An Unsupervised Colorization Method of Thermal Infrared Image Based on Edge Consistency

Jiaming Cai, Xin Tang, Yao Hu*, Shaohui Zhang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Due to the lack of pixel level structural matching data, thermal infrared grayscale images are more difficult to color than visible and near-infrared grayscale images. Therefore, this paper proposes a unsupervised learning method based on CycleGAN. On the basis of CycleGAN, a pre trained edge monitor is introduced to calculate the edge feature map before and after image transformation, and the edge similarity loss function is calculated as the basis for optimizing the neural network parameters. The experimental results show that the proposed method effectively reduces the loss of effective edge information during the coloring process and suppresses the generation of abnormal edge information during the coloring process.

源语言英语
主期刊名Third International Conference on Advanced Algorithms and Neural Networks, AANN 2023
编辑Pavel Loskot, Xiaofeng Ding
出版商SPIE
ISBN(电子版)9781510668355
DOI
出版状态已出版 - 2023
活动3rd International Conference on Advanced Algorithms and Neural Networks, AANN 2023 - Qingdao, 中国
期限: 5 5月 20237 5月 2023

出版系列

姓名Proceedings of SPIE - The International Society for Optical Engineering
12791
ISSN(印刷版)0277-786X
ISSN(电子版)1996-756X

会议

会议3rd International Conference on Advanced Algorithms and Neural Networks, AANN 2023
国家/地区中国
Qingdao
时期5/05/237/05/23

指纹

探究 'An Unsupervised Colorization Method of Thermal Infrared Image Based on Edge Consistency' 的科研主题。它们共同构成独一无二的指纹。

引用此