Nonconvex Compressive Sensing Optimal Reconstruction Method Based on Sketch Representation and Structured Clustering

Abstract

The invention discloses a non-convex compressive sensing optimization reconstruction method based on sketch representation and structured clustering, which mainly solves the problem of inaccurate reconstruction of compressive sensing images at low sampling rates. The realization process is as follows: according to the sketch map of the image , defines sketchable blocks and non-sketchable blocks, where non-sketchable blocks include smooth blocks and texture blocks, and sketchable blocks include unidirectional and multi-directional blocks; unidirectional blocks use clustering based on sketch direction guidance; multi-directional blocks use Clustering based on directional distribution features; smooth blocks and texture blocks adopt grayscale clustering; multi-measurement vector observations are performed for each type of image block; when reconstructing, according to the multi-measurement matrix, category index and The direction information adopts the particle swarm algorithm based on intersection and atomic direction constraints to obtain the final reconstructed image. Compared with the TS_RS and NR_DG methods, the reconstructed image has high quality and good robustness, and can be used for the reconstruction of natural images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a non-convex compressive sensing optimization reconstruction method based on sketch representation and structured clustering, which can be used to reconstruct natural images. Background technique [0002] In recent years, a new data theory compressive sensing CS has emerged in the field of signal processing. This theory realizes compression while collecting data, breaks through the limitations of the traditional Nyquist sampling theorem, and brings new advantages to data collection technology. The revolutionary changes make the theory have broad application prospects in compressed imaging systems, military cryptography, wireless sensing and other fields. Compressed sensing theory mainly includes three aspects: sparse representation of signal, observation of signal and reconstruction of signal. Designing effective observation and reconstruction methods is an ...

AI Technical Summary

Problems solved by technology

Although this method judges the structure type and direction of the image block, it is not accurate in the case of low sampling rate, which leads to the lack of accuracy and robustness of reconstruction at low sampling rate.

[0005] At the same time, both of the above two methods have the disadvantage of slow reconstruction speed. Both of them are based on the two-stage optimization of genetic optimization algorithm and clone selection algorithm, which is slow and not conducive to real-time application.

Images