Title :
Kernel image similarity criterion
Author :
Talens, Vicent ; Moreno, José ; Camps-Valls, Gustavo
Author_Institution :
Image Process. Lab. (IPL), Univ. de Valencia, Valencia, Spain
Abstract :
This paper presents a family of metrics for assessing image similarity. The methods use the Hilbert-Schmidt Independence Criterion (HSIC) to estimate nonlinear statistical dependence between multidimensional images. The proposed methods have very good theoretical and practical properties. We illustrate the performance in evaluating the quality of natural photographic images, hyperspectral images under different noise levels, in synthetic multiresolution problems, and real pansharpening products.
Keywords :
estimation theory; geophysical image processing; image resolution; remote sensing; spectral analysis; Hilbert-Schmidt independence criterion; hyperspectral images; kernel image similarity criterion; multidimensional images; natural photographic image quality evaluation; nonlinear statistical dependence estimation; pansharpening product; synthetic multiresolution problem; Distortion measurement; Gray-scale; Kernel; Remote sensing; Spatial resolution; Hilbert-Schmidt Independence Criterion (HSIC); Kernel methods; dependence estimation; learning; pansharpening;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4577-1003-2
DOI :
10.1109/IGARSS.2011.6049181
