A New Deep Learning Based Multi-Spectral Image Fusion Method

• Published in: Entropy (Basel, Switzerland) Vol. 21; no. 6; p. 570
• Main Authors: Piao, Jingchun, Chen, Yunfan, Shin, Hyunchul
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 05.06.2019; MDPI
• Subjects: Algorithms; Artificial neural networks; Classification; Computer vision; convolutional neural network; Decomposition; Deep learning; Design; Image classification; image fusion; Image processing; infrared; Machine learning; Methods; Neural networks; Principal components analysis; Quality assessment; Radiation; Siamese network; Training; visible; Visual perception; Wavelet transforms

In this paper, we present a new effective infrared (IR) and visible (VIS) image fusion method by using a deep neural network. In our method, a Siamese convolutional neural network (CNN) is applied to automatically generate a weight map which represents the saliency of each pixel for a pair of source...