Abstract: An image processing method is used to detect a letter by using a classifier generated through statistical learning of handling a sample image of a fixed size as supervised data, and includes the following steps. A conversion step acquires a converted image by geometrically converting a target image containing a letter to be detected such that the target image has a predetermined ratio defining an aspect ratio. A search step searches the converted image for one or more letter candidates each including a region of a possible letter by using the classifier. An integration step applies clustering to the letter candidates, integrating the letter candidates, and eliminates the letter candidate having low reliability A circumscribing step cuts a letter out of the letter candidate that has been integrated and has not been eliminated, and generates a rectangle circumscribing the letter.

Abstract: A face collation apparatus has a storage that stores a feature quantity of at least one registrant, the feature quantity being extracted from a registration image of the registrant, a feature quantity extractor that extracts a feature quantity from a collation image of a collation object person, a score calculator that calculates a score indicating an analogy degree between the feature quantity of the registrant and the feature quantity of the collation object person, a score adjuster that adjusts the score using a score adjustment parameter so that any one of a stranger acceptance rate indicating a probability that a stranger is accepted at the time of collation, a principal rejection rate indicating a probability that a principal is rejected at the time of collation, and an equal error rate, which is a probability that the stranger acceptance rate and the principal rejection rate are equal, becomes substantially constant regardless of a registration condition and/or a collation condition, and a determinatio