Method of and device for collating data, and computer product

• US 20040015457A1
• Filed: 10/24/2001
• Published: 01/22/2004
• Est. Priority Date: 03/21/2001
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Yamazaki, Yasushi, Sasaki, Hitoshi, Otani, Takeshi
• Granted Patent: US 7,039,903 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 16/176 Support for shared access to files; File sharing support
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

The collating device includes the Formant estimation section that estimates feature amount data that represents a time-based change in frequencies of first and second Formants from voice data input through the microphone. The difference computing section calculates a difference between some reference feature amount data and the feature amount data as the feature-amount difference data. This feature-amount difference data is stored in a database. The feature-amount difference data corresponding to voice data input upon collation is collated with the feature-amount difference data registered in the database, and the result is output.

Claims

1. A computer program containing instructions which when executed on a computer causes the computer to realize:

a feature amount data extracting unit which extracts feature amount data from a physical amount data;

a feature-amount difference data computing unit which calculates a difference between the feature amount data and a predetermined reference feature amount data as the feature-amount difference data;

a registering unit which registers the feature-amount difference data in a database; and

a collating unit which collates the feature-amount difference data corresponding to the physical amount data input upon collation with the feature amount difference data registered in said database, and outputs the result of collation.

2. The computer program according to claim 1, wherein said feature amount data extracting unit calculates a time-based change in the feature amount data to provide the resulting change as the feature amount data.

3. The computer program according to claim 1, wherein the physical amount data is voice data, and

said collating unit outputs the result of collation to a controlled device that uses voice data.

4. The computer program according to claim 1, wherein the physical amount data is image data, and

said collating unit outputs the result of collation to a controlled device that uses image data.

5. The computer program according to claim 1 further including instruction which realizes a reading unit which reads the feature-amount difference data from said database when the collation by said collating unit indicates coincidence.

6. The computer program according to claim 5 further including instruction which realizes a physical amount data generation unit which generates the physical amount data based on the feature-amount difference data read by said reading means and the reference feature amount data.

12. The computer program according to claim 1, wherein said feature-amount difference data computing unit uses standardized data obtained by standardizing a range of the feature amount data instead of the reference feature amount data, and calculates a feature-amount difference data including the feature amount data within the range and a difference between the standardized data and a feature amount data beyond the range.

7. A computer program containing instructions which when executed on a computer causes the computer to realize:

a first feature amount data extracting unit which extracts a first feature amount data from a first physical amount data;

a first feature-amount difference data computing unit which calculates a difference between the first feature amount data and a predetermined first reference feature amount data as the first feature amount difference data;

a second feature amount data extracting unit which extracts second feature amount data from a second physical amount data;

a second feature-amount difference data computing unit which calculates a difference between the second feature amount data and a predetermined second reference feature amount data as the second feature amount difference data;

a registering unit which registers the first feature-amount difference data and the second feature-amount difference data in a database; and

a collating unit which collates the first feature-amount difference data corresponding to the first physical amount data input upon collation with the first feature-amount difference data registered in said database, collates the second feature-amount difference data corresponding to the second physical amount data input upon collation with the second feature amount difference data registered in said database, and outputs the result of collation.

8. The computer program according to claim 7, wherein the first physical amount data is voice data and the second physical amount data is image data.

9. The computer program according to claim 7, wherein said collating unit outputs the result of collation to a controlled device that is controlled based on the result of collation.

10. A method of collating data comprising the steps of:

extracting a feature amount data from a physical amount data;

calculating a difference between the feature amount data and a predetermined reference feature amount data as the feature-amount difference data;

storing the feature-amount difference data in a database; and

collating the feature-amount difference data corresponding to physical amount data input upon collation with the feature amount difference data registered in said database, and outputting the result of collation.

11. A device for collating data comprising:

a feature amount data extracting unit which extracts feature amount data from a physical amount data;

a feature-amount difference data computing unit which calculates a difference between the feature amount data and a predetermined reference feature amount data as the feature-amount difference data;

a registering unit which registers the feature-amount difference data in a database; and

a collating unit which collates the feature-amount difference data corresponding to the physical amount data input upon collation with the feature amount difference data registered in said database, and outputs the result of collation.