Абстрактный

Hyperspectral Image Resolution Enhancement Using Object Tagging OLHE Technique

R. Dhivya, S. Agustin Vijay

Resolution plays an important role in hyperspectral images like satellite images. The discrete wavelet transform based (DWT) resolution enhancement scheme generates artifacts due to a shift-variant property. Resolution enhancement based on dual-tree complex wavelet transform (DT-CWT) and nonlocal means (NLM) suffers from high latency. In this paper a new method based on oriented local histogram equalization (OLHE) is proposed for resolution enhancement of hyper spectral images. Satellite Images acquired by satellite is affected by impulse noise. This impulse noise distorts the edge pixels in the satellite image, which degrades the segmentation process. Hence, this impulse noise should be removed before enhancing satellite images. Optimum Edge preserving impulse noise removing algorithm is proposed in this paper to remove the impulse noise present in the satellite image. OLHE technique which is similar to local histogram equalization is proposed to capture the orientation of edges in the image that enhances the resolution. Performance analysis is made by calculating PSNR and MSE value which reveals superiority of the proposed technique over the conventional and state-of-the-art RE techniques.