher, G. Panda, B. Majhi 3, M.R. Meher 4,,4 Department of Eletronis and I.E., National Institute of Tehnology,

More information

Capturing Large Intra-class Variations of Biometric Data by Template Co-updating

Capturing Large Intra-class Variations of Biometric Data by Template Co-updating Capturing Large Intra-lass Variations of Biometri Data by Template Co-updating Ajita Rattani University of Cagliari Piazza d'armi, Cagliari, Italy ajita.rattani@diee.unia.it Gian Lua Marialis University

More information

Cluster-Based Cumulative Ensembles

Cluster-Based Cumulative Ensembles Cluster-Based Cumulative Ensembles Hanan G. Ayad and Mohamed S. Kamel Pattern Analysis and Mahine Intelligene Lab, Eletrial and Computer Engineering, University of Waterloo, Waterloo, Ontario N2L 3G1,

More information

New Fuzzy Object Segmentation Algorithm for Video Sequences *

New Fuzzy Object Segmentation Algorithm for Video Sequences * JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 24, 521-537 (2008) New Fuzzy Obet Segmentation Algorithm for Video Sequenes * KUO-LIANG CHUNG, SHIH-WEI YU, HSUEH-JU YEH, YONG-HUAI HUANG AND TA-JEN YAO Department

More information

Extracting Partition Statistics from Semistructured Data

Extracting Partition Statistics from Semistructured Data Extrating Partition Statistis from Semistrutured Data John N. Wilson Rihard Gourlay Robert Japp Mathias Neumüller Department of Computer and Information Sienes University of Strathlyde, Glasgow, UK {jnw,rsg,rpj,mathias}@is.strath.a.uk

More information

HYPERSPECTRAL image (HSI) acquired by spaceborne

HYPERSPECTRAL image (HSI) acquired by spaceborne 1 SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery Junjun Jiang, Member, IEEE, Jiayi Ma, Member, IEEE, Chen Chen, Member, IEEE, Zhongyuan Wang, Member,

More information

Dr.Hazeem Al-Khafaji Dept. of Computer Science, Thi-Qar University, College of Science, Iraq

Dr.Hazeem Al-Khafaji Dept. of Computer Science, Thi-Qar University, College of Science, Iraq Volume 4 Issue 6 June 014 ISSN: 77 18X International Journal of Advaned Researh in Computer Siene and Software Engineering Researh Paper Available online at: www.ijarsse.om Medial Image Compression using

More information

Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair

Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair Hyperspectral and Multispectral Image Fusion Using Local Spatial-Spectral Dictionary Pair Yifan Zhang, Tuo Zhao, and Mingyi He School of Electronics and Information International Center for Information

More information

FUZZY WATERSHED FOR IMAGE SEGMENTATION

FUZZY WATERSHED FOR IMAGE SEGMENTATION FUZZY WATERSHED FOR IMAGE SEGMENTATION Ramón Moreno, Manuel Graña Computational Intelligene Group, Universidad del País Vaso, Spain http://www.ehu.es/winto; {ramon.moreno,manuel.grana}@ehu.es Abstrat The

More information

A scheme for racquet sports video analysis with the combination of audio-visual information

A scheme for racquet sports video analysis with the combination of audio-visual information A sheme for raquet sports video analysis with the ombination of audio-visual information Liyuan Xing a*, Qixiang Ye b, Weigang Zhang, Qingming Huang a and Hua Yu a a Graduate Shool of the Chinese Aadamy

More information

HYPERSPECTRAL imagery has been increasingly used

HYPERSPECTRAL imagery has been increasingly used IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, VOL. 14, NO. 5, MAY 2017 597 Transferred Deep Learning for Anomaly Detection in Hyperspectral Imagery Wei Li, Senior Member, IEEE, Guodong Wu, and Qian Du, Senior

More information

Does Normalization Methods Play a Role for Hyperspectral Image Classification?

