Image super-resolution reconstruction method based on local regression model

Abstract

The invention discloses an image super-resolution reconstruction method based on a local regression model. The method comprises the following steps: at first, carrying out Gaussian low pass filtering on an input low resolution image to obtain a low frequency band image thereof, carrying out bicubic interpolation to obtain an approximate low frequency band image of a high resolution image; then, applying a one-order regression model to each image block in the low frequency band image of the high resolution image during reconstruction, wherein a mapping function between high / low images in the regression model can be obtained by a machine learning method of an input image, namely, sampling corresponding positions of the input low resolution image and the low frequency band image thereof to obtain sampling image blocks of corresponding positions, and carrying out dictionary training; and finally, respectively applying the one-order regression model to non-local self-similar blocks of the reconstructed image blocks, and carrying out weighted integration to obtain reconstructed high resolution image blocks. By adopting the method provided by the invention, no external image model is required, a prior model is obtained by learning the input image, and the high resolution image reconstructed by the model has better subjective and objective reconstruction effects.

Description

Technical field [0001] The present invention relates to the technical field of image super-resolution reconstruction, in particular to an image super-resolution reconstruction method based on a local regression model. Background technique [0002] Most digital imaging applications require high-resolution images for analysis and processing. Image resolution describes the image details, so higher resolution images have more details. The most direct way to obtain high-resolution images is to use a camera with a better prism and optical processor. However, due to physical reasons, this method has limitations and sometimes even impossible to achieve, and it often requires the need to reacquire existing images. Increase the resolution. Therefore, the practical method is to do super-resolution image reconstruction based on signal processing and machine learning. Super-resolution image reconstruction intends to break through the limitations of image acquisition to enhance the resoluti...

AI Technical Summary

Problems solved by technology

[0005] At present, most of these image super-resolution reconstruction methods that use the self-similarity of local image structure require additional training samples as the prior model for reconstruction, and the local image structure in the training sample and the local image structure of the image to be reconstructed have a great impact on the reconstruction quality. The impact of some super-resolution reconstruction methods is too complex, and the computational complexity is too high

Images