DATABASE LOGGING METHOD AND LOGGING DEVICE RELATING TO APPROXIMATE NEAREST NEIGHBOR SEARCH
The present application relates to a method whereby a plurality of characteristic vectors which are extracted from image data are logged in a database together with the image data for approximate nearest neighbor searching, and has as an objective reducing computation time and memory use. L groups of K hash tables are generated, and each characteristic vector is respectively logged with each hash table. With one group as a copy destination, another group as a copy source, and each respective division by combination of logging bin of the K hash tables of each group as a bucket: 1) a given characteristic vector is focused on
2) another characteristic vector which is logged in the same bucket in the copy source as the characteristic vector is identified
3) a characteristic vector is selected in which a number of groups in which the other characteristic vector is logged in the same bucket as the characteristic vector which is focused on is greater than or equal to a prescribed threshold
and 4) when the characteristic vector which is selected in 3) is not logged in each bin of the copy destination in which the characteristic vector being focused on is logged, the characteristic vector is logged in each bin. After focusing on a prescribed number of characteristic vectors and executing 1) - 4) foregoing for each characteristic vector, the copy source hash tables are deleted.