This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

A new spectral-spatial classification scheme for hyperspectral images is proposed. The method combines the results of a pixel wise support vector machine classification and the segmentation map obtained by partitional clustering using majority voting. The ISODATA algorithm and Gaussian mixture resolving techniques are used for image clustering. Experimental results are presented for two hyperspectral airborne images. The developed classification scheme improves the classification accuracies and provides classification maps with more homogeneous regions, when compared to pixel wise classification. The proposed method performs particularly well for classification of images with large spatial structures and when different classes have dissimilar spectral responses and a comparable number of pixels.

/pdf/spectral-spatial-classification-of-hyperspectral-imagery-2y26zvvaob.pdf

Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques

Hyperspectral imaging involves large amounts of information. This paper presents a technique for dimensionality reduction to deal with hyperspectral images. The proposed method is based on a hierarchical clustering structure to group bands to minimize the intracluster variance and maximize the intercluster variance. This aim is pursued using information measures, such as distances based on mutual information or Kullback-Leibler divergence, in order to reduce data redundancy and non useful information among image bands. Experimental results include a comparison among some relevant and recent methods for hyperspectral band selection using no labeled information, showing their performance with regard to pixel image classification tasks. The technique that is presented has a stable behavior for different image data sets and a noticeable accuracy, mainly when selecting small sets of bands.

/pdf/clustering-based-hyperspectral-band-selection-using-73nc955ok0.pdf

Clustering-Based Hyperspectral Band Selection Using Information Measures

Imaging spectroscopy, also known as hyperspectral imaging, has been transformed in the last four decades from being a sparse research tool into a commodity product available to a broad user community. Specially, in the last 10 years, a large number of new techniques able to take into account the special properties of hyperspectral data have been introduced for hyperspectral data processing, where hyperspectral image classification, as one of the most active topics, has drawn massive attentions. Spectral–spatial hyperspectral image classification can achieve better classification performance than its pixel-wise counterpart, since the former utilizes not only the information of spectral signature but also that from spatial domain. In this paper, we provide a comprehensive overview on the methods belonging to the category of spectral–spatial classification in a relatively unified context. First, we develop a concept of spatial dependency system that involves pixel dependency and label dependency, with two main factors: neighborhood covering and neighborhood importance. In terms of the way that the neighborhood information is used, the spatial dependency systems can be classified into fixed, adaptive, and global systems, which can accommodate various kinds of existing spectral–spatial methods. Based on such, the categorizations of single-dependency, bilayer-dependency, and multiple-dependency systems are further introduced. Second, we categorize the performings of existing spectral–spatial methods into four paradigms according to the different fusion stages wherein spatial information takes effect, i.e., preprocessing-based, integrated, postprocessing-based, and hybrid classifications. Then, typical methodologies are outlined. Finally, several representative spectral–spatial classification methods are applied on real-world hyperspectral data in our experiments.

Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines

Convolutional neural networks for hyperspectral image classification

This letter 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. This scheme aims at improving land-use classification results, decreasing significantly the number of spectral bands needed in order to reduce the dimensionality of the task owing to an adequate description of the spatial characteristics of the image. This allows requiring less data and avoiding the curse of dimensionality. Very promising results are obtained which are similar to or better than previous classification results provided by other spectral-spatial methods but here also reducing the complexity using a reduced number of spectral bands.

/pdf/spectral-spatial-pixel-characterization-using-gabor-filters-4z72uuxaq5.pdf

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

Face gender classification: A statistical study when neutral and distorted faces are combined for training and testing purposes

This work presents the application of a novel technique on dimensionality reduction to deal with multispectral images. A distance based on mutual information is used to construct a hierarchical clustering structure. Experimental results show that the method provides a very suitable subset of multispectral bands for pixel classification purposes.

Clustering-based multispectral band selection using mutual information

Hyperspectral remote sensing provides data in large amounts from a wide range of wavelengths in the spectrum and the possibility of distinguish subtle differences in the image. For this reason, the process of band selection to reduce redundant information is highly recommended to deal with them. Band selection methods pursue the reduction of the dimension of the data resulting in a subset of bands that preserves the most of information. The accuracy is given by the classification performance of the selected set of bands. Usually, pixel classification tasks using grey level values are used to validate the selection of bands. We prove that by using textural features, instead of grey level information, the number of hyperspectral bands can be significantly reduced and the accuracy for pixel classification tasks is improved. Several characterizations based on the frequency domain are presented which outperform grey level classification rates using a very small number of hyperspectral bands.

Pedro García-Sevilla

Papers

Clustering-Based Hyperspectral Band Selection Using Information Measures

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

Face gender classification: A statistical study when neutral and distorted faces are combined for training and testing purposes

Clustering-based multispectral band selection using mutual information

Textural Features for Hyperspectral Pixel Classification