Application of image processing technology combined with the CNN algorithm to improve the quality of the artwork Online publication date: Wed, 11-Jan-2023
by Yu Zhou
International Journal of Computing Science and Mathematics (IJCSM), Vol. 16, No. 3, 2022
Abstract: Deep learning algorithms have made great achievements in the fields of voice, image, text, and so on. Aiming at the current situation of image quality improvement, this study proposes an image quality improvement method for artworks integrated with a convolutional neural network (CNN). In this method, the images of ink painting artworks are generated by CNN, the image information and texture are extracted by a vgg-19 convolution neural network structure, and the images are transformed through red, green, blue (RGB) and hue, saturation, value (HSV) colour space. Under the ratio of three kinds of parameters, the accuracy of the VGg grid is improved compared with that of the illustration grid, and when the ratio of style picture influence factor to content picture influence factor is 5, the accuracy is improved the fastest, and the accuracy is nearly 20%. This research will be of great significance in the field of computer-generated high-quality ink painting art images in the future.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computing Science and Mathematics (IJCSM):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook