Edge-based deep learning image motion blur removing method

Abstract

The invention relates to an image restoration technology, in particular to an edge-based deep learning image motion blur removing method, which comprises the following steps of: extracting an edge from a blur image by using a trained HED network, and then extracting edge feature information for guiding a motion blur removing process by using a convolution layer; extracting multi-scale feature information from the blurred image by a deblurring backbone network, integrating image features and edge features on each scale by using a spatial feature transformation layer, and a decoding part gradually recovering a potential clear image from the deepest image features; taking the blurred-clear image pair as a training sample set, defining a total loss function by the sum of a mean square error loss function and a perception loss function, and training the deblurred backbone network by using the total loss function until the deblurred backbone network is converged to the optimal precision; andinputting the motion blurred image into the trained deblurred backbone network to obtain a deblurred result. According to the method, effective integration of image features and edge features is realized, and the deblurring effect is remarkable.

Description

technical field [0001] The invention belongs to the technical field of image restoration, and in particular relates to an edge-based deep learning image de-blurring method. Background technique [0002] During the photographing process, relative motion between the imaging device and the scene objects will cause motion blur, and the image obtained at this time loses important details. The process of recovering a potentially sharp image from a degraded blurred image is called deblurring. De-blurring can restore clear edges from blurred images caused by camera shake, vehicles passing by in the scene, etc., which can not only improve the quality of visual perception, but also help subsequent text recognition, target detection, etc. Hierarchical applications, so motion blur removal has high research value and application prospects. [0003] Existing image deblurring algorithms can be generally divided into traditional deblurring methods based on energy optimization and deblurri...

AI Technical Summary

Problems solved by technology

The subsequent end-to-end deblurring network framework learns a mapping from blurred images to clear images. Compared with traditional energy optimization methods, the existing non-uniform deblurring methods based on deep learning are more effective in model building, model solving and deblurring effects. Great progress has been made on the image, but there is still a problem of insufficient deblurring at the edge of the image

Images