Noise Reduction for Hyperspectral Image Classification using Deep Learning Technique

Hyperspectral remotely sensed images generally contain hundreds of contiguous spectral bands, which can precisely discriminate the various spectrally similar land cover classes. The presences of irrelevant and highly correlated spectral bands make a significant reduction in the classification accuracy of the hyperspectral images. Therefore, the process of dimensionality reduction is more demanding in improving the classification accuracy of the HSI. Image de-noising technique is used to improve the appearance of the image or to extract the fine details in the degraded image. The purpose of image denoising is to process an image whereby the resulting output image will be clearer than the original image. Noise reduction for HIS using deep learning is present in this paper. The presented model is simulated MATALB and analysis MSE and PSNR.