Image de-noising in the wavelet domain using prior spatial constraints

This paper describes an algorithm for the noise removal in the wavelet domain, which takes into account not only the local noise measure, but also prior spatial constraints. These prior spatial or geometrical constraints express the fact that meaningful wavelet coefficients appear in spatially connected clusters, forming edges of given directions. Existing techniques that exploit this kind of prior knowledge are computationally expensive, while the proposed method exploits the spatial constraints in a different and simple manner. We are mostly interested in de-noising infrared images of natural terrain, for the purpose of landmine detection