| 摘要 |
<p><P>PROBLEM TO BE SOLVED: To provide a method and device for performing various kinds of spatial conversion processing such as image deformation, linear spatial filtering, and luminance distribution correction, without increasing parameters or the processing load. <P>SOLUTION: An image processing apparatus classifies variations from a specific state of a target object in an image into a plurality of kinds of attributes and holds, per attribute of the variations, correction parameters for spatial conversion processing of correcting the target object into the specific state. The image processing apparatus vectorizes at least a partial region of the input image to generate an input image vector and, on the basis of the input image, detects a variation from the specific state of the target object in the input image to determine an attribute of the variation. Then the image processing apparatus uses a correction parameter selected from the correction parameters held per attribute of variations, on the basis of the determined attribute of the variation to generate a converted image vector by subjecting the input image vector to spatial conversion processing. <P>COPYRIGHT: (C)2011,JPO&INPIT</p> |
