Hyperspectral Image Classification via Kernel Basic Thresholding Classifier

TOKSÖZ, Mehmet Altan
Ulusoy, İlkay
We propose a nonlinear kernel version of recently introduced basic thresholding classifier (BTC) for hyperspectral image (HSI) classification. BTC is a sparsity-based linear classifier, which utilizes inner product for similarity measure based on the fact that the hyperspectral data are linearly separable in the feature space. In practice, the pixels of different classes of a given HSI are not always distinct and may overlap. This is known as the inseparability problem, which reduces the performance of a linear classifier. In order to solve this problem in the feature space, we propose the kernel BTC (KBTC) algorithm that achieves promising performance by utilizing well-known "kernel trick." To increase the classification accuracy further, we present spatial-spectral KBTC that incorporates spatial information using weighted least squares filter with a guidance image. Furthermore, we apply L-0 smoothing technique on the guidance image, which provides additional improvements. Experimental results on publicly available HSI data sets showed that the proposal and its spatial extension yield better classification results as compared with linear similarity-based BTC, nonlinear kernel-based support vector machines, kernel orthogonal matching pursuit, recently proposed logistic regression via splitting and augmented Lagrangian, and their spatial extensions.


Hyperspectral Image Classification via Basic Thresholding Classifier
Toksoz, Mehmet Altan; Ulusoy, İlkay (2016-07-01)
We propose a lightweight sparsity-based algorithm, namely, the basic thresholding classifier (BTC), for hyperspectral image (HSI) classification. BTC is a pixelwise classifier which uses only the spectral features of a given test pixel. It performs the classification using a predetermined dictionary consisting of labeled training pixels. It then produces the class label and residual vector of the test pixel. Since incorporating spatial and spectral information in HSI classification is quite an effective way...
Image segmentation by fusion of low level and domain specific information via Markov Random Fields
Karadag, Ozge Oztimur; Yarman Vural, Fatoş Tunay (2014-09-01)
We propose a new segmentation method by fusing a set of top-down and bottom-up segmentation maps under the Markov Random Fields (MRF) framework. The bottom-up segmentation maps are obtained by varying the parameters of an unsupervised segmentation method, such as Mean Shift. The top-down segmentation maps are constructed from some priori information, called domain specific information (DSI), received from a domain expert in the form of general properties about the image dataset. The properties are then used...
Sahin, Kerem; Ulusoy, İlkay (2013-07-26)
An automatic segmentation algorithm that is based on watersheds and region merging type multi-scale segmentation (MSS) is proposed, which can be used as the initial step of an object-based classifier. First, the image is segmented using watershed segmentation. Then, primitive segments are merged to create meaningful objects by the proposed hybrid region merging algorithm. During these steps, an unsupervised segmentation accuracy metric is considered so that best performing parameters of the proposed algorit...
Süperpikseller ve İmza Tabanlı Yöntemler Kullanarak Hiperspektral Hedef Tespiti
Kütük, Mustafa; Alatan, Abdullah Aydın (2019-06-27)
Spectral signature based methods which form the mainstream in hyperspectral target detection can be classified mainly in three categories as the methods using background modeling, subspace projection based methods, and hybrid methods merging linear unmixing with background estimation. A common characteristic of all these methods is to classify each pixel of the hyperspectral image as a target or background while ignoring the spatial relations between neighbor pixels. Integration of contextual information de...
Contour approximation of data: A duality theory
İyigün, Cem (Elsevier BV, 2009-05-01)
Given a dataset D partitioned in clusters, the joint distance function (JDF)J(x) at any point x is the harmonic mean of the distances between x and the cluster centers. The JDF is a continuous function, capturing the data points in its lower level sets (a property called contour approximation), and is a useful concept in probabilistic clustering and data analysis.
Citation Formats
M. A. TOKSÖZ and İ. Ulusoy, “Hyperspectral Image Classification via Kernel Basic Thresholding Classifier,” IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, pp. 715–728, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/38058.