The problem of matching two images of the same scene taken by different sensors under different viewing geometries is a challenging problem in the field of computer applications to image processing and pattern recognition. The scenes are usually transformed so drastically by the different viewing geometries and sensor characteristics that it is extremely difficult, if not impossible, to match the original images without the proper data processing. Geometric transformation must be performed on the images to bring the matching elements into one-to-one correspondence. Because of the difference in operating conditions and sensor characteristics, images of the same object taken by two different sensors have different intensity values. A new intensity matching technique based on the Karhunen-Loeve transformation was developed to match the intensity values of one image to those of the other as closely as possible through the use of a digital computer.
[1]
Harvey F. Silverman,et al.
A Class of Algorithms for Fast Digital Image Registration
,
1972,
IEEE Transactions on Computers.
[2]
E. Hall,et al.
Computer Classification of Pneumoconiosis from Radiographs of Coal Workers
,
1975,
IEEE Transactions on Biomedical Engineering.
[3]
Josef Kittler,et al.
A new approach to feature selection based on the Karhunen-Loeve expansion
,
1973,
Pattern Recognit..
[4]
E. Hall,et al.
Hierarchical search for image matching
,
1976,
1976 IEEE Conference on Decision and Control including the 15th Symposium on Adaptive Processes.
[5]
Joseph G. Kawamura,et al.
Automatic Recognition of Changes in Urban Development from Aerial Photographs
,
1971,
IEEE Trans. Syst. Man Cybern..
[6]
George Nagy,et al.
Digital image-processing activities in remote sensing for earth resources
,
1972
.