Partitioning compressive sensing reconstruction method based on image block clustering and sparse dictionary learning

Abstract

The invention discloses a partitioning compressive sensing reconstruction method based on image block clustering and sparse dictionary learning, and belongs to the technical field of image processing. The method comprises the following steps that an image is read in, and is divided into sub-image blocks; compressive sampling is carried out on the sub-image blocks to achieve measurement; edge images in (K-1) directions are generated, PCA transformation is carried out on the edge images to generate (K-1) PCA bases, and then, a DCT base is taken for forming a union dictionary of K initial direction bases; the typical correlation coefficients between the measurement and the direction bases are calculated, and the sub-images are clustered to form K classes; the sub-image blocks in the K classes are reconstructed through a multivariable tracking algorithm; the reconstructed sub-image blocks are used for updating the K direction bases; whether the maximum number of times of iteration reconstruction is reached or not is judged; the reconstructed sub-image blocks are spliced together to obtain a reconstructed image of the original image; the image is output. According to the partitioning compressive sensing reconstruction method based on image block clustering and sparse dictionary learning, the blocking effect in the reconstructed image can be obviously weakened or removed in two reconstruction modes, and the method has a reconstruction effect on a natural image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image block compression sensing reconstruction method, which can be used to reconstruct natural images. Background technique [0002] Compressive Sensing (CS) is a brand-new signal sampling theory formally proposed by American scholars Cand?s and Donoho in 2006, such as: Donoho D L. Compressed sensing. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306; Cand?s E. Near optimal signal recovery from random projections: Universal encoding strategies? IEEE Transactions on Information Theory, 2006, 52(12): 5406-525. The traditional Nyquist sampling theory first samples the signal at a high rate, and then compresses the data; while CS synchronizes the sampling and compression process, and directly perceives the signal in a compressed form. The measurements obtained by CS are a set of linear projections of the original signal onto a low-dimensional s...

AI Technical Summary

Problems solved by technology

The advantage of this method is that it is fast and takes up less memory; the disadvantages are: (1) Using a fixed sparse dictionary cannot flexibly describe the different features in the image block, such as edges, textures, e

Images