IMAGE IDENTIFICATION DEVICE AND PROGRAM

PROBLEM TO BE SOLVED: To provide an image identification device capable of highly accurately identifying a tablet based on image data of a PTP packaged tablet.SOLUTION: Covariance matrix calculation means 8 calculates a variance covariance matrix S of a color vector pof each pixel of an object image...

Full description

Saved in:
Bibliographic Details
Main Authors KAMATA SEIICHIRO, SUGIMOTO KENJIRO
Format Patent
LanguageEnglish
Published 24.05.2012
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES
MEASURING
PHYSICS
TESTING
Online AccessGet full text

Cover

More Information
Summary:PROBLEM TO BE SOLVED: To provide an image identification device capable of highly accurately identifying a tablet based on image data of a PTP packaged tablet.SOLUTION: Covariance matrix calculation means 8 calculates a variance covariance matrix S of a color vector pof each pixel of an object image. Unique value/unique vector calculation means 9 calculates a unique value λand a unique vector of the variance covariance matrix S. CDD calculation means 10 calculates a contribution rate r=λ/(λ+...+λ) from each unique value λ, and calculates a color dispersion descriptor D={r ,...,r }. CDD distance calculation means calculates a distance S(D,D) between the color dispersion descriptor Dand the color dispersion descriptor D of each template image. Template selection means 12 selects a template image where this distance S(D,D) is smallest, and outputs its number α as an identification result.
Bibliography:Application Number: JP20100246946