Does Normalization Methods Play a Role for Hyperspectral Image Classification? Does Normalization Methods Play a Role for Hyperspectral Image Classification? Faxian Cao 1, Zhijing Yang 1*, Jinchang Ren 2, Mengying Jiang 1, Wing-Kuen Ling 1 1 School of Information Engineering, Guangdong

More information

Fast Rigid Motion Segmentation via Incrementally-Complex Local Models

Fast Rigid Motion Segmentation via Incrementally-Complex Local Models Fast Rigid Motion Segmentation via Inrementally-Complex Loal Models Fernando Flores-Mangas Allan D. Jepson Department of Computer Siene, University of Toronto {mangas,jepson}@s.toronto.edu Abstrat The

More information

A Novel Bit Level Time Series Representation with Implication of Similarity Search and Clustering

A Novel Bit Level Time Series Representation with Implication of Similarity Search and Clustering A Novel Bit Level Time Series Representation with Impliation of Similarity Searh and lustering hotirat Ratanamahatana, Eamonn Keogh, Anthony J. Bagnall 2, and Stefano Lonardi Dept. of omputer Siene & Engineering,

More information

A {k, n}-secret Sharing Scheme for Color Images

A {k, n}-secret Sharing Scheme for Color Images A {k, n}-seret Sharing Sheme for Color Images Rastislav Luka, Konstantinos N. Plataniotis, and Anastasios N. Venetsanopoulos The Edward S. Rogers Sr. Dept. of Eletrial and Computer Engineering, University

More information

Plot-to-track correlation in A-SMGCS using the target images from a Surface Movement Radar

Plot-to-track correlation in A-SMGCS using the target images from a Surface Movement Radar Plot-to-trak orrelation in A-SMGCS using the target images from a Surfae Movement Radar G. Golino Radar & ehnology Division AMS, Italy ggolino@amsjv.it Abstrat he main topi of this paper is the formulation

More information

TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM

TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM TUMOR DETECTION IN MRI BRAIN IMAGE SEGMENTATION USING PHASE CONGRUENCY MODIFIED FUZZY C MEAN ALGORITHM M. Murugeswari 1, M.Gayathri 2 1 Assoiate Professor, 2 PG Sholar 1,2 K.L.N College of Information

More information

A Coarse-to-Fine Classification Scheme for Facial Expression Recognition

A Coarse-to-Fine Classification Scheme for Facial Expression Recognition A Coarse-to-Fine Classifiation Sheme for Faial Expression Reognition Xiaoyi Feng 1,, Abdenour Hadid 1 and Matti Pietikäinen 1 1 Mahine Vision Group Infoteh Oulu and Dept. of Eletrial and Information Engineering

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information

One Against One or One Against All : Which One is Better for Handwriting Recognition with SVMs?

One Against One or One Against All : Which One is Better for Handwriting Recognition with SVMs? One Against One or One Against All : Whih One is Better for Handwriting Reognition with SVMs? Jonathan Milgram, Mohamed Cheriet, Robert Sabourin To ite this version: Jonathan Milgram, Mohamed Cheriet,

More information

Performance of Histogram-Based Skin Colour Segmentation for Arms Detection in Human Motion Analysis Application

Performance of Histogram-Based Skin Colour Segmentation for Arms Detection in Human Motion Analysis Application World Aademy of Siene, Engineering and Tehnology 8 009 Performane of Histogram-Based Skin Colour Segmentation for Arms Detetion in Human Motion Analysis Appliation Rosalyn R. Porle, Ali Chekima, Farrah

More information

Learning Discriminative and Shareable Features. Scene Classificsion

Learning Discriminative and Shareable Features. Scene Classificsion Learning Disriminative and Shareable Features for Sene Classifiation Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang, and Xudong Jiang Nanyang Tehnologial University, Singapore, Advaned Digital

More information

Improved Vehicle Classification in Long Traffic Video by Cooperating Tracker and Classifier Modules

Improved Vehicle Classification in Long Traffic Video by Cooperating Tracker and Classifier Modules Improved Vehile Classifiation in Long Traffi Video by Cooperating Traker and Classifier Modules Brendan Morris and Mohan Trivedi University of California, San Diego San Diego, CA 92093 {b1morris, trivedi}@usd.edu

