WSEAS Transactions on Signal Processing
Print ISSN: 1790-5052, E-ISSN: 2224-3488
Volume 21, 2025
Style Transfer Algorithm of Traditional Paper-cut Images based on Convolutional Neural Network: Taking Jiaxian Paper-cut as an Example
Author:
Search Articles
Abstract: The paper-cutting style migration algorithm based on a convolutional neural network retains the characteristics of traditional paper cutting and realizes fast and accurate migration. The algorithm selects the content image as the initial, uses the small convolutional neural network to quickly extract features, introduces a new absolute error loss function to improve the image smoothness, and uses the adaptive Adam optimization algorithm to prevent the gradient problem. The experiment proves that the proposed algorithm can obtain the ideal paper-cutting style migration effect.
Keywords:
Convolutional neural network, Traditional Paper Cuttings, Style transfer, Image features, Absolute error loss function, Adam optimization, Migration algorithm, Jiaxian Paper Cuttings, Artistic style transformation, Deep Learning
Pages: 112-121
DOI: 10.37394/232014.2025.21.13