Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles

Signal & Image Dept., Grenoble Inst. of Technol., Grenoble
IEEE Transactions on Geoscience and Remote Sensing (Impact Factor: 3.47). 12/2008; DOI: 10.1109/TGRS.2008.922034
Source: OAI

ABSTRACT A method is proposed for the classification of urban hyperspectral data with high spatial resolution. The approach is an extension of previous approaches and uses both the spatial and spectral information for classification. One previous approach is based on using several principal components (PCs) from the hyperspectral data and building several morphological profiles (MPs). These profiles can be used all together in one extended MP. A shortcoming of that approach is that it was primarily designed for classification of urban structures and it does not fully utilize the spectral information in the data. Similarly, the commonly used pixelwise classification of hyperspectral data is solely based on the spectral content and lacks information on the structure of the features in the image. The proposed method overcomes these problems and is based on the fusion of the morphological information and the original hyperspectral data, i.e., the two vectors of attributes are concatenated into one feature vector. After a reduction of the dimensionality, the final classification is achieved by using a support vector machine classifier. The proposed approach is tested in experiments on ROSIS data from urban areas. Significant improvements are achieved in terms of accuracies when compared to results obtained for approaches based on the use of MPs based on PCs only and conventional spectral classification. For instance, with one data set, the overall accuracy is increased from 79% to 83% without any feature reduction and to 87% with feature reduction. The proposed approach also shows excellent results with a limited training set.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Hyperspectral imaging has been used in dermatology for many years. The enrichment of hyperspectral imaging with image analysis broadens considerably the possibility of reproducible, quantitative evaluation of, for example, melanin and haemoglobin at any location in the patient's skin. The dedicated image analysis method proposed by the authors enables to automatically perform this type of measurement.Material and method: As part of the study, an algorithm for the analysis of hyperspectral images of healthy human skin acquired with the use of the Specim camera was proposed. Images were collected from the dorsal side of the hand. The frequency lamda of the data obtained ranged from 397 to 1030 nm. A total of 4'000 2D images were obtained for 5 hyperspectral images. The method proposed in the paper uses dedicated image analysis based on human anthropometric data, mathematical morphology, median filtration, normalization and others. The algorithm was implemented in Matlab and C programs and is used in practice. The algorithm of image analysis and processing proposed by the authors enables segmentation of any region of the hand (fingers, wrist) in a reproducible manner. In addition, the method allows to quantify the frequency content in different regions of interest which are determined automatically. Owing to this, it is possible to perform analyses for melanin in the frequency range lamdaE[element of](450,600) nm and for haemoglobin in the range lamdaH[element of](397,500) nm extending into the ultraviolet for the type of camera used. In these ranges, there are 189 images for melanin and 126 images for haemoglobin. For six areas of the left and right sides of the little finger (digitus minimus manus), the mean values of melanin and haemoglobin content were 17% and 15% respectively compared to the pattern. The obtained results confirmed the usefulness of the proposed new method of image analysis and processing in dermatology of the hand as it enables reproducible, quantitative assessment of any fragment of this body part. Each image in a sequence was analysed in this way in no more than 100 ms using Intel Core i5 CPU M460 @ 2.5GHz 4GB RAM.
    BioMedical Engineering OnLine 04/2014; 13(1):47. · 1.61 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a novel sparse representation-based classifier for landcover mapping of hyperspectral image data. Each image patch is factorized into segmentation patterns, also called shapelets, and patch-specific spectral features. The combination of both is represented in a patch-specific spatial-spectral dictionary, which is used for a sparse coding procedure for the reconstruction and classification of image patches. Hereby, each image patch is sparsely represented by a linear combination of elements out of the dictionary. The set of shapelets is specifically learned for each image in an unsupervised way in order to capture the image structure. The spectral features are assumed to be the training data. The experiments show that the proposed approach shows superior results in comparison to sparse-representation based classifiers that use no or only limited spatial information and behaves competitive or better than state-of-the-art classifiers utilizing spatial information and kernelized sparse representation-based classifiers.
    IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS); 08/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The 2013 Data Fusion Contest organized by the Data Fusion Technical Committee (DFTC) of the IEEE Geoscience and Remote Sensing Society aimed at investigating the synergistic use of hyperspectral and Light Detection And Ranging (LiDAR) data. The data sets distributed to the participants during the Contest, a hyperspectral imagery and the corresponding LiDAR-derived digital surface model (DSM), were acquired by the NSF-funded Center for Airborne Laser Mapping over the University of Houston campus and its neighboring area in the summer of 2012. This paper highlights the two awarded research contributions, which investigated different approaches for the fusion of hyperspectral and LiDAR data, including a combined unsupervised and supervised classification scheme, and a graph-based method for the fusion of spectral, spatial, and elevation information.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 05/2014; · 2.87 Impact Factor

Full-text (2 Sources)

Available from
May 30, 2014