An image recovery method

Abstract

The invention provides a method for image restoration, which is used to restore a known degradation image of a degradation model. The process method of the invention is processing the degradation image to be processed with three-dimensional cell neural network image processing method, and the output is just the restored image. The method is simple and easy, and is suitable for being used in restoring a known degradation image of a degradation model. The method can have a very high processing speed when adopting a cellular neural network chip to realize the algorithm.

Description

technical field [0001] The invention relates to a method for restoring a degraded image with a known degraded model based on a cellular neural network. Background technique [0002] In the imaging system, due to factors such as poor focus and relative motion, noise and interference are inevitably added to the actual image, resulting in image degradation. In the case of severe degradation, further applications on the image, such as feature extraction, automatic recognition and image analysis, are quite detrimental. Therefore, the restoration of degraded images has very important practical significance in many fields such as military affairs and remote sensing. [0003] The image dedefinition degradation model can be described in matrix-vector form as: [0004] g=Hf+n (1) [0005] Among them, g, f, and n are stacked matrices of observed image, original image, and noise, respectively. H is a circular matrix generated by the desharp function as a convolution kernel. The cor...

AI Technical Summary

Problems solved by technology

Although the inversion of large-size matrices is avoided, their basic idea is still based on matrix operations, and the amount of calculation is very large

In addition to the regularization method, another commonly used image restoration method based on random and statistical process analysis also has the disadvantage of large amount of calculation.

In order to improve the calculation speed, Zhou et al. proposed an image restoration method based on neural network, but the hardware implementation of neural network is not easy

Therefore, it is very difficult to achieve real-time image restoration

Images