Filters








44,755 Hits in 6.3 sec

A study on design of object sorting algorithms in the industrial application using hyperspectral imaging

Pavel Paclík, Raimund Leitner, Robert P. W. Duin
2006 Journal of Real-Time Image Processing  
Objects represented by sets of pixels/spectra in hyperspectral images are to be allocated into prespecified sorting categories.  ...  The paper provides a case-study on algorithm design in a real-world industrial sorting problem. Four groups of algorithms are studied varying the level of prior knowledge about the sorting problem.  ...  Acknowledgments The authors would like to thank Sergey Verzakov and Carmen Lai for fruitful comments on the manuscript.  ... 
doi:10.1007/s11554-006-0018-5 fatcat:q7depdun4reulixglcpppcug6y

Adaptive hierarchical clustering for hyperspectral image classification: Umbrella Clustering

S.S.P. Vithana, E.M.M.B. Ekanayake, A.R.M.A.N. Rathnayake, G.C. Jayatilaka, H.M.V.R. Herath, G.M.R.I. Godaliyadda, M.P.B. Ekanayake
2019 Journal of Spectral Imaging  
The classification algorithm which incorporates all novel concepts was tested on the HSI data set of Pavia University as well the database of Common Sri Lankan Spices and Adulterants in order to assess  ...  However, the relative proximity of spectral signatures among classes can be exploited to generate an adaptive hierarchical structure for HSI classification.  ...  Acknowledgement We are sincerely grateful to the Computational Intelligence Group of the University of the Basque Country for providing the hyperspectral image databases of the Pavia University scene,  ... 
doi:10.1255/jsi.2019.a11 fatcat:rbeq7rvwdzazpnwszbojh5xdvi

Geochemistry, Mineralization and Alteration Zones of Darrehzar Porphyry Copper Deposit, Kerman, Iran

R. Derakhshani, M. Abdolzadeh
2009 Journal of Applied Sciences  
In this work, our aim is to evaluate the capability of a regression mode of SVM, namely Support Vector Regression (SVR), for the sub-pixel classification of alteration zones.  ...  As a case study, the Hyperion data for the Sarcheshmeh, Darrehzar, and Sereidun districts is used.  ...  Acknowledgments The authors are grateful to the staff of the National Iranian Copper Industries Company, especially Sarcheshmeh and Darrehzar copper mines. We are sincerely thankful to Mr.  ... 
doi:10.3923/jas.2009.1628.1646 fatcat:24r2iposp5dfracnz7eqp2375q

Partitioned Relief-F Method for Dimensionality Reduction of Hyperspectral Images

Jiansi Ren, Ruoxiang Wang, Gang Liu, Ruyi Feng, Yuanni Wang, Wei Wu
2020 Remote Sensing  
To verify the effectiveness of the proposed Partitioned Relief-F method, a classification experiment is performed on three publicly available data sets.  ...  The experimental results indicate that the addition of the proposed partitioning strategy increases the overall accuracy of the three data sets by 1.55%, 3.14%, and 0.83%, respectively.  ...  The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; and in the decision to publish the results.  ... 
doi:10.3390/rs12071104 fatcat:724c3v5hyjdwhbf4foc7e4bm44

Utilizing Pansharpening Technique to Produce Sub-Pixel Resolution Thematic Map from Coarse Remote Sensing Image

Peng Wang, Liguo Wang, Yiquan Wu, Henry Leung
2018 Remote Sensing  
Figure 1a shows the soft classification result for Class 1. There are 3 × 3 mixed pixels in Figure 1a , and the proportion of Class 1 are marked on each mixed pixel.  ...  When the soft classification results are upsampled with scale factor of S = 2, a mixed pixel is divided into 2 × 2 sub-pixels, and 0.25 which means that 4 × 0.25 sub-pixels belong to Class 1.  ...  The authors would like to thank Qunming Wang of the Tongji University for providing the relevant data set.  ... 
doi:10.3390/rs10060884 fatcat:sa5ldfnevvexvp42hmifidqbqy

