Single-frame image super resolution reconstruction method based on sparse domain selection

Abstract

The invention discloses a single-frame image super resolution reconstruction method based on sparse domain selection, mainly to solve the problem that the reconstruction result is poor caused when the existing reconstruction method carries out joint dictionary training. The method comprises steps: low-resolution and high-resolution image training sets are constructed according to an image set; low-resolution and high-resolution feature training sets are constructed according to the image training sets; sparse representation is carried out on the low-resolution feature training set; according to the high-resolution feature training set and a low-resolution feature coding coefficient, an iterative initial value for a high-resolution dictionary is solved; an optimization objective formula for sparse domain selection is constructed, and the high-resolution dictionary, a high-resolution feature coding coefficient and a mapping matrix are solved iteratively; and according to the inputted test image, the high-resolution dictionary, the high-resolution feature coding coefficient and the mapping matrix, a high-resolution image is reconstructed and outputted. The experimental simulation shows that the reconstruction result has higher subjective and objective quality evaluation, and can applied to medical imaging, high-definition video imaging, remote sensing monitoring, traffic and safety monitoring.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to a single-frame image super-resolution reconstruction method, which can be applied to the fields of medical imaging, high-definition video imaging, remote sensing monitoring, traffic and safety monitoring and the like. Background technique [0002] As a carrier for humans to record information about the objective world, images play an important role in human production and life. However, limited by the conditions of the imaging system equipment, imaging environment, and limited network data transmission bandwidth, the imaging process often has degraded processes such as motion blur, down-sampling, and noise pollution. low quality. For this reason, image super-resolution reconstruction technology has important theoretical and application value as an effective method to improve image resolution, restore image texture details, and improve image visual effects. [0003]...

AI Technical Summary

Problems solved by technology

However, considering that only low-resolution image information can be obtained in the reconstruction stage, the dictionary pair obtained through joint training cannot ensure the mapping relationship between the reconstructed low-resolution and high-resolution image blocks, so this assumption is limited to a certain extent. The flexibility and accuracy of this type of method for modeling the mapping relationship of complex image blocks is reflected in the edge details of the reconstructed image with certain ringing effects and artificial traces.

Images