Title :
A retina based multi-resolution image-fusion
Author :
Ghassemian, Hassan
Author_Institution :
Dept. of Electr. Eng., Tarbiat Modares Univ., Tehran, Iran
Abstract :
Multiresolution images can be merged more efficiently, by taking into account the multiscale properties of the human vision system. To achieve this goal it is necessary to build a multiscale fusion model, based on the retinal cell photoreceptors. This paper introduces a general issue of this model, and the new application of the model in multispectral image fusion. The proposed method is compared with the HSI, PCA, Brovey, and wavelet, methods. Results show it preserves more spectral features with less spatial distortion
Keywords :
geophysical signal processing; geophysical techniques; image processing; image resolution; multidimensional signal processing; sensor fusion; terrain mapping; geophysical measurement technique; image processing; land surface; merged; multi-resolution image fusion; multiresolution image; multiresolution method; multiscale fusion model; multiscale properties; multispectral image fusion; multispectral remote sensing; optical imaging; retina method; retinal cell photoreceptors; sensor fusion; spatial distortion; spectral features; terrain mapping; Humans; Image fusion; Image resolution; Machine vision; Multiresolution analysis; Multispectral imaging; Principal component analysis; Retina; Signal resolution; Spatial resolution;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-7031-7
DOI :
10.1109/IGARSS.2001.976610