More information

Boosted Random Forest

Boosted Random Forest Boosted Random Forest Yohei Mishina, Masamitsu suhiya and Hironobu Fujiyoshi Department of Computer Siene, Chubu University, 1200 Matsumoto-ho, Kasugai, Aihi, Japan {mishi, mtdoll}@vision.s.hubu.a.jp,

More information

Gray Codes for Reflectable Languages

Gray Codes for Reflectable Languages Gray Codes for Refletable Languages Yue Li Joe Sawada Marh 8, 2008 Abstrat We lassify a type of language alled a refletable language. We then develop a generi algorithm that an be used to list all strings

More information

Chromaticity-matched Superimposition of Foreground Objects in Different Environments

Chromaticity-matched Superimposition of Foreground Objects in Different Environments FCV216, the 22nd Korea-Japan Joint Workshop on Frontiers of Computer Vision Chromatiity-mathed Superimposition of Foreground Objets in Different Environments Yohei Ogura Graduate Shool of Siene and Tehnology

More information

Multivariate Texture-based Segmentation of Remotely Sensed. Imagery for Extraction of Objects and Their Uncertainty

Multivariate Texture-based Segmentation of Remotely Sensed. Imagery for Extraction of Objects and Their Uncertainty Multivariate Texture-based Segmentation of Remotely Sensed Imagery for Extration of Objets and Their Unertainty Arko Luieer*, Alfred Stein* & Peter Fisher** * International Institute for Geo-Information

More information

SINCE the successful launch of high-resolution sensors and

SINCE the successful launch of high-resolution sensors and 1458 IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 45, NO. 5, MAY 2007 Classifiation of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features Yindi

More information

Time delay estimation of reverberant meeting speech: on the use of multichannel linear prediction

Time delay estimation of reverberant meeting speech: on the use of multichannel linear prediction University of Wollongong Researh Online Faulty of Informatis - apers (Arhive) Faulty of Engineering and Information Sienes 7 Time delay estimation of reverberant meeting speeh: on the use of multihannel

More information

Video Data and Sonar Data: Real World Data Fusion Example

Video Data and Sonar Data: Real World Data Fusion Example 14th International Conferene on Information Fusion Chiago, Illinois, USA, July 5-8, 2011 Video Data and Sonar Data: Real World Data Fusion Example David W. Krout Applied Physis Lab dkrout@apl.washington.edu

More information

Comparing Images Under Variable Illumination

Comparing Images Under Variable Illumination ( This paper appeared in CVPR 8. IEEE ) Comparing Images Under Variable Illumination David W. Jaobs Peter N. Belhumeur Ronen Basri NEC Researh Institute Center for Computational Vision and Control The

More information

A New RBFNDDA-KNN Network and Its Application to Medical Pattern Classification

A New RBFNDDA-KNN Network and Its Application to Medical Pattern Classification A New RBFNDDA-KNN Network and Its Appliation to Medial Pattern Classifiation Shing Chiang Tan 1*, Chee Peng Lim 2, Robert F. Harrison 3, R. Lee Kennedy 4 1 Faulty of Information Siene and Tehnology, Multimedia

More information

Polyhedron Volume-Ratio-based Classification for Image Recognition

Polyhedron Volume-Ratio-based Classification for Image Recognition Polyhedron Volume-Ratio-based Classifiation for Image Reognition Qingxiang Feng, Jeng-Shyang Pan, Senior Member, IEEE, Jar-Ferr Yang, Fellow, IEEE and Yang-ing Chou Abstrat In this paper, a novel method,

More information

GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION

GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION Nasehe Jamshidpour a, Saeid Homayouni b, Abdolreza Safari a a Dept. of Geomatics Engineering, College of Engineering,

More information

4178 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, VOL. 9, NO. 9, SEPTEMBER 2016

4178 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, VOL. 9, NO. 9, SEPTEMBER 2016 4178 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, VOL. 9, NO. 9, SEPTEMBER 016 Hyperspectral Image Classification by Fusing Collaborative and Sparse Representations

More information

3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT?

