Filters








5,698 Hits in 4.2 sec

HYPERSPECTRAL IMAGE BAND SELECTION BASED ON SUBSPACE CLUSTERING

Zhi-jun ZHENG, Yan-bin PENG
2021 International Journal of Engineering Technologies and Management Research  
This method considers each band image as a feature vector, clustering band images using subspace clustering method. After that, a representative band is selected from each cluster.  ...  Aiming at the problems in hyperspectral image classification, such as high dimension, small sample and large computation time, this paper proposes a band selection method based on subspace clustering,  ...  Based on the similarity matrix, the spectral clustering algorithm is used to cluster the band images, and the cluster center of each class is selected as the representative band to form the band subset  ... 
doi:10.29121/ijetmr.v8.i8.2021.1014 fatcat:xch34kmrdrhz3leuko6kbd467e

Lossless Compression for Hyperspectral Images based on Adaptive Band Selection and Adaptive Predictor Selection

2020 KSII Transactions on Internet and Information Systems  
Then, an adaptive predictor selection strategy based on clustering map is adopted to select the optimal CRLS predictor for each pixel.  ...  Afterwards, an adaptive band selection strategy based on inter-spectral correlation coefficient is adopted to select the reference bands for each band.  ...  For one hyperspectral image, clustering module requires where W, H and N represent the width, height and number of band for hyperspectral image, respectively.  ... 
doi:10.3837/tiis.2020.08.008 fatcat:76orwrwvtnaknina7mm63spasu

A survey of band selection techniques for hyperspectral image classification

Shrutika Sawant, Manoharan Prabukumar
2020 Journal of Spectral Imaging  
Hyperspectral images usually contain hundreds of contiguous spectral bands, which can precisely discriminate the various spectrally similar classes.  ...  Our purpose is to highlight the progress attained in band selection techniques for hyperspectral image classification and to identify possible avenues for future work, in order to achieve better performance  ...  Acknowledgement The authors thank the Council of Scientific & Industrial Research (CSIR), New Delhi, India, for the award of CSIR-SRF and the Vellore Institute of Technology (VIT) for providing a VIT seed  ... 
doi:10.1255/jsi.2020.a5 fatcat:cvibjoofbbd6jpu4ij626wigdy

Unsupervised Spectral-Spatial Feature Selection-Based Camouflaged Object Detection Using VNIR Hyperspectral Camera

Sungho Kim
2015 The Scientific World Journal  
Conventional supervised learning methods for hyperspectral images can be a feasible solution. Such approaches, however, require a priori information of a camouflaged object and background.  ...  This letter proposes a fully autonomous feature selection and camouflaged object detection method based on the online analysis of spectral and spatial features.  ...  The optimal set of bands can be selected using the local maxima/minima from the loading curve of PC2 as shown in Figure 6 (b).  ... 
doi:10.1155/2015/834635 pmid:25879073 pmcid:PMC4386716 fatcat:dn6muvgp4rhh7e2csq4jwinsrq

Material Discrimination Algorithm Based on Hyperspectral Image

Jian Zhou, Zhuping Wang, Yingjie Jiao, Cong Nie, Yi-Zhang Jiang
2021 Scientific Programming  
However, it is difficult to process it directly because of the huge hyperspectral image data.  ...  The subspace clustering self-attention adversarial network is constructed to realize the initial selection of band.  ...  [13] used the particle swarm optimization to optimize the band selection process; Xiurui Geng et al. [14] realized a band selection through gradient analysis of different band images.  ... 
doi:10.1155/2021/8329974 fatcat:ubolzysibragzn5zi5p3huez5q

BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image [article]

Yaoming Cai, Xiaobo Liu, Zhihua Cai
2019 arXiv   pre-print
Hyperspectral image (HSI) consists of hundreds of continuous narrow bands with high spectral correlation, which would lead to the so-called Hughes phenomenon and the high computational cost in processing  ...  However, many of existing band selection methods separately estimate the significance for every single band and cannot fully consider the nonlinear and global interaction between spectral bands.  ...  Zhang who provided the source codes of the OPBS method, and Prof. M. Gong who provided the source codes of the MOBS method.  ... 
arXiv:1904.08269v1 fatcat:ej2fiy5s4zfp3jgi6vrijeclui

Spectral partitioning for hyperspectral remote sensing image classification

Yi Liu, Jun Li, Antonio Plaza, Jose Bioucas-Dias, Aurora Cuartero, Pablo Garcia Rodriguez
2014 2014 IEEE Geoscience and Remote Sensing Symposium  
In this paper, we present a new approach for spectral partitioning which is intended to deal with ill-posed problems in hyperspectral image classification.  ...  Such grouping strategy not only allows us to reduce the number of spectral bands, but also to provide a different perspective on the original hyperspectral data.  ...  It is also worth mentioning that the optimal number of clusters selected by AAP (N C = 3) performs better than any other tested number.  ... 
doi:10.1109/igarss.2014.6947220 dblp:conf/igarss/LiuLPBCR14 fatcat:xypqof32lfdttci5spz6xli4ye

A novel approach to hyperspectral band selection based on spectral shape similarity analysis and fast branch and bound search

