Image processing method, image processing device and storage medium

Abstract

The invention relates to an image processing method, an image processing device and a storage medium, the image processing method is applied to electronic equipment, an image collection device is installed in the electronic equipment, the image processing method comprises the steps that an original image collected by the image collection device is collected, and the original image is an image whose pixel position has aberration; and inputting the original image into a deep convolutional neural network model to obtain a processed image, the deep convolutional neural network being obtained by aberration function training based on an image collection device. According to the embodiment of the invention, the aberration function is determined by the image collection device with the same attribute as the image collection device through a measurement means; a deep convolutional neural network is trained based on the obtained aberration function, and the trained deep convolutional neural network is used to remove the phase difference of the images with the phase difference collected by the image collection device so as to improve the image processing quality.

Description

technical field [0001] The present disclosure relates to the field of image processing, and in particular, to an image processing method, an image processing device, and a storage medium. Background technique [0002] With the rapid development of smart terminal technology, smart terminals are becoming more and more popular in people's work and life. In order to better meet the needs of users, their performance in various aspects is also getting higher and higher. The user uses the terminal to shoot anytime and anywhere, which brings great convenience to the user. Therefore, one aspect of performance that has attracted much attention is the shooting performance of the terminal. [0003] The shooting performance of the terminal is more intuitively reflected in the quality of the captured images. The larger the sensor size of the terminal, the more light received by the pixels per unit area of ​​the picture taken, and the better the image quality. The aperture of the camera ...

AI Technical Summary

Problems solved by technology

[0004] In order to pursue superior image quality, the size and aperture of the image sensor configured by the terminal are becoming larger and larger. At the same time, the optical aberration of the terminal with a large image sensor and a large aperture will cause blurred images and poor shooting effects. Poor, affecting user experience

Images