| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a method and apparatus for acquiring descriptive information of a plurality of images and an image matching method. <P>SOLUTION: The method includes performing a feature point detection with respect to each image of the plurality of images so as to obtain a plurality of feature points of each image, and acquiring 0-level descriptive information of the plurality of images. The 0-level descriptive information of each image is generated in accordance with a plurality of first local feature descriptors for the image, obtained on the basis of the plurality of feature points of the image, and a plurality of first visual words, obtained on the basis of the plurality of first local feature descriptors for the plurality of images. For each image, a division of the image is performed n-1 times, so as to obtain a plurality of (n-1)-level sub-images; and (n-1)-level descriptive information is generated in accordance with a plurality of n-th local feature descriptors, obtained on the basis of the plurality of feature points and (n-1)-level sub-images where the respective feature points lie, and a plurality of n-th visual words, obtained on the basis of the plurality of n-th local feature descriptors, where n=2, 3, ..., K+1, and K is a positive integer. <P>COPYRIGHT: (C)2013,JPO&INPIT |
