A Novel Feature Derivation Technique for SVM based Hyper Spectral Image Classification

Abstract

A spatial classification technique incorporating a novel feature derivation method is proposed for classifying the heterogeneous classes present in the hyper spectral images. The classification accuracy can be improved if and only if both the feature extraction and classifier selection are proper. As the classes present in the hyper spectral image are having different textures,

Online Classification and Measurement of Pencils using Image Processing Techniques

“…A LabVIEW controlled image acquisition system is developed in [4] for automated, dynamic pupilometry and blink detection based on fire wire digital camera. Classification of the heterogeneous classes present in the hyper spectral image using a spatial classification technique incorporating a novel feature derivation method is proposed in [5]. In [6], an image segmentation technique using moment based K-Means algorithm is proposed to identify ripe tomatoes.…”

Hyperspectral Image Classification using Softcomputing Techniques: A Review

“…The notion of the existence of natural, inherent groupings of spectral values within a scene may not be intuitively obvious, but it can be demonstrated that remotely sensed images are usually composed of spectral classes that are reasonably uniform internally in respect to brightness in several spectral channels. The algorithm identifies clusters or groups of these similar data and the analyst identifies the individual clusters [16].…”

“…The choice of a particular classifier or decision rule depends on the nature of the input data and the desired output. Among the most frequently used classification algorithms are the maximum likelihood, Bayesian, minimum distance and parallelepiped algorithms [16].…”