Method for removing Poisson noise in mage based on non-local similarity low rank matrix

Abstract

The invention discloses a method for removing Poisson noise in mage based on non-local similarity low rank matrix. The method comprises (1) carrying out a noise analysis according to a joint probability density function and a maximum likelihood principle of Poisson distribution, deriving that the removal of the Poisson noise is equivalent to the minimization of the KL divergence function, and thenusing the prior knowledge of the image non-local similarity block as a regular term to solve a stability number; (2)establishing a model, i.e., according to the noise analysis and a posterior probability formulas, obtaining a Poisson low rank noise removing model (the model is as shown in the specification); (3) carrying out a noise removing process, i.e., according to the Poisson low rank noiseremoving model, by optimizing a knowledge, obtaining respectively a iterative formulas for solving F j and f, then obtaining the final solution through the alternating iterative method; (4) outputtinga noise removed image. According to a image non-local similarity, a low rank matrix noise removing model is established, the image noise is effectively removed, and meanwhile the detail information such as the structure, texture, and edges of the image is kept as far as possible by using the rank minimization method, and a better visual effect is obtained.

Description

technical field [0001] The invention belongs to the field of image denoising, in particular to a method for removing Poisson noise from an image based on a non-local similarity low-rank matrix. Background technique [0002] Photon noise is caused by the statistical nature of light and the photoelectric conversion process in image sensors, and is commonly found in images generated by magnetic resonance imaging systems, electron microscopy imaging systems, and astronomical imaging systems. From the statistical point of view, the signal is closely related to the noise, the higher the signal strength, the greater the noise. Since the photon noise obeys the Poisson distribution, the problem of eliminating photon noise can be transformed into the problem of noise removal obeying the Poisson distribution, which will provide convenience for research in the fields of medical treatment, biology, and astronomy. [0003] Image denoising is a basic topic of image processing and computer...

AI Technical Summary

Problems solved by technology

However, the above methods use different emphases to build models and construct algorithms. While removing noise, they lose details such as image structure, texture, and edges to varying degrees.

Images