A framework for contrast enhancement by dyadic wavelet analysis

This paper introduces a method for accomplishing mammographic feature analysis by mul-tiresolution representations of the dyadic wavelet transform. Our approach consists of the application of non-linear enhancing functions E(z) within levels of a multiresolution representation. We show that there exists a simple constraint for E(z) such that image enhancement is guaranteed. Furthermore, a simple case in which the enhancement operator is a constant multiplier is mathematically equivalent to traditional unsharp masking. We show quantitatively that transform coeecients, modiied within each level by non-linear operators, can make more obvious unseen or barely seen features of mammography without requiring additional radiation. Our results are compared with traditional image enhancement techniques by measuring the local contrast of known mammographic features.