Shijin Li, Jianbin Qiu, Xinxin Yang, Huan Liu, Dingsheng Wan, Yuelong Zhu
2014 Engineering applications of artificial intelligence  
information of hyperspectral remote sensing images.  ...  Firstly, spectral clustering is utilized to cluster all the training samples, which produces the prototypical spectral curves of each cluster.  ...  Moser for providing us the training/test samples of Indian Pine data set.  ... 
doi:10.1016/j.engappai.2013.07.010 fatcat:kxukw7m2gjaj7c2vzabahrozzm

An Unsupervised Learning Of Hyperspectral Images Using Fuzzy C-means (FCM) Clustering Method With Glowworm Swarm Optimization (GSO)

2019 Advanced Materials Proceedings  
The GSO is introduced to enhance the performance of fuzzy clustering to optimize the characteristics of hyperspectral images.  ...  Fuzzy C-Means (FCM) clustering is an optimistic and strategic method for selecting the unsupervised bands. There are some limits and standards in fuzzy clustering technique.  ...  By using the proposed Fuzzy C-means Clustering Method with Glowworm Swarm Optimization FCM-GSO method the selected datasets are executed using MATLAB program and the screenshot of each dataset executed  ... 
doi:10.5185/amp.2019.0019 fatcat:l3gq4i5lsratnkuzijxnj2rzma

Unsupervised hyperspectral band selection via multi-feature information-maximization clustering

Marco Bevilacqua, Yannick Berthoumieu
2017 2017 IEEE International Conference on Image Processing (ICIP)  
This paper presents a new approach for unsupervised band selection in the context of hyperspectral imaging.  ...  The hyperspectral band selection (HBS) task is considered as a clustering problem: bands are clustered in the image space; one representative image is then kept for each cluster, to be part of the set  ...  Band selection: for each cluster, a unique representant (an image, corresponding to a specific spectral band) is kept.  ... 
doi:10.1109/icip.2017.8296339 dblp:conf/icip/BevilacquaB17 fatcat:qrb2pb4se5a63bqoz2wbm7wacm

A Spatial–Spectral Combination Method for Hyperspectral Band Selection

Xizhen Han, Zhengang Jiang, Yuanyuan Liu, Jian Zhao, Qiang Sun, Yingzhi Li
2022 Remote Sensing  
Hyperspectral images are characterized by hundreds of spectral bands and rich information. However, there exists a large amount of information redundancy among adjacent bands.  ...  In this study, a spatial–spectral combination method for hyperspectral band selection (SSCBS) is proposed to reduce information redundancy.  ...  was used for band selection.  ... 
doi:10.3390/rs14133217 fatcat:mlweqayppjb45gblj3mvmou4ja

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Samiran Das, Sawon Pratiher, Chirag Kyal, Pedram Ghamisi
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The work subsequently selects the representative bands from each cluster by combining structural information of the band images with the statistical similarity measure.  ...  Hyperspectral images provide rich spectral information corresponding to visible and near-infrared imaging regions, facilitating accurate classification, object identification, and target detection.  ...  PROPOSED BAND SELECTION METHOD Generally, the adjoining spectral bands of any hyperspectral data disseminate similar information resulting in spectral redundancy [51] .  ... 
doi:10.1109/jstars.2022.3172112 fatcat:sdrvf2r5ind23p2iruylfmgccy

Feature Band Selection for Online Multispectral Palmprint Recognition

Zhenhua Guo, David Zhang, Lei Zhang, Wenhuang Liu
2012 IEEE Transactions on Information Forensics and Security  
One crucial step in developing online multispectral palmprint systems is how to determine the optimal number of spectral bands and select the most representative bands to build the system.  ...  This paper presents a study on feature band selection by analyzing hyperspectral palmprint data (520-1050 nm).  ...  CONCLUSION In this paper, a spectral -means clustering algorithm is proposed to cluster hyperspectral palmprint cubes. The clustering could be used to determine an optimal number of feature bands.  ... 
doi:10.1109/tifs.2012.2189206 fatcat:qq4vt6ucljgnfeya2u5l7hofti

An Automatic Method for Unsupervised Feature Selection of Hyperspectral Images Based on Fuzzy Clustering of Bands

Behnam Beirami, Mehdi Mokhtarzade
2020 Traitement du signal  
In this study, an automatic unsupervised method is presented for feature selection from hyperspectral images.  ...  Hyperspectral sensors collect spectral data in numerous adjacent spectral bands which are usually redundant and cause some challenges such as Hughes phenomenon.  ...  For example, clustering and ranking methods can be integrated for unsupervised band selection of the hyperspectral image [29] .  ... 
doi:10.18280/ts.370218 fatcat:x2qqt2vdpzd5parrjfpubfhb2m

Growth Identification of Aspergillus flavus and Aspergillus parasiticus by Visible/Near-Infrared Hyperspectral Imaging

Xuan Chu, Wei Wang, Xinzhi Ni, Haitao Zheng, Xin Zhao, Ren Zhang, Yufeng Li
2018 Applied Sciences  
A band ratio using two bands at 446 nm and 460 nm separated A. flavus and A. parasiticus on day 1 from other days. Image at band of 520 nm classified A. parasiticus on day 6.  ...  Finally, the visualized prediction images for A. flavus and A. parasiticus in different growth days were made by applying the optimal wavelength's SVM models on every pixel of the hyperspectral image.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app8040513 fatcat:2rxstlkdbncwrm2bm6ltho5guq
« Previous Showing results 1 — 15 out of 5,698 results