Super-resolution reconstruction method

Abstract

The invention provides a super-resolution reconstruction method. The method comprises the following steps: establishing a picture data set; constructing a neural network structure, wherein the neuralnetwork structure is used for extracting features of the picture data set in a neural network training process; establishing a loss function of a neural network structure, wherein the loss function isused for guiding neural network training; training the picture data set to obtain a neural network model; and reconstructing a picture by using the neural network model, inputting a low-resolution picture, and outputting a high-resolution picture. According to the technical scheme of the present invention, the SRGAN (Super-Resolution Generation Advanced Network) is improved, so that the SRGAN (Super-Resolution Generation Advanced Network) is improved; according to the super-resolution reconstruction method, the network structure of the generation network G-NET is changed, the loss function isimproved, and after improvement, the generation network G-NET extracts more accurate features, so that the super-resolution reconstruction effect is better, and a better effect can be obtained duringdetection, recognition and semantic segmentation.

Description

【Technical field】 [0001] The invention relates to the technical field of image processing, in particular to a super-resolution reconstruction method. 【Background technique】 [0002] Super-resolution (Super-Resolution) is to improve the resolution of the original image through hardware or software. The process of obtaining a high-resolution image through a series of low-resolution images is super-resolution reconstruction. High resolution means a high density of pixels in an image, providing more detail that is essential in many practical applications. [0003] The current super-resolution reconstruction methods include three types: interpolation-based, reconstruction-based, and learning-based methods, and the interpolation-based method is the most classic, including the nearest neighbor interpolation method and cubic spline interpolation method. The reconstruction effect is excellent. Oscillating and jagged over-smoothed images; the performance of reconstruction-based metho...

AI Technical Summary

Problems solved by technology

[0003] The current super-resolution reconstruction methods include three types: interpolation-based, reconstruction-based, and learning-based methods, and the interpolation-based method is the most classic, including the nearest neighbor interpolation method and cubic spline interpolation method. The reconstruction effect is excellent. Oscillating and jagged over-smoothed images; the performance of reconstruction-based methods relies heavily on the prior knowledge of high-resolution images applied, which can easily lead to over-smoothing and loss of important high-frequency details; learning-based methods are based on machine learning theory , especially deep learning, some methods have emerged in recent years, the more representative ones are SRCNN (Super-Resolution Convolutional Neural Network), SRGAN (Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network), etc. Although these methods are in certain To a certain extent, it makes up for the defects of the other two types of methods, and improves the clarity of the image in terms of visual perception, but in terms of details, it is impossible to control the appearance of some redundant lines.

Images