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: This letter presents a novel spatial feature called object correlative index (OCI) to enhance the classification of very high resolution images. This novel method considers the property of an image object based on spectral similarity to construct a useful OCI to describe the spatial information objectively. Compared with the generic features widely used in image classification, the classification approach based on the OCI spatial feature results in higher classification accuracy than those approaches that only consider spectral features or pixelwise spatial features, such as the pixel shape index and mathematical morphology profiles. Experiments are conducted on QuickBird satellite image and aerial photo data, and results confirm that the proposed method is feasible and effective.
    IEEE Geoscience and Remote Sensing Letters 01/2013; 10(6):1572-1576. · 1.82 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The availability of satellite imagery has expanded over the past few years, and the possibility to perform fast processing of massive databases comprising this kind of imagery data has opened ground-breaking perspectives in many different fields. This paper describes a web-based system (available online:, which allows an inexperienced user to perform unsupervised classification of satellite/airborne images. The processing chain adopted in this work has been implemented in C language and integrated in our proposed tool, developed with HTML5, JavaScript, Php, AJAX and other web programming languages. Image acquisition with the applications programmer interface (API) is fast and efficient. An important added functionality of the developed tool is its capacity to exploit a remote server to speed up the processing of large satellite/airborne images at different zoom levels. The ability to process images at different zoom levels allows the tool an improved interaction with the user, who is able to supervise the final result. The previous functionalities are necessary to use efficient techniques for the classification of images and the incorporation of content-based image retrieval (CBIR). Several experimental validation types of the classification results with the proposed system are performed by comparing the classification accuracy of the proposed chain by means of techniques available in the well-known Environment for Visualizing Images (ENVI) software package.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 01/2013; 6(4):1934-1948. · 2.87 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a novel method for dimensionality reduction of hyperspectral images. It combines Empirical Mode Decomposition (EMD) with wavelets in order to generate the smallest set of features that leads to the best classification accuracy. The introduced method exploits both spatial and spectral information of the image which leads to more and better class separability and hence to better classification accuracy. Specifically, the 2D-EMD is applied to each hyperspectral band to enhance spatial information and then 1D-DWT is applied to each EMD feature's signatures to enhance spectral information. The reduced Wavelet-based Intrinsic Mode Function Features (WIMF) are obtained by selecting coefficients. Then, new features are generated by summing up the lower order WIMF features. Support Vector Machine (SVM) based classification is performed with two different hyperspectral data sets, namely AVIRIS Indian Pine and ROSIS Pavia. The experimental results show that features obtained by the proposed method significantly increase the classification accuracy compared to features obtained by other frequency based direct dimensionality reduction methods.
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 01/2012; 5(6):1821-1830. · 2.87 Impact Factor

Full-text (2 Sources)

Available from
May 30, 2014