Tone Image Classification and Weighted Learning for Visible and NIR Image Fusion

• Published in: Entropy (Basel, Switzerland) Vol. 24; no. 10; p. 1435
• Main Authors: Im, Chan-Gi, Son, Dong-Min, Kwon, Hyuk-Ju, Lee, Sung-Hak
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 09.10.2022; MDPI
• Subjects: Algorithms; Artificial neural networks; Comparative analysis; Computer vision; Datasets; Decomposition; Deep learning; Feature maps; Image classification; image fusion; Image processing; Image quality; infrared image; Infrared imagery; Machine learning; Methods; Near infrared radiation; Neural networks; Performance evaluation; Raster scanning; supervised learning; Synthesis; Visibility; visible image; infrared image; deep learning; image fusion; supervised learning; visible image
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e24101435

In this paper, to improve the slow processing speed of the rule-based visible and NIR (near-infrared) image synthesis method, we present a fast image fusion method using DenseFuse, one of the CNN (convolutional neural network)-based image synthesis methods. The proposed method applies a raster scan algorithm to secure visible and NIR datasets for effective learning and presents a dataset classification method using luminance and variance. Additionally, in this paper, a method for synthesizing a feature map in a fusion layer is presented and compared with the method for synthesizing a feature map in other fusion layers. The proposed method learns the superior image quality of the rule-based image synthesis method and shows a clear synthesized image with better visibility than other existing learning-based image synthesis methods. Compared with the rule-based image synthesis method used as the target image, the proposed method has an advantage in processing speed by reducing the processing time to three times or more.