3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT? 3-D IMAGE MODELS AND COMPRESSION - SYNTHETIC HYBRID OR NATURAL FIT? Bernd Girod, Peter Eisert, Marus Magnor, Ekehard Steinbah, Thomas Wiegand Te {girod eommuniations Laboratory, University of Erlangen-Nuremberg

More information

Hyperspectral Image Classification by Using Pixel Spatial Correlation

Hyperspectral Image Classification by Using Pixel Spatial Correlation Hyperspectral Image Classification by Using Pixel Spatial Correlation Yue Gao and Tat-Seng Chua School of Computing, National University of Singapore, Singapore {gaoyue,chuats}@comp.nus.edu.sg Abstract.

More information

RANGE DOPPLER ALGORITHM FOR BISTATIC SAR PROCESSING BASED ON THE IMPROVED LOFFELD S BISTATIC FORMULA

RANGE DOPPLER ALGORITHM FOR BISTATIC SAR PROCESSING BASED ON THE IMPROVED LOFFELD S BISTATIC FORMULA Progress In Eletromagnetis Researh Letters, Vol. 27, 161 169, 2011 RANGE DOPPLER ALGORITHM FOR ISTATIC SAR PROCESSING ASED ON THE IMPROVED LOFFELD S ISTATIC FORMULA X. Wang 1, * and D. Y. Zhu 2 1 Nanjing

More information

Discrete sequential models and CRFs. 1 Case Study: Supervised Part-of-Speech Tagging

Discrete sequential models and CRFs. 1 Case Study: Supervised Part-of-Speech Tagging 0-708: Probabilisti Graphial Models 0-708, Spring 204 Disrete sequential models and CRFs Leturer: Eri P. Xing Sribes: Pankesh Bamotra, Xuanhong Li Case Study: Supervised Part-of-Speeh Tagging The supervised

More information

arxiv: v1 [cs.db] 13 Sep 2017

arxiv: v1 [cs.db] 13 Sep 2017 An effiient lustering algorithm from the measure of loal Gaussian distribution Yuan-Yen Tai (Dated: May 27, 2018) In this paper, I will introdue a fast and novel lustering algorithm based on Gaussian distribution

More information

Evolutionary Feature Synthesis for Image Databases

Evolutionary Feature Synthesis for Image Databases Evolutionary Feature Synthesis for Image Databases Anlei Dong, Bir Bhanu, Yingqiang Lin Center for Researh in Intelligent Systems University of California, Riverside, California 92521, USA {adong, bhanu,

More information

An Alternative Approach to the Fuzzifier in Fuzzy Clustering to Obtain Better Clustering Results

An Alternative Approach to the Fuzzifier in Fuzzy Clustering to Obtain Better Clustering Results An Alternative Approah to the Fuzziier in Fuzzy Clustering to Obtain Better Clustering Results Frank Klawonn Department o Computer Siene University o Applied Sienes BS/WF Salzdahlumer Str. 46/48 D-38302

More information

A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks

A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks A Partial Sorting Algorithm in Multi-Hop Wireless Sensor Networks Abouberine Ould Cheikhna Department of Computer Siene University of Piardie Jules Verne 80039 Amiens Frane Ould.heikhna.abouberine @u-piardie.fr

More information

Semi-Supervised Affinity Propagation with Instance-Level Constraints

Semi-Supervised Affinity Propagation with Instance-Level Constraints Semi-Supervised Affinity Propagation with Instane-Level Constraints Inmar E. Givoni, Brendan J. Frey Probabilisti and Statistial Inferene Group University of Toronto 10 King s College Road, Toronto, Ontario,

More information

Smooth Trajectory Planning Along Bezier Curve for Mobile Robots with Velocity Constraints

Smooth Trajectory Planning Along Bezier Curve for Mobile Robots with Velocity Constraints Smooth Trajetory Planning Along Bezier Curve for Mobile Robots with Veloity Constraints Gil Jin Yang and Byoung Wook Choi Department of Eletrial and Information Engineering Seoul National University of

More information

Weak Dependence on Initialization in Mixture of Linear Regressions

Weak Dependence on Initialization in Mixture of Linear Regressions Proeedings of the International MultiConferene of Engineers and Computer Sientists 8 Vol I IMECS 8, Marh -6, 8, Hong Kong Weak Dependene on Initialization in Mixture of Linear Regressions Ryohei Nakano

