Feature Extraction of Hyperspectral Images Based On LBP and RF Feature Extraction Techniques

This project deals with the feature extraction of hyperspectral images using LBP and RF based feature extraction techniques. Nowadays hyperspectral images find a wide variety of applications in the field of agriculture, eye care, mineralogy, astronomy and chemical imaging. Since hyperspectral images collect and process information from the entire EM spectrum, these images give exhaustive spectral data about the behavior of the objects. This information is used to discriminate various landscapes. Due to the high dimensionality of hyperspectral images, it is difficult to process the hyperspectral images. Feature extraction techniques are used to eliminate the dimensionality problems and reduce the computational complexity. The performance of this method is analyzed by using the quality indexes called, overall accuracy, average accuracy and kappa.