PROJECT TITLE :
Discriminant Tensor Spectral–Spatial Feature Extraction for Hyperspectral Image Classification
We have a tendency to propose to integrate spectral-spatial feature extraction and tensor discriminant analysis for hyperspectral image classification. Initial, we tend to apply exceptional spectral-spatial feature extraction approaches within the hyperspectral cube to extract a feature tensor for each pixel. Then, based on category label data, local tensor discriminant analysis is used to get rid of redundant info for subsequent classification procedure. The approach not solely extracts sufficient spectral-spatial options from original hyperspectral images but also gets higher feature representation as a result of tensor framework. Comparative results on 2 benchmarks demonstrate the effectiveness of our method.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here