More information

DUe to the rapid development and proliferation of hyperspectral. Hyperspectral Image Classification in the Presence of Noisy Labels

DUe to the rapid development and proliferation of hyperspectral. Hyperspectral Image Classification in the Presence of Noisy Labels Hyperspectral Image Classification in the Presence of Noisy Labels Junjun Jiang, Jiayi Ma, Zheng Wang, Chen Chen, and Xianming Liu arxiv:89.422v [cs.cv] 2 Sep 28 Abstract Label information plays an important

More information

Exploring Structural Consistency in Graph Regularized Joint Spectral-Spatial Sparse Coding for Hyperspectral Image Classification

Exploring Structural Consistency in Graph Regularized Joint Spectral-Spatial Sparse Coding for Hyperspectral Image Classification 1 Exploring Structural Consistency in Graph Regularized Joint Spectral-Spatial Sparse Coding for Hyperspectral Image Classification Changhong Liu, Jun Zhou, Senior Member, IEEE, Jie Liang, Yuntao Qian,

More information

Hyperspectral Image Classification via Kernel Sparse Representation

Hyperspectral Image Classification via Kernel Sparse Representation 1 Hyperspectral Image Classification via Kernel Sparse Representation Yi Chen 1, Nasser M. Nasrabadi 2, Fellow, IEEE, and Trac D. Tran 1, Senior Member, IEEE 1 Department of Electrical and Computer Engineering,

More information

STRATIFIED SAMPLING METHOD BASED TRAINING PIXELS SELECTION FOR HYPER SPECTRAL REMOTE SENSING IMAGE CLASSIFICATION

STRATIFIED SAMPLING METHOD BASED TRAINING PIXELS SELECTION FOR HYPER SPECTRAL REMOTE SENSING IMAGE CLASSIFICATION Volume 117 No. 17 2017, 121-126 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu STRATIFIED SAMPLING METHOD BASED TRAINING PIXELS SELECTION FOR HYPER

More information

Unsupervised Stereoscopic Video Object Segmentation Based on Active Contours and Retrainable Neural Networks

Unsupervised Stereoscopic Video Object Segmentation Based on Active Contours and Retrainable Neural Networks Unsupervised Stereosopi Video Objet Segmentation Based on Ative Contours and Retrainable Neural Networks KLIMIS NTALIANIS, ANASTASIOS DOULAMIS, and NIKOLAOS DOULAMIS National Tehnial University of Athens

More information

Cluster Centric Fuzzy Modeling

Cluster Centric Fuzzy Modeling 10.1109/TFUZZ.014.300134, IEEE Transations on Fuzzy Systems TFS-013-0379.R1 1 Cluster Centri Fuzzy Modeling Witold Pedryz, Fellow, IEEE, and Hesam Izakian, Student Member, IEEE Abstrat In this study, we

More information

Measurement of the stereoscopic rangefinder beam angular velocity using the digital image processing method

Measurement of the stereoscopic rangefinder beam angular velocity using the digital image processing method Measurement of the stereosopi rangefinder beam angular veloity using the digital image proessing method ROMAN VÍTEK Department of weapons and ammunition University of defense Kouniova 65, 62 Brno CZECH

More information

PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING. Yesheng Gao, Kaizhi Wang, Xingzhao Liu

PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING. Yesheng Gao, Kaizhi Wang, Xingzhao Liu 20th European Signal Proessing Conferene EUSIPCO 2012) Buharest, Romania, August 27-31, 2012 PARAMETRIC SAR IMAGE FORMATION - A PROMISING APPROACH TO RESOLUTION-UNLIMITED IMAGING Yesheng Gao, Kaizhi Wang,

More information

Detection and Recognition of Non-Occluded Objects using Signature Map

Detection and Recognition of Non-Occluded Objects using Signature Map 6th WSEAS International Conferene on CIRCUITS, SYSTEMS, ELECTRONICS,CONTROL & SIGNAL PROCESSING, Cairo, Egypt, De 9-31, 007 65 Detetion and Reognition of Non-Oluded Objets using Signature Map Sangbum Park,

