摘要 |
<P>PROBLEM TO BE SOLVED: To improve image quality by learning in units smaller than pixels. Ž<P>SOLUTION: This learning device is provided with: a prediction tap extraction part for extracting a plurality of pixels included in a first image, that is, a plurality of pixels corresponding to pixel positions near a pixel of interest in a second image whose quality is higher than that of the first image as a prediction tap; and a learning part for learning prediction coefficients to be used for predicting the pixel value of the pixel of interest from the pixel value of the prediction tap so that an error between a detail image generated according to the first image, that is, a detail image whose pixel density is higher than that of the second image and a given detail teacher image can be minimized. Ž<P>COPYRIGHT: (C)2010,JPO&INPIT Ž
|