| 摘要 |
<p>Processing multispectral images to separate artificial objects from natural objects by background discriminant transformation. The processing involved identifying on the image an object of the natural, (or background class), identifying an object of the artificial class, calculating a mean vector and co-variance matrix of both areas, and calculating transformation vector for maximising the co-variance of the artificial class relative to the natural class, and applying the transformation vectors to the image to produce a transformed image.</p> |
