Jian Fan

TL;DR: In this article, the performance of wavelet packet spaces is measured in terms of sensitivity and selectivity for the classification of twenty-five natural textures, where both energy and entropy metrics are computed for each wavelet packets and incorporated into distinct scale space representations, where each texture channel reflected a specific scale and orientation sensitivity.

TL;DR: The reliability exhibited by texture signatures based on wavelet packets analysis suggest that the multiresolution properties of such transforms are beneficial for accomplishing segmentation, classification and subtle discrimination of texture.

TL;DR: It is demonstrated that features extracted from multiresolution representations can provide an adaptive mechanism for accomplishing local contrast enhancement and by improving the visualization of breast pathology, one can improve chances of early detection while requiring less time to evaluate mammograms for most patients.

TL;DR: Improvements in image contrast for multiscale imageprocessing algorithms were superior to those obtained using existing competitive algorithms and suggest that wavelet based image processing algorithms could play an important role in improving the imaging performance of digital mammography.

TL;DR: A novel method of feature extraction for texture segmentation that relies on multichannel wavelet frames and 2-D envelope detection and two algorithms for envelope detection based on the Hilbert transform and zero crossings are introduced.