More information

Using Augmented Measurements to Improve the Convergence of ICP

Using Augmented Measurements to Improve the Convergence of ICP Using Augmented Measurements to Improve the onvergene of IP Jaopo Serafin, Giorgio Grisetti Dept. of omputer, ontrol and Management Engineering, Sapienza University of Rome, Via Ariosto 25, I-0085, Rome,

More information

2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media,

2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any urrent or future media, inluding reprinting/republishing this material for advertising

More information

ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS

ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS ASSESSMENT OF TWO CHEAP CLOSE-RANGE FEATURE EXTRACTION SYSTEMS Ahmed Elaksher a, Mohammed Elghazali b, Ashraf Sayed b, and Yasser Elmanadilli b a Shool of Civil Engineering, Purdue University, West Lafayette,

More information

A Fast Kernel-based Multilevel Algorithm for Graph Clustering

A Fast Kernel-based Multilevel Algorithm for Graph Clustering A Fast Kernel-based Multilevel Algorithm for Graph Clustering Inderjit Dhillon Dept. of Computer Sienes University of Texas at Austin Austin, TX 78712 inderjit@s.utexas.edu Yuqiang Guan Dept. of Computer

More information

Incomplete Multi-Modal Visual Data Grouping

Incomplete Multi-Modal Visual Data Grouping Proeedings of the Twenty-ifth International Joint Conferene on Artifiial Intelligene (IJCAI-16) Inomplete Multi-Modal Visual Data Grouping Handong Zhao, Hongfu Liu and Yun u Department of Eletrial and

More information

Graph-Based vs Depth-Based Data Representation for Multiview Images

Graph-Based vs Depth-Based Data Representation for Multiview Images Graph-Based vs Depth-Based Data Representation for Multiview Images Thomas Maugey, Antonio Ortega, Pasal Frossard Signal Proessing Laboratory (LTS), Eole Polytehnique Fédérale de Lausanne (EPFL) Email:

More information

A Unified Subdivision Scheme for Polygonal Modeling

A Unified Subdivision Scheme for Polygonal Modeling EUROGRAPHICS 2 / A. Chalmers and T.-M. Rhyne (Guest Editors) Volume 2 (2), Number 3 A Unified Subdivision Sheme for Polygonal Modeling Jérôme Maillot Jos Stam Alias Wavefront Alias Wavefront 2 King St.

More information

The Implementation of RRTs for a Remote-Controlled Mobile Robot

The Implementation of RRTs for a Remote-Controlled Mobile Robot ICCAS5 June -5, KINEX, Gyeonggi-Do, Korea he Implementation of RRs for a Remote-Controlled Mobile Robot Chi-Won Roh*, Woo-Sub Lee **, Sung-Chul Kang *** and Kwang-Won Lee **** * Intelligent Robotis Researh

More information

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. Improvement of low illumination image enhancement algorithm based on physical mode

BioTechnology. An Indian Journal FULL PAPER. Trade Science Inc. Improvement of low illumination image enhancement algorithm based on physical mode [Type text] [Type text] [Type text] ISSN : 0974-7435 Volume 10 Issue 22 BioTehnology 2014 An Indian Journal FULL PAPER BTAIJ, 10(22), 2014 [13995-14001] Improvement of low illumination image enhanement

More information

Flow Demands Oriented Node Placement in Multi-Hop Wireless Networks

Flow Demands Oriented Node Placement in Multi-Hop Wireless Networks Flow Demands Oriented Node Plaement in Multi-Hop Wireless Networks Zimu Yuan Institute of Computing Tehnology, CAS, China {zimu.yuan}@gmail.om arxiv:153.8396v1 [s.ni] 29 Mar 215 Abstrat In multi-hop wireless

More information

Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Learning Machine

Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Learning Machine Remote Sens. 2014, 6, 5795-5814; doi:10.3390/rs6065795 Article OPEN ACCESS remote sensing ISSN 2072-4292 www.mdpi.com/journal/remotesensing Spectral-Spatial Classification of Hyperspectral Image Based

