To generate a new ornamental image, add an image’s oil painting style information to any image while preserving the image’s semantic content. With the rapid advancement of deep learning (DL), image style transfer has become one of the most active areas of computer vision research (CV). This paper proposes an oil painting style transfer technique based on parallel convolutional neural networks to address the ineffective style transfer of locally similar regions in content images and the slow processing speed of existing methods. By incorporating Gaussian sampling and a parallelization algorithm, this method effectively transfers the style of an oil painting. The algorithm can combine the content of any image with a variety of well-known oil painting styles to create high-quality works of art. The experimental results indicate that, compared to existing methods, the proposed method can effectively reduce the style loss of the generated image, make the generated image’s overall style more uniform, and produce a more pleasing visual effect.
In recent years, the research on the non photorealistic painting of watercolor painting through computer algorithms has made rapid progress, and its specific application has also been increasingly valued. This paper proposes a new machine vision method based on genetic algorithm, and applies it to the research of oil painting style and image processing optimization. First of all, it provides a stroke layout method based on machine vision important areas. It analyzes the key areas through face, visual focus analysis and other technologies, and realizes the starting point, angle calculation, accuracy optimization and image quality optimization of pen painting based on the data of this area, thus realizing the function of distinguishing the primary and secondary of oil painting. Secondly, the machine vision method based on genetic algorithm can explore the style characteristics of any oil painting graphics according to the characteristics of oil painting, and create artistic images through this method. The experimental results show that the machine vision method based on genetic algorithm not only has achieved good results in the practical application of oil painting style, but also can optimize the image processing.
In recent years, the research on the non photorealistic painting of watercolor painting through computer algorithms has made rapid progress, and its speci c application has also been increasingly valued. This paper proposes a new machine vision method based on genetic algorithm, and applies it to the research of oil painting style and image processing optimization. First of all, it provides a stroke layout method based on machine vision important areas. It analyzes the key areas through face, visual focus analysis and other technologies, and realizes the starting point, angle calculation, accuracy optimization and image quality optimization of pen painting based on the data of this area, thus realizing the function of distinguishing the primary and secondary of oil painting. Secondly, the machine vision method based on genetic algorithm can explore the style characteristics of any oil painting graphics according to the characteristics of oil painting, and create artistic images through this method. The experimental resultsshow that the machine vision method based on genetic algorithm not only has achieved good results in the practical application of oil painting style, but also can optimize the image processing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.