An image strip noise suppression method based on wavelet decomposition convolutional neural network

Abstract

The invention relates to an image stripe noise suppression method based on a wavelet decomposition convolutional neural network, and the method comprises the steps: carrying out the wavelet transformation of a noise image, and obtaining a wavelet coefficient; constructing a stripe noise suppression convolutional neural network; inputting the wavelet coefficient into a stripe noise suppression convolutional neural network to obtain a denoising coefficient; And calculating according to the wavelet coefficient and the denoising coefficient to obtain an image after noise suppression. According tothe image stripe noise suppression method based on the wavelet decomposition convolutional neural network provided by the invention, the specific response of the stripe noise in a wavelet domain is utilized; the feature extraction capability of the convolutional neural network is combined; Compared with an existing stripe noise suppression method, the method has the advantages that the stripe noise in the image can be effectively removed, detail information of the image is protected in the denoising process, the structural similarity of the denoised ground image is higher, the visual effect ismore sharp, stripe noise residues in the denoised image are fewer, and the detail information is more abundant.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to an image band noise suppression method based on a wavelet decomposition convolutional neural network. Background technique [0002] In remote sensing imaging, medical diagnosis and military fields, due to the process characteristics and thermal characteristics of the sensor and optical system, the acquired image is polluted by fixed band noise, which affects the further processing of the image. Therefore, it is necessary to suppress the band noise in the image and eliminate the influence of external factors on the imaging quality. [0003] The current image stripe noise suppression methods mainly include methods based on calibration and methods based on prior optimization. Calibration-based methods include two-point method, multi-point method, etc. Since the response of the sensor actually drifts slowly with time and temperature, it is necessary to p...

AI Technical Summary

Problems solved by technology

Calibration-based methods include two-point method, multi-point method, etc. Since the response of the sensor actually drifts slowly with time and temperature, it is necessary to periodically re-calibrate the detector, thereby disturbing the normal operation of the detector. Work

However, based on prior optimization methods such as total variation method and non-local average filtering method, the residual information and prior information in the image can be effectively suppressed, but when the image is disturbed by strong noise, the The noise suppression effect of the method will be seriously degraded

Images