Go to PriorIP Home
Advanced Search

Method and device for collating biometric information

 ENOMOTO
Abstract:
A feature amount obtained from an image group for registration is stored as dictionary data in a memory. When an input image group constituted of a plurality of images is supplied to be collated with the dictionary data, the images constituting the input image group are classified based on a specific classification standard (S15), a feature amount obtained from each of the classified image groups is collated with the feature amount stored as the dictionary data in the memory (S17-S20, S22), and a result of the collation of all the input image groups with the dictionary data is determined based on a result of integrating a plurality of collection results of the classified image groups with the dictionary data (S21, S23).

Inventor(s): NOBUYOSHI ENOMOTO (JP)

Applicant: TOSHIBA KK

Designated Countries: AL; BA; DE; GB; HR; MK; YU;

European Classification(s):
G06K9/00F3; G06K9/62B6;

International Classification(s):
G06K 9/00; G06K 9/00; G06K 9/62; G06K 9/62;

PriorIP Cluster(s):
face image detecting (program, video, digital)

View Application at EPO...
Download PDF...

Citations

Application Number Title Applicant Publication date
US 2005147291 (A1) Pose-invariant face recognition system and process MICROSOFT CORP Jul 7, 2005
US 2005123202 (A1) Face recognition apparatus and method using PCA learning per subgroup SAMSUNG ELECTRONICS CO LTD Jun 9, 2005
EP 1416427 (A2) Person recognising apparatus, person recognising method & passage controller TOSHIBA KK May 6, 2004