Feature extraction for hyperspectral image classification: a review

Hyperspectral image sensors capture surface reflectance over a range of wavelengths. The fine spectral information is recorded in terms of hundreds of bands. Hyperspectral image classification has observed a great interest among researchers in remote sensing community. High dimensionality provides rich spectral information for the classification process. But due to dense sampling, some of the bands may contain redundant information. Sometimes, spectral information alone may not be sufficient to obtain desired accuracy of results. Therefore, often spatial and spectral information is integrated for better accuracy. However, unlike spectral information, the spatial information is not directly available with the image. Additional efforts are needed to extract spatial information. Feature extraction is an important step in a classification framework. It has following major objectives: redundancy reduction, dimensionality reduction (usually but not always), enhancing discriminative information, and modelling of spatial features. The spectral feature extraction process transforms the original data to a new space of a different dimension, enhancing the class separability without significant loss of information. Various mathematical techniques are applied for modelling spatial features based on pixel spatial neighbourhood relations. In this paper, a review of the major feature extraction techniques is presented. Experimental results are presented for two benchmark hyperspectral images to evaluate different feature extraction techniques for various parameters.