摘要 |
A feature-amount extracting unit extracts a first feature amount of information to be registered, from the information. A searching unit searches for a second feature amount of information from a feature-amount storing unit. A similarity calculating unit calculates a similarity between the first feature amount and the second feature amount. A registering unit registers the first information in association with a similarity-information list in a similarity-information-list storing unit, which includes the second information corresponding to the second feature amount of which the calculated similarity is larger than a threshold, as similarity information.
|