Space target image restoration method based on convolutional auto-encoding convolutional Neural Network

Abstract

The invention discloses a space target image restoration method based on a convolutional auto-encoding convolutional neural network. The method comprises the steps of establishing degraded images withdifferent degradation degree as input data, wherein the input data is used for learning and establishing a relatively robust CAE neural network model; and establishing simulation image sets of different types and different blurring degree through utilization of the prior knowledge with limited space target quantity and known part of models, and the feature that the similarity among the models ishigh, wherein the simulation image sets are used for carrying out training in the convolutional network. The method has the advantages that the images with clear edge structures can be restored; the method has excellent turbulence blurring removing capacity; the edge contrast of the restored images is high; the anti-noise capacity is excellent; the internal structures of the restored images are displayed relatively stably and clearly; and the efficiency is relatively high.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a space object image restoration method based on convolutional self-encoding convolutional neural network. Background technique [0002] The overall idea of ​​the neural network is to define an effective target model and a loss function that can measure the pros and cons of the target model. By gradually optimizing the target model and minimizing the loss of the target model, the intrinsic relationship between the input data and the predicted data is learned, so that Neural network models accomplish various tasks. In the learning method for image restoration, it is assumed that there is a local correlation between images, on this basis, by learning the degradation model of the image and the characteristics of the degraded image, the restoration of the degraded image will be realized. Among them, there are mainly methods based on sparse representation and methods...

AI Technical Summary

Problems solved by technology

However, the method and reason for the construction of the convolutional layer are not clear in the article, and the training difficulty brought about by an overly deep network will also increase exponentially, and it is easy to bring about the learning consequences of overfitting, and for different page directions, In terms of font style and text language, the performance of neural networks is not very good

Images