More information

Face and Facial Feature Tracking for Natural Human-Computer Interface

Face and Facial Feature Tracking for Natural Human-Computer Interface Fae and Faial Feature Traking for Natural Human-Computer Interfae Vladimir Vezhnevets Graphis & Media Laboratory, Dept. of Applied Mathematis and Computer Siene of Mosow State University Mosow, Russia

More information

Cross-layer Resource Allocation on Broadband Power Line Based on Novel QoS-priority Scheduling Function in MAC Layer

Cross-layer Resource Allocation on Broadband Power Line Based on Novel QoS-priority Scheduling Function in MAC Layer Communiations and Networ, 2013, 5, 69-73 http://dx.doi.org/10.4236/n.2013.53b2014 Published Online September 2013 (http://www.sirp.org/journal/n) Cross-layer Resoure Alloation on Broadband Power Line Based

More information

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors Eurographis Symposium on Geometry Proessing (003) L. Kobbelt, P. Shröder, H. Hoppe (Editors) Rotation Invariant Spherial Harmoni Representation of 3D Shape Desriptors Mihael Kazhdan, Thomas Funkhouser,

More information

Preliminary investigation of multi-wavelet denoising in partial discharge detection

Preliminary investigation of multi-wavelet denoising in partial discharge detection Preliminary investigation of multi-wavelet denoising in partial disharge detetion QIAN YONG Department of Eletrial Engineering Shanghai Jiaotong University 8#, Donghuan Road, Minhang distrit, Shanghai

More information

Outline: Software Design

Outline: Software Design Outline: Software Design. Goals History of software design ideas Design priniples Design methods Life belt or leg iron? (Budgen) Copyright Nany Leveson, Sept. 1999 A Little History... At first, struggling

More information

Improved Circuit-to-CNF Transformation for SAT-based ATPG

Improved Circuit-to-CNF Transformation for SAT-based ATPG Improved Ciruit-to-CNF Transformation for SAT-based ATPG Daniel Tille 1 René Krenz-Bååth 2 Juergen Shloeffel 2 Rolf Drehsler 1 1 Institute of Computer Siene, University of Bremen, 28359 Bremen, Germany

More information

Multi-Piece Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality

Multi-Piece Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality INTERNATIONAL CONFERENCE ON MANUFACTURING AUTOMATION (ICMA200) Multi-Piee Mold Design Based on Linear Mixed-Integer Program Toward Guaranteed Optimality Stephen Stoyan, Yong Chen* Epstein Department of

More information

Chemical, Biological and Radiological Hazard Assessment: A New Model of a Plume in a Complex Urban Environment

Chemical, Biological and Radiological Hazard Assessment: A New Model of a Plume in a Complex Urban Environment hemial, Biologial and Radiologial Haard Assessment: A New Model of a Plume in a omplex Urban Environment Skvortsov, A.T., P.D. Dawson, M.D. Roberts and R.M. Gailis HPP Division, Defene Siene and Tehnology

More information

Automatic Physical Design Tuning: Workload as a Sequence Sanjay Agrawal Microsoft Research One Microsoft Way Redmond, WA, USA +1-(425)

Automatic Physical Design Tuning: Workload as a Sequence Sanjay Agrawal Microsoft Research One Microsoft Way Redmond, WA, USA +1-(425) Automati Physial Design Tuning: Workload as a Sequene Sanjay Agrawal Mirosoft Researh One Mirosoft Way Redmond, WA, USA +1-(425) 75-357 sagrawal@mirosoft.om Eri Chu * Computer Sienes Department University

More information

Accepted Manuscript. Domain Class Consistency based Transfer Learning for Image Classification Across Domains. Lei Zhang, Jian Yang, David Zhang

Accepted Manuscript. Domain Class Consistency based Transfer Learning for Image Classification Across Domains. Lei Zhang, Jian Yang, David Zhang Aepted Manusript Domain lass onsisteny based ransfer Learning for Image lassifiation Aross Domains Lei Zhang Jian Yang David Zhang PII: 000-055(6)335-9 DOI: 0.06/j.ins.07.08.034 Referene: IN 3038 o appear

More information

Pipelined Multipliers for Reconfigurable Hardware

Pipelined Multipliers for Reconfigurable Hardware Pipelined Multipliers for Reonfigurable Hardware Mithell J. Myjak and José G. Delgado-Frias Shool of Eletrial Engineering and Computer Siene, Washington State University Pullman, WA 99164-2752 USA {mmyjak,

