Biometric coding

Patent metadata

Field	Value
Publication number	US-9412004-B2
Application number	US-201013518490-A
Country	US
Kind code	B2
Filing date	Dec 23, 2010
Priority date	Dec 23, 2009
Publication date	Aug 9, 2016
Grant date	Aug 9, 2016

Abstract

A database stores a number N of biometric data representatives which correspond to a set of characteristics of said biometric data. Acquired biometric data is obtained. Then, transformed biometric data is obtained by transforming the acquired biometric data according to said set of characteristics. Next, N deviation values are obtained by applying a comparison between the transformed biometric data and the N representatives in the database. Finally, a vector representing the acquired biometric data is obtained, the representation vector having a number of components less than or equal to N, said components being determined in relation to said N deviation values.

First claim

The invention claimed is:

1. A method for encoding a biometric data item, comprising:
defining a biometric dataspace comprising a plurality of representatives of biometric data items stored in a database, wherein each representative is defined in accordance with a set of characteristics of a biometric data item;
obtaining an acquired biometric data item;
transforming said acquired biometric data item according to said set of characteristics to generate a transformed biometric data item;
positioning the acquired biometric data item relative to the biometric dataspace by applying a comparison between the transformed biometric data item and each representative in the database to obtain N deviation values which position the acquired biometric data item relative to the biometric dataspace; and
generating an encoded form of the acquired biometric data item as a representative vector for the acquired biometric data item, said representative vector having at most N components, wherein each one of said N components is determined as a function of a corresponding one of said N deviation values;
wherein the representative vector for the biometric data item is a binary vector, and wherein each of the components is a binary value resulting from comparison against at least one threshold value; and
wherein the binary vector is obtained by the following steps:
determining a statistical noise value relative to each representative;
obtaining a weight associated with each representative as a function of the statistical value relative to it;
determining the binary components of the representative vector by comparing the deviation values obtained for the respective representatives to the threshold value, taking into consideration the associated weight obtained using a histogram of the distribution of the distances relative to each representative.

2. The method according to claim 1 , further comprising:
/i/ selecting as the N deviation values, values that are relevant according to a criterion; and
/ii/ determining the N components relative to the selected deviation values.

3. The method according to claim 1 , wherein a set of characteristics corresponds to a local definition of biometric data.

4. The method according to claim 3 , wherein the local definition is obtained by:
determining a main minutia; and
determining local information relating to characteristics neighboring the main minutia.

5. The method according to claim 4 , wherein the local information indicates at least one element selected from the group consisting of: a position of a neighboring minutia, a ridge count, a minutia type, and a local curvature.

6. The method according to claim 1 , wherein a set of characteristics corresponds to an image illustrating the biometric data item.

7. The method, according to claim 1 , wherein the representative biometric data items in the database are obtained by the following steps:
/1/ capturing a number M′ of different biometric data items;
/2/ obtaining M″ respective representatives of said biometric data items by transforming the M′ biometric data items according to the same set of characteristics;
/3/ selecting, from among the M″ representatives, the ones which have a deviation value between them that exceeds a threshold value according to a comparison; and
/4/ storing the selected representatives in the database.

8. The method according to claim 7 , wherein the threshold value is determined as a function of the level of performance of the vector representation of a biometric data item.

9. Apparatus for encoding biometric data in a vector representation, comprising:
an interface unit for cooperating with a database which stores a plurality of representatives of biometric data items as a biometric dataspace, wherein each representative is defined in accordance with a set of characteristics of a biometric data item;
an obtaining unit for obtaining an acquired biometric data item;
a transformation unit for transforming said acquired biometric data item according to said set of characteristics to generate a transformed biometric data item;
a comparison unit for positioning the acquired biometric data item relative to the biometric dataspace by applying a comparison between the transformed biometric data item and each representative in the database to generate N deviation values which position the acquired biometric data item relative to the biometric dataspace; and
a determination unit for generating an encoded form of the acquired biometric data item as a representative vector for the acquired biometric data item, said representative vector having at most N components, wherein each one of said N components is determined as a function of a corresponding one of said N deviation values;
wherein the representative vector for the biometric data item is a binary vector, and wherein each of the components is a binary value resulting from comparison against at least one threshold value; and
wherein the determination unit obtains the binary vector by performing the following steps:
determining a statistical noise value relative to each representative;
obtaining a weight associated with each representative as a function of the statistical value relative to it;
determining the binary components of the representative vector by comparing the deviation values obtained for the respective representatives to the threshold value, taking into consideration the associated weight obtained using a histogram of the distribution of the distances relative to each representative.

10. The apparatus according to claim 9 , further comprising a database storing the representative biometric data items.

11. The apparatus according to claim 10 , additionally comprising:
a sensor for capturing a number M′ of different biometric data items;
a transformation unit for obtaining M″ respective representatives of said biometric data items by transforming the M′ biometric data according to the same set of characteristics;
a selection unit for selecting, from among the M″ representatives, the ones which have a deviation value between them that exceeds a threshold value according to a comparison; and
a database for storing the selected representatives in the database.

12. A non-transitory computer storage medium having stored thereon computer program instructions that, when executed by a processor, perform the method according to claim 1 .

13. The apparatus according to claim 9 , wherein the determining unit is configured to:
/i/ select as the N deviation values, values that are relevant according to a criterion; and
/ii/ determine the N components relative to the selected deviation values.

14. The apparatus according to claim 13 , wherein a set of characteristics corresponds to a local definition of biometric data.

15. The apparatus according to claim 14 , wherein the local definition is obtained by:
determining a main minutia; and
determining local information relating to characteristics neighboring the main minutia.

16. The apparatus according to claim 15 , wherein the local information indicates at least one element selected from the group consisting of: a position of a neighboring minutia, a ridge count, a minutia type, and a local curvature.

17. The apparatus according to claim 9 , wherein a set of characteristics corresponds to an image illustrating the biometric data item.

18. The apparatus according to claim 9 , further comprising means for obtaining the representative biometric data items in the database, said means for obtaining configured to perform the foll

Assignees

• Bringer Julien
• Despiegel Vincent
• Morpho

Inventors

• Bringer Julien
• Despiegel Vincent

Classifications

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• G06K9/00087 Primary

  Physics · mapped topic

• G06V40/1365 Primary

  Matching; Classification · CPC title