Color image restoration using synthetic method
暂无分享,去创建一个
Abstract A color image restoration method is developed. The Fourier spectrum of a restored image is synthesized from the Fourier spectra of three primary color bands of a given degraded image. The synthesizing weights depend upon the evaluation of the final restored image. Two examples, the weights which minimize the mean square error and the weights which are expressed as the weighted mean proportional to the magnitude of the power spectra, are shown. This restoration method is shown to be effective especially when three primary color images strongly correlate to each other.
[1] J Bescos,et al. Digital restoration models for color imaging. , 1988, Applied optics.
[2] Toshio Honda,et al. Least-squares filter for color-image restoration , 1988 .
[3] B. R. Hunt,et al. Karhunen-Loeve multispectral image restoration, part I: Theory , 1984 .
[4] Jumpei Tsujiuchi,et al. Compensation of motion blur in CCD color endoscope images. , 1987, Applied optics.
[5] G. J. Burton,et al. Color and spatial structure in natural scenes. , 1987, Applied optics.