A comparative study on fusion of visible and infrared images

摘要

In this paper, principal component analysis (PCA), laplacian pyramid (LP), discrete wavelet transform (DWT), non-subsampled contourlet transform (NSCT), Bayesian PCA (BPCA), and non-negative matrix factorization (NMF) methods are compared in order to obtain a single informative image from visible and thermal images. The quality of the fused images obtained in the experimental studies is evaluated using five different quality metrics.