ABSTRACT

Linear discriminant analysis (LDA) is most commonly used as a dimensionality reduction technique in the pre-processing step for pattern classification and machine learning applications. In contrast to principal component analysis (PCA), LDA is “supervised” and computes the directions or linear discriminants that will represent the axes that maximize the separation between multiple classes. X. Cheng et al. presented a novel method that combines PCA and FLD methods to show that the hybrid PCA-FLD method maximizes the representation and classification effects on the extracted new feature bands. A near-infrared (NIR) hyperspectral imaging system was used to develop classification models to differentiate wheat classes. Wavelet texture analysis was used for classification of eight Western Canadian wheat classes using NIR hyperspectral imaging of bulk samples. The research by M. Nagata et al. was aimed at developing techniques for detection of compression bruises in strawberries using NIR hyperspectral imaging.