Image style processing method and device based on artificial intelligence and electronic equipment

Abstract

The invention provides an image style processing method and device based on artificial intelligence, equipment and a computer readable storage medium. The method comprises the following steps: performing style transformation processing on a first image sample through a style generation network to obtain a second image sample; obtaining a corresponding style classification loss function when the second image sample is subjected to style classification and a corresponding content classification loss function when the second image sample is subjected to content classification; training the style generation network according to the style classification loss function and the content classification loss function; and performing style transformation processing on the first image through the trained style generation network to obtain a second image. According to the method and device, accurate image style migration can be achieved.

Description

technical field [0001] The present application relates to artificial intelligence technology, and in particular to an image style processing method, device, electronic equipment and computer-readable storage medium based on artificial intelligence. Background technique [0002] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. [0003] With the development of deep learning, image recognition technology is applied to more and more fields and products. For the field of image style transformation, when the confrontation generation network is applied to the field of image style transformation, only rely on the discriminant network to supervise the generation network for training. The resulting generative network cannot meet the needs of...

AI Technical Summary

Problems solved by technology

[0003] With the development of deep learning, image recognition technology is applied to more and more fields and products. For the field of image style transformation, when the confrontation generation network is applied to the field of image style transformation, only rely on the discriminant network to supervise the generation network for training. The resulting generative network cannot meet the needs of diverse image style transfer, for example, individual users have diverse handwritten images, etc., and the generative network trained based on the discriminant network supervised generative network cannot achieve image style transformation as expected

Images