675 Hits in 3.6 sec

Anomaly detection using morphology-based collaborative representation in hyperspectral imagery

Maryam Imani
2018 European Journal of Remote Sensing  
To deal with this difficulty, in this work, the fused spectral and spatial features obtained by applying 3D Gabor filters are proposed for hyperspectral anomaly detection.  ...  Ignoring the nature of hyperspectral image leads to lose the contained spectral-spatial correlations in the hyperspectral cube.  ...  Due to the 3D spectral-spatial structure of hyperspectral image and the tightly packed correlation between spectral and spatial information, the use of 3D Gabor filters may be preferred.  ... 
doi:10.1080/22797254.2018.1446727 fatcat:tax25dk7wjewxd2cltdcrwqivu


M. Darvishnezhad, H. Ghassemian, M. Imani
2019 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Three-Dimensional Gabor Filters are the best method to extract spectral and spatial features simultaneously.  ...  One of the challenges of the hyperspectral image classification is the fusing spectral and spatial features. There are several methods for fusing features in hyperspectral image classification.  ...  In this step, spectral-spatial features will be extracted by the 3D-Gabor filters on the original hyperspectral data sets.  ... 
doi:10.5194/isprs-archives-xlii-4-w18-285-2019 fatcat:rbzhlx6lvjhyfaq4u357y2smri

Spectral–Spatial Pixel Characterization Using Gabor Filters for Hyperspectral Image Classification

O. Rajadell, P. Garcia-Sevilla, F. Pla
2013 IEEE Geoscience and Remote Sensing Letters  
This paper presents a spectral-spatial pixel characterization method for hyperspectral images.  ...  The characterization is based on textural features obtained using Gabor filters over a selected set of spectral bands.  ...  The image has a spatial dimension of 145 × 145 pixels. Spatial resolution is 20m per pixel. Spectral coverage ranges from 0.38 to 2.50nm with 220 spectral bands. Classes range from 20 to 2468 pixels.  ... 
doi:10.1109/lgrs.2012.2226426 fatcat:x4xqedjqqjc2tjtpbxwdfbpiii

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

Chen Chen, Wei Li, Hongjun Su, Kui Liu
2014 Remote Sensing  
In this paper, we propose to integrate spectral-spatial information for hyperspectral image classification and exploit the benefits of using spatial features for the kernel based ELM (KELM) classifier.  ...  Gabor features have currently been successfully applied for hyperspectral image analysis due to the ability to represent useful spatial information.  ...  Previous work [15] [16] [17] [18] has applied extracted spectral-spatial features of Gabor filter for hyperspectral image classification.  ... 
doi:10.3390/rs6065795 fatcat:e3yysmi6fzar3p3ct5fiwpzzsi

A Study of Spatial-Spectral Feature Extraction frameworks with 3D Convolutional Neural Network for Robust Hyperspectral Imagery Classification

Bishwas Praveen, Vineetha Menon
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Gabor filtering is used for spatial feature extraction in conjunction with sparse random projections for spectral feature extraction and dimensionality reduction.  ...  Experimental results reveal that the proposed spatial-spectral hyperspectral data analysis frameworks outperform the conventional 2-D convolution neural network-based spectral-spatial feature extraction  ...  A Gabor filter can effectively extract the local image "textures" or "edges" present in the image, which is achieved through convolution of the input hyperspectral image with a Gabor filter bank.  ... 
doi:10.1109/jstars.2020.3046414 fatcat:iql57nofl5f2fimjtohqgd5zmu

A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images

Yi Wang, Yan Zhang, Haiwei Song
2016 Remote Sensing  
In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated.  ...  Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps.  ...  Landgrebe from Purdue University for providing the AVIRIS image of Indian Pines and the Gamba from University of Pavia for providing the ROSIS data set.  ... 
doi:10.3390/rs8110919 fatcat:imapxo5gyvajxgkrcvfdqcnlgq

Spatial-Spectral Random Patches Network for Classification of Hyperspectral Images

Behnam Beirami, Mehdi Mokhtarzade
2019 Traitement du signal  
The results prove the superiority of the proposed method in the classification of hyperspectral images over some recent shallow and deep spatial-spectral classification techniques.  ...  The proposed network extracts the deep hierarchical Gabor features, with Gabor spatial features as inputs.  ...  In section 2, we summarize the concepts of Gabor filters, SVM, and introduce the G-RPNet and the method of combining the deep spatial-spectral features.  ... 
doi:10.18280/ts.360504 fatcat:ucd44ntflrdefo3cf3i4dfhlpy

3D local derivative pattern for hyperspectral face recognition

Jie Liang, Jun Zhou, Yongsheng Gao
2015 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
In this paper, we propose a novel 3D high-order texture pattern descriptor for hyperspectral face recognition, which effectively exploit both spatial and spectral features in hyperspectral images.  ...  Hyperspectral imaging meets such requirements by providing additional spectrum information on objects, in completion to the traditional spatial features extracted in 2D images.  ...  IMPLEMENT DETAILS In our method, we first filter the hyperspectral faces with a 3D Gabor filter.  ... 
doi:10.1109/fg.2015.7163115 dblp:conf/fgr/LiangZG15 fatcat:qyl464k6tveszapvpgag3bweau

