Using geometric wavelets based on active contours for signal processing

Abstract

Certain embodiments provide systems and methods for using geometric wavelets based on active contours for signal processing. Certain embodiments may allow image processing. A system includes providing an image processing circuitry that computes a segmentation tree using active contours for an input image data; creates a geometric wavelets representation using the segmentation tree; and then generate an image based on geometric wavelet sparse representation extracted from the geometric wavelets representation. The geometric wavelet sparse representation may comprise M most active geometric wavelets from a set of N geometric wavelets in the geometric wavelets representation. The image processing circuitry may recursively find sub-domains and multivariate polynomials for each domain at each stage in the computing of the segmentation tree. Each of the sub-domains is a domain for a succeeding stage for the segmentation tree. The recursively finding may be terminated, for example, when each domain at a stage comprises less than a determined number of pixels.