Parallel processing of remotely sensed hyperspectral imagery: full-pixel versus mixed-pixel classification

Antonio J. Plaza
2008 Concurrency and Computation  
PLAZA studies: urban characterization, land-cover classification in agriculture, and mapping of geological features, using AVIRIS data sets with detailed ground-truth.  ...  For that purpose, several dimensionality reduction techniques have been widely used in order to bring the data from a high-order dimension to a low-order dimension, thus overcoming the 'curse' of dimensionality  ...  Last but not least, the author gratefully thanks Dr Alejandro Curado from the Department of English at the University of Extremadura for his linguistic revision of the manuscript.  ... 
doi:10.1002/cpe.1291 fatcat:yc5smpfphnbwpdorihxmarulzi

Unsupervised spectral sub-feature learning for hyperspectral image classification

Viktor Slavkovikj, Steven Verstockt, Wesley De Neve, Sofie Van Hoecke, Rik Van de Walle
2016 International Journal of Remote Sensing  
In this article, we propose an unsupervised feature learning method for classification of hyperspectral images.  ...  Spectral pixel classification is one of the principal techniques used in hyperspectral image (HSI) analysis.  ...  Conclusion In this study we propose an unsupervised spectral sub-feature learning method for classification of hyperspectral images.  ... 
doi:10.1080/01431161.2015.1125554 fatcat:ef6tvu4qi5c3vnbqnygpe3rg6a

Research on Fast Face RecognitionAlgorithm Based on Block CS-LBP and HIK Kernel Method

Shaoming Pan, Gongkun Luo, Baozhong Ke, Kejiang Li
2016 International Journal of Signal Processing, Image Processing and Pattern Recognition  
Subsequently, experiments are carried out on the Yale data set and the ORL data set.  ...  At the present stage, the traditional face recognition algorithm based on LBP and SVM is not good, and the process of feature extraction and feature classification are deeply studied in this paper.  ...  and the original data is transformed into a linear separable data set in high dimensional space through high dimensional space mapping.  ... 
doi:10.14257/ijsip.2016.9.12.20 fatcat:5rfth3fhsjakpiuksx5mcn7lvq

Machine learning based hyperspectral image analysis: A survey [article]

Utsav B. Gewali, Sildomar T. Monteiro, Eli Saber
2019 arXiv   pre-print
Hyperspectral sensors enable the study of the chemical properties of scene materials remotely for the purpose of identification, detection, and chemical composition analysis of objects in the environment  ...  Machine learning algorithms due to their outstanding predictive power have become a key tool for modern hyperspectral image analysis.  ...  Open Issues and Future Challenges Curse of dimensionality The high dimensionality of hyperspectral data is a well-studied problem in remote sensing.  ... 
arXiv:1802.08701v2 fatcat:bfi6qkpx2bf6bowhyloj2duugu

Unsupervised Linear Feature-Extraction Methods and Their Effects in the Classification of High-Dimensional Data

Luis O. Jimenez-Rodriguez, Emmanuel Arzuaga-Cruz, Miguel Velez-Reyes
2007 IEEE Transactions on Geoscience and Remote Sensing  
to its capacity to overcome some difficulties of high-dimensional data.  ...  The impact is studied for supervised classification even on the conditions of a small number of training samples and unsupervised classification where unknown structures are to be uncovered and detected  ...  Flight Center for providing the AVIRIS hyperspectral image data sets used at experiment C.  ... 
doi:10.1109/tgrs.2006.885412 fatcat:pjix7c3gj5gnfbgellemubtf6y

