Multispectral infrared image classification using filters derived from independent component analysis
Abstract
Spectral-spatial independent component analysis (ICA) basis functions of visible color images are similar to some processing elements in the human visual systems in that they resemble Gabor filters and show color opponencies. In this research we studied combined spectral-spatial ICA basis functions of multispectral mid wave infrared (MWIR) images. These ICA spectral-spatial basis functions were then used as filters to extract features from multispectral MWIR images for classification. The images were captured in the 3.0-5.0 μm, 3.7-4.2 μm, and 4.0-4.5 μm bands using a multispectral MWIR camera. In the proposed algorithm, phase relationships between the basis functions indicate how the extracted features from the different spectral band images can be combined. We used classification performance to compare features obtained by filtering using multispectral ICA basis functions, multispectral principal component analysis basis functions, and Gabor filters. © 2007 Society of Photo-Optical Instrumentation Engineers.
Publication Title
Optical Engineering
Recommended Citation
Chari, S., Halford, C., Robinson, A., & Jacobs, E. (2007). Multispectral infrared image classification using filters derived from independent component analysis. Optical Engineering (11) https://doi.org/10.1117/1.2801401