More information

HIGHER ORDER full-wave three-dimensional (3-D) large-domain techniques in

HIGHER ORDER full-wave three-dimensional (3-D) large-domain techniques in FACTA UNIVERSITATIS (NIŠ) SER.: ELEC. ENERG. vol. 21, no. 2, August 2008, 209-220 Comparison of Higher Order FEM and MoM/SIE Approahes in Analyses of Closed- and Open-Region Eletromagneti Problems Milan

More information

Segmentation of brain MR image using fuzzy local Gaussian mixture model with bias field correction

Segmentation of brain MR image using fuzzy local Gaussian mixture model with bias field correction IOSR Journal of VLSI and Signal Proessing (IOSR-JVSP) Volume 2, Issue 2 (Mar. Apr. 2013), PP 35-41 e-issn: 2319 4200, p-issn No. : 2319 4197 Segmentation of brain MR image using fuzzy loal Gaussian mixture

More information

Spectral-Spatial Response for Hyperspectral Image Classification

Spectral-Spatial Response for Hyperspectral Image Classification Article Spectral-Spatial Response for Hyperspectral Image Classification Yantao Wei 1,2, *,, Yicong Zhou 2, and Hong Li 3 1 School of Educational Information Technology, Central China Normal University,

More information

Particle Swarm Optimization for the Design of High Diffraction Efficient Holographic Grating

Particle Swarm Optimization for the Design of High Diffraction Efficient Holographic Grating Original Artile Partile Swarm Optimization for the Design of High Diffration Effiient Holographi Grating A.K. Tripathy 1, S.K. Das, M. Sundaray 3 and S.K. Tripathy* 4 1, Department of Computer Siene, Berhampur

More information

Accommodations of QoS DiffServ Over IP and MPLS Networks

Accommodations of QoS DiffServ Over IP and MPLS Networks Aommodations of QoS DiffServ Over IP and MPLS Networks Abdullah AlWehaibi, Anjali Agarwal, Mihael Kadoh and Ahmed ElHakeem Department of Eletrial and Computer Department de Genie Eletrique Engineering

More information

EASY TRANSFER LEARNING BY EXPLOITING INTRA-DOMAIN STRUCTURES

EASY TRANSFER LEARNING BY EXPLOITING INTRA-DOMAIN STRUCTURES EASY TRANSFER LEARNING BY EXPLOITING INTRA-DOMAIN STRUCTURES Jindong Wang 1, Yiqiang Chen 1,, Han Yu 2, Meiyu Huang 3, Qiang Yang 4 1 Beiing Key Lab. of Mobile Computing and Pervasive Devie, Inst. of Computing

More information

A Hybrid Neuro-Genetic Approach to Short-Term Traffic Volume Prediction

A Hybrid Neuro-Genetic Approach to Short-Term Traffic Volume Prediction A Hybrid Neuro-Geneti Approah to Short-Term Traffi Volume Predition 1. Introdution Shahriar Afandizadeh 1,*, Jalil Kianfar 2 Reeived: January 2003, Revised: July 2008, Aepted: January 2009 Abstrat: This

More information

A Load-Balanced Clustering Protocol for Hierarchical Wireless Sensor Networks

A Load-Balanced Clustering Protocol for Hierarchical Wireless Sensor Networks International Journal of Advanes in Computer Networks and Its Seurity IJCNS A Load-Balaned Clustering Protool for Hierarhial Wireless Sensor Networks Mehdi Tarhani, Yousef S. Kavian, Saman Siavoshi, Ali

More information

Optimization of Two-Stage Cylindrical Gear Reducer with Adaptive Boundary Constraints

Optimization of Two-Stage Cylindrical Gear Reducer with Adaptive Boundary Constraints 5 JOURNAL OF SOFTWARE VOL. 8 NO. 8 AUGUST Optimization of Two-Stage Cylindrial Gear Reduer with Adaptive Boundary Constraints Xueyi Li College of Mehanial and Eletroni Engineering Shandong University of

More information