An efficient super-resolution reconstruction method based on deep learning

Abstract

The present invention relates to the fields of image processing and computer vision, and relates to convolutional neural network image super-resolution reconstruction related technologies. Specifically, it provides a high-efficiency super-resolution reconstruction method based on deep learning. On the basis of the relatively simple and efficient FSRCNN network structure, the nearest neighbor interpolation algorithm, residual connection, dense connection and transfer learning are added to form a new network structure-LuNet structure, and the LuNet structure is combined with the existing common super-resolution algorithm (Bicubic, SCN, SRCNN, FSRCNN) carry out experimental tests on the performance, and the test structure shows that the LuNet structure formed by the present invention has higher reconstruction quality and its performance is more perfect under the condition that the model parameters remain unchanged. .

Description

technical field [0001] The present invention relates to the fields of image processing and computer vision, and relates to technologies related to convolutional neural network image super-resolution reconstruction, specifically an efficient super-resolution reconstruction method based on deep learning. Background technique [0002] Image super-resolution reconstruction, also known as image enlargement, aims to enlarge the low-resolution image input by the user while improving the clarity of the image. After the image super-resolution reconstruction process, the low-resolution image becomes clearer. Traditional super-resolution image reconstruction methods use interpolation methods such as linear interpolation, bilinear interpolation, and nearest neighbor interpolation. This processing effect is fast, but it can blur high-frequency details in the picture and cause serious distortion. [0003] With the development of convolutional neural network (CNN), a large number of conv...

AI Technical Summary

Problems solved by technology

Although this processing effect is fast, it will cause blurred high-frequency details in the picture, causing severe distortion

[0003] With the development of convolutional neural network (CNN), a large number of convolutional neural networks are used in the field of super-resolution reconstruction. CNN with complex structure can complete the reconstruction process through feature extraction and mapping of multiple modules, although it will form real detailed information. , but due to the complexity of the network, it is difficult to achieve real-time and fast super-resolution reconstruction

The CNN with a simple structure can complete the feature extraction and reconstruction process through a relatively rough module structure. Although it has high real-time performance, it will lack relatively complete high-frequency details.

Images