TY - JOUR
T1 - Neural Network-Based Mapping Mining of Image Style Transfer in Big Data Systems
AU - Li, Hong An
AU - Zheng, Qiaoxue
AU - Qi, Xin
AU - Yan, Wenjing
AU - Wen, Zheng
AU - Li, Na
AU - Tang, Chu
N1 - Publisher Copyright:
© 2021 Hong-an Li et al.
PY - 2021
Y1 - 2021
N2 - Image style transfer can realize the mutual transfer between different styles of images and is an essential application for big data systems. The use of neural network-based image data mining technology can effectively mine the useful information in the image and improve the utilization rate of information. However, when using the deep learning method to transform the image style, the content information is often lost. To address this problem, this paper introduces L1 loss on the basis of the VGG-19 network to reduce the difference between image style and content and adds perceptual loss to calculate the semantic information of the feature map to improve the model's perceptual ability. Experiments show that the proposal in this paper improves the ability of style transfer, while maintaining image content information. The stylization of the improved model can better meet people's requirements for stylization, and the evaluation indexes of structural similarity, cosine similarity, and mutual information value have increased by 0.323%, 0.094%, and 3.591%, respectively.
AB - Image style transfer can realize the mutual transfer between different styles of images and is an essential application for big data systems. The use of neural network-based image data mining technology can effectively mine the useful information in the image and improve the utilization rate of information. However, when using the deep learning method to transform the image style, the content information is often lost. To address this problem, this paper introduces L1 loss on the basis of the VGG-19 network to reduce the difference between image style and content and adds perceptual loss to calculate the semantic information of the feature map to improve the model's perceptual ability. Experiments show that the proposal in this paper improves the ability of style transfer, while maintaining image content information. The stylization of the improved model can better meet people's requirements for stylization, and the evaluation indexes of structural similarity, cosine similarity, and mutual information value have increased by 0.323%, 0.094%, and 3.591%, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85114608483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114608483&partnerID=8YFLogxK
U2 - 10.1155/2021/8387382
DO - 10.1155/2021/8387382
M3 - Article
C2 - 34475949
AN - SCOPUS:85114608483
SN - 1687-5265
VL - 2021
JO - Computational Intelligence and Neuroscience
JF - Computational Intelligence and Neuroscience
M1 - 8387382
ER -