Unsharp masking filter based shadow-invariant feature extraction for hyperspectral signatures

Hyperspectral image processing is an important research topic in remote sensing. The effect of atmosphere, especially cloud shadows need to be taken care of in hyperspectral image processing analysis. In this paper, a shadow-invariant feature extraction technique based on unsharp mask filtering is proposed for hyperspectral signatures. This technique is designed to remedy the problem of one material having different spectral signatures due to illumination condition. Similarity of the two signatures belonging to a same material in differently illuminated areas (shadow and non-shadow) is investigated before and after filtering. According to the first experiments, the proposed approach seems to be effective.