Multiresolution manifold learning for classification of hyperspectral data

Wonkook Kim, Yangchi Chen, Melba M. Crawford, James C. Tilton, Joydeep Ghosh
2007 2007 IEEE International Geoscience and Remote Sensing Symposium  
Nonlinear manifold learning algorithms assume that the original high dimensional data actually lie on a low dimensional manifold defined by local geometric distances between samples.  ...  The new approach, which develops the manifold for the purpose of classification, incorporates an updating scheme whereby the spatial information and class labels are transferred through the segmentation  ...  We thank Amy Neuenschwander of the UT Center for Space Research for help in pre-processing the Hyperion data and interpreting the overall classification results.  ... 
doi:10.1109/igarss.2007.4423667 dblp:conf/igarss/KimCCTG07 fatcat:x6x432jwandk5im75m7pu7iqca

Deep Learning Algorithm for Video Saliency Object Detection using 3D DWT with Set Partition Integer Hierarchical Tree List

Suresh Babu D, Research Scholar Dept of ECE, UVCE, Bangalore University, India, Cyril Prasanna Raj, Professor, Dept of ECE, CIT, Bangalore. India
2021 International Journal on Electrical Engineering and Informatics  
The measure of PSNR and MSE for 120 different data sets of various dimensions and orientations demonstrates an improvement of 12%-18% in PSNR measurement as compared with existing methods.  ...  In this work detection of salient objects in image and video sequences with higher accuracy, faster processing speed and reduced computation complexity is designed using deep learning algorithm. 3 Dimensional  ...  Related work Studies have been reported in literature on use of wavelet sub bands for training deep neural networks for classification process and object detection.  ... 
doi:10.15676/ijeei.2021.13.3.7 fatcat:wx4edme7ynamxoepxwpglpvpca

Probabilistic Classification of Hyperspectral Images by Learning Nonlinear Dimensionality Reduction Mapping

X. Wang, Suresh Kumar, Fabio Ramos, Tobias Kaupp, Ben Upcroft, Hugh Durrant-Whyte
2006 2006 9th International Conference on Information Fusion  
In this paper, we combined the application of a non-linear dimensionality reduction technique, Isomap, with Expectation Maximisation in graphical probabilistic models for learning and classification of  ...  This low dimensional representation of the hyperspectral data facilitates the learning of a mixture of linear models representation similar to a mixture of factor analysers, the joint probability distributions  ...  Each pixel thus can be treated as a point in high dimensional space. Performing classification on this high dimensional data can be a large and complex problem.  ... 
doi:10.1109/icif.2006.301586 dblp:conf/fusion/WangKRKUD06 fatcat:hmscdo2sejaapbnoeocauq553m

Comparison of Two Algorithms for Land Cover Mapping Based on Hyperspectral Imagery

S. S. P. Vithana, A. M. R. Abeysekara, T. S. J. Oorloff, R. A. A. Rupasinghe, H. M. V. R. Herath, G. M. R. I. Godaliyadda, M. P. B. Ekanayake
2018 The International Journal on Advances in ICT for Emerging Regions  
The two algorithms discussed in this paper, initially represent each pixel as a point in a high dimensional space of which the dimensions represent each band of wavelength and subsequently follows two  ...  The pixels belonging to each cluster were labeled under 'soil', 'foliage' or 'water bodies', with the aid of the k-means algorithm and the hyperspectral image data of the training set obtained with the  ...  data which were used in applying the algorithm discussed in this paper.  ... 
doi:10.4038/icter.v11i1.7190 fatcat:ybunl4or5rhyjds2mch4ycbm5q

Supervised super-resolution to improve the resolution of hyperspectral images classification maps

Alberto Villa, Jocelyn Chanussot, Jon Atli Benediktsson, Christian Jutten, Lorenzo Bruzzone
2010 Image and Signal Processing for Remote Sensing XVI  
Hyperspectral data provide a wide spectral range, coupled with a very high spectral resolution, and are suitable for detection and classification of surfaces and chemical elements in the observed image  ...  Experiments were carried out on a real hyperspectral data set.  ...  Beside the problem of handling very high dimensional data, the main issue to be considered is the low spatial resolution of such images, especially in the case of high altitude sensors or instruments which  ... 
doi:10.1117/12.864938 fatcat:uk734dmv7jby3klfksxaqkvgli
« Previous Showing results 1 — 15 out of 44,755 results