A 3d-Deep CNN Based Feature Extraction and Hyperspectral Image Classification

Hyperspectral image consists of huge spectral and special information. Deep learning models, such as deep convolutional neural networks (CNNs) being widely used for HSI classification. Most of the approaches are based on 2D CNN. Whereas, the HSI classification performance depends on both spatial and spectral information. This paper proposes a new 3D-Deep Feature Extraction CNN model for the HSI classification which uses both spectral and spatial information. Here the HSI data is divided into 3D patches and fed into the proposed model for deep feature extractions. Experimental results show that the performance of HSI classification is improved significantly with the proposed model. The experimental results on the publicly available HSI datasets, viz., Indian Pines(IP), Pavia University scene(PU) and Salinas scene(SA), are compared with the contemporary models. The current results indicates that the proposed model provides comparatively better results than the state-of-the-art methods.