公开(公告)号：EP4134914A1

公开(公告)日：2023-02-15

申请号：EP22193531.5

申请日：2012-04-17

申请人： NEC Corporation

发明人： HARA, Masanori ,  SHIMAHARA, Tatsuya

IPC分类号： G06T7/73 ,  G06V10/26 ,  A61B5/1172 ,  G06V40/12 ,  A61B5/117 ,  G06T1/00

摘要： An object of the present invention is to appropriately segment fingerprint regions from a ten-print card, reduce an error of imprinting position or an error of finger position specification, and improve fingerprint matching accuracy. Specifically, a system, which computer processes a tenprint card where fingerprint images are imprinted, provides a processing mechanism which automatically crops or segments respective fingerprint images on the tenprint card. In particular, the system provides: a processing mechanism which appropriately crops or segments a slap print image, even if a fingerprint image of slap prints does not fit in a predetermined frame or even if noise other than fingerprints to be cropped or segmented is present within a frame of a four-finger slap, by using a result of matching with rolled prints; and a processing mechanism which checks a correspondence relationship between the rolled prints and the plane prints, assesses a finger position, and detects an error of imprinting position.

公开(公告)号：EP3696770A1

公开(公告)日：2020-08-19

申请号：EP18867156.4

申请日：2018-09-13

申请人： NEC Corporation

发明人： SHIMAHARA, Tatsuya

IPC分类号： G06T7/00

摘要： Provided is a biometric recognition apparatus and a fingerprint feature extraction method that can automatically optimize parameters used for extracting a feature template from a biometric image. The biometric recognition apparatus includes: a teacher data generation unit that generates a genuine pair and an imposter pair of a first biometric image and a second biometric image; a learning data generation unit that uses a plurality of different temporary parameters to extract feature templates from the first biometric image and the second biometric image; and an optimum solution determination unit that calculates a score separation degree on the temporary parameter basis based on a first score representing a similarity degree of a pair of the feature templates extracted from the genuine pair and a second score representing a similarity degree of a pair of the feature templates extracted from the imposter pair and determines the temporary parameter based on a level of the score separation degree.