Single image super-resolution reconstruction method based on depth component learning network

Abstract

The invention discloses a single image super-resolution reconstruction method based on a depth component learning network, which comprises the following steps: expanding a training sample image and carrying out region extraction and degradation operations to obtain corresponding high-resolution and low-resolution image training sets; a deep network with component learning structure being constructed. The network decomposes the input low-resolution image into global components, and then predicts the corresponding image in high-resolution space using the residual components extracted from the global components. Batch random gradient descent method and back propagation algorithm are used to train the constructed deep component network iteratively on the training set, and the model with optimized weights is obtained. Reconstruction of Low Resolution Images Using the Trained Component Networks; the reconstruction result is restored to the original color space, and the final output of the super-resolution reconstruction is obtained. The method of the invention not only can improve the quality of the reconstructed super-resolution image, but also can improve the operation speed of the model.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a single image super-resolution reconstruction method based on a deep component learning network. Background technique [0002] The spatial resolution of a digital image is an important index to measure the image quality. The higher the resolution of the image, the clearer the image and the stronger the ability to present details. However, in practice, due to the low physical resolution of the imaging system, too far away from the target, or the harsh shooting environment, the quality of the collected images is often poor, and it is difficult to obtain the required detailed features from the images, which will greatly improve the quality of the images for subsequent image processing, Analysis creates additional difficulties against accurately understanding the objective information contained in the image. [0003] In order to solve the above problems, the most direct method is to ...

AI Technical Summary

Problems solved by technology

It is a pity that high-definition camera equipment is complex and expensive, so it is difficult to upgrade existing equipment on a large scale in a short period of time

Moreover, the capability limit of camera equipment is also restricted by the current sensor manufacturing process and objective optical diffraction law.

At the same time, in some occasions where the imaging environment is harsh, it is difficult to obtain satisfactory images even with high-quality imaging equipment.

Images