multispectral images

Development of an artificial neural network with oscillatory neurons for recognition of spectral images

This paper shows a new type of artificial neural network with dynamic oscillatory neurons that have natural frequencies. Artificial neural network in the mode of information resonance implements a new method of recognition of multispectral images. The constructed neural network will recognize the input spectral images with the amplitude of the non-stationary signal commensurate with the amplitude of the noise signal, due to the resonance effect in nonlinear oscillatory neurons.

Improving the Resolution of Multispectral Images by Subpixel Processing Method

The methods, their advantages and disadvantages, of fusion a low-resolution multispectral and panchromatic high-resolution image in high-resolution color image are considered. Is proposed a method to provide high-resolution, which is based on the use of sub-pixel processing, the essence of which is the handling of input data in the form of a CCD sensor arrays shifted by a half pixel with respect to each other.