Recent Developments in Hyperspectral Imaging for Assessment of Food Quality and Safety

Hui Huang, Li Liu, Michael Ngadi
2014 Sensors  
Hyperspectral imaging could be used to simultaneously obtain large amounts of spatial and spectral information on the objects being studied.  ...  The potential and future work of hyperspectral imaging for food quality and safety control is also discussed.  ...  [99] studied the wide line detector and Gabor filter for NIR spectral image analysis of pork marbling.  ... 
doi:10.3390/s140407248 pmid:24759119 pmcid:PMC4029639 fatcat:dfmkf2wzcne5hb4gdhygbwfrde

Gabor feature-based composite kernel method for hyperspectral image classification

Heng-Chao Li, Hong-Lian Zhou, Lei Pan, Qian Du
2018 Electronics Letters  
Different from the traditional kernel classifiers that map the original data into high-dimensional kernel space, a novel classifier that projects Gabor features of the hyperspectral image into the kernel  ...  The proposed method can not only improve the flexibility of the exploitation of spatial information but also successfully apply the kernel technique from a very different perspective to strengthen the  ...  Introduction: Hyperspectral image (HSI) is obtained by airborne or spaceborne imaging spectrometer that transmits tens or even hundreds of narrow spectral bands spanning from the visible to the infrared  ... 
doi:10.1049/el.2018.0272 fatcat:5akcfcbgkbal7pimk7wqd3rpqu

Filter Banks for Hyperspectral Pixel Classification of Satellite Images [chapter]

Olga Rajadell, Pedro García-Sevilla, Filiberto Pla
2009 Lecture Notes in Computer Science  
Satellite hyperspectral imaging deals with heterogenous images containing different texture areas.  ...  To pursue this, Gabor filters over complex planes and opponent features are taken into account and also compared in the feature extraction process. E.  ...  Briefly, spatial analysis between pixels improves hyperspectral satellite images characterization [11] but the nature of this kind of images, which are heterogeneous due to being composed of different  ... 
doi:10.1007/978-3-642-10268-4_121 fatcat:zjokmxx3bbhqlny2ifx5jhjvyq

Robust Features for Snapshot Hyperspectral Terrain-Classification [chapter]

Christian Winkens, Volkmar Kobelt, Dietrich Paulus
2017 Lecture Notes in Computer Science  
Conventional spectral cameras as used in satellite imaging use spatial or spectral scanning during acquisition which is only suitable for static scenes.  ...  Furthermore we utilize Gabor texture features which add spatial information to the feature space without increasing the data dimensionality in an excessive fashion.  ...  Conclusion Both spectral and spatial information have been investigated for classification of hyperspectral images captured with snapshot mosaic cameras.  ... 
doi:10.1007/978-3-319-64689-3_2 fatcat:qhmfpxxe4jcptg6la4y3x5nxmy

Illumination-Invariant Face Recognition in Hyperspectral Images

Han Wang, Glenn Healey
2019 Journal of Computer Sciences and Applications  
We first learn a basis in the spectral domain. We then extract spatial features using 2D Gabor filters. Finally, we use the basis and the spatial features to classify face images.  ...  Previous studies use either spatial or spectral information to address this problem. In this paper, we propose an algorithm that uses spatial and spectral information simultaneously.  ...  Gabor Phase The central band of a hyperspectral image is used to extract Gabor phase features. This band is first normalized to the range [0,1] to remove scaling effects.  ... 
doi:10.12691/jcsa-7-1-4 fatcat:c2rmxqkgfreghbyd3pir3f24rq

A steerable filter bank approach to endmembers estimation in imaging spectroscopy

Ivica Kopriva, Danielle Nuzillard
2015 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)  
Estimation of pure spectral signatures, called endmembers, is a key step in hyperspectral image (HI) analysis.  ...  We propose endmembers estimation method that uses Gabor Filter Banks (GFBs) to filter HI into set of HIs with different resolutions and orientations.  ...  METHODOLOGY 2-D Gabor filters are used due to their ability to realize multichannel filtering and decomposing an input spectral images into sparse images containing intensity variation over narrow range  ... 
doi:10.1109/igarss.2015.7326133 dblp:conf/igarss/KoprivaN15 fatcat:g5auqcisnjcfhjxlty7xc2khnq

Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework

Zexuan Zhu, Sen Jia, Shan He, Yiwen Sun, Zhen Ji, Linlin Shen
2015 Information Sciences  
[4] introduced a 3D Gabor filterbank as a tool for extracting spectral-spatial features to represent image regions in hyperspectral region classification.  ...  Introduction Hyperspectral imaging captures an image of objects with wavelengths ranging from the visible spectrum to the infrared region.  ... 
doi:10.1016/j.ins.2014.11.045 fatcat:clivk6nhevblnbcsei4ybsu4ri
« Previous Showing results 1 — 15 out of 675 results