Abstract In a fingerprint scanning device for use in identification, a fingerprint image input device is provided to photoelectronically input a specified fingerprint of an entrant. A monochrome image data of the ridge pattern of the entrant fingerprint is stored as fingerprint image data. A feature extraction device has a calculator which treats the ridge pattern image with one-dimensional group-delay spectrum transform in X- and Y-directions. The feature extraction device has the characteristic of isolating and emphasizing peaks of the individual frequency spectra in the form of differential with respect to a phase component frequency in Fourier transform analysis, and determining group-delay spectra in X- and Y-direction respectively as fingerprint feature portions. A distinction device is provided to collate the entrant feature portion with a registrant feature portion which is registered by the fingerprint image input means so as to identify the entrant with the registrant when X-oriented and Y-oriented group-delay spectra are recognized as being the same between the entrant and the registrant by calculating whether Euclidean distances fall short of a predetermined threshold limit upon collating the individual ridge pattern image.
A fingerprint scanning device for use in identification comprising: a fingerprint image input means adapted to photoelectronically input a specified fingerprint of an entrant, and storing two-dimensional monochrome image data of a ridge pattern of the entrant fingerprint as fingerprint image data; a feature extraction means having a calculator which treats the ridge pattern image with one-dimensional group-delay spectrum transform in X- and Y-directions which has a characteristic of isolating and emphasizing peaks of the individual frequency spectra in the form of differential with respect to a phase component frequency in Fourier transform analysis, and determining group-delay spectra in X- and Y-directions, respectively, as fingerprint feature portions; and a distinction means provided to collate the entrant feature portion with a registrant feature position which is registered by the fingerprint image input means so as to identify the entrant with the registrant when at least one of X-oriented and Y-oriented group-delay spectra is recognized to be the same between the entrant and the registrant by calculating whether Euclidean distances fall short of a predetermined threshold limit upon collating the individual ridge pattern image.
Claim 2
Dependent Claim
182 words
A fingerprint scanning device for use in identification comprising: a fingerprint image input means adapted to photoelectronically input a specified fingerprint of an entrant, and storing two-dimensional monochrome image data of a ridge pattern of the entrant fingerprint as fingerprint image data; a feature extraction means having a calculator which treats the ridge pattern image with one-dimensional group-delay spectrum transform in X- and Y-directions which has a characteristic of isolating and emphasizing peaks of the individual frequency spectra in the form of differential with respect to a phase component frequency in Fourier transform analysis, and determining group-delay spectra in X- and Y-directions, respectively, as fingerprint feature portions; and a distinction means provided to collate the entrant feature portion with a registrant feature position which is registered by the fingerprint image input means so as to identify the entrant with the registrant when at least one of X-oriented and Y-oriented group-delay spectra is recognized to be the same between the entrant and the registrant by calculating whether Euclidean distances fall short of a predetermined threshold limit upon collating the individual ridge pattern image.
Claim 3
Dependent Claim
109 words
In a fingerprint scanning device for use in identification as recited in claim 1, wherein the feature extraction means comprises a plural-feature extraction means including the group-delay spectrum transformation and the Fourier spectrum transformation or the like which extracts a plurality of features of the entrant from the fingerprint image data; and wherein the distinction means comprises a comprehensive distinction means which individually collates the entrant feature portion with a registrant feature portion registered by the fingerprint image input means; wherein the entrant is identified as the registrant on the basis of a plurality of collation results obtained by collating the entrant feature portion with the registrant feature portion.