Efficient texture comparison

• US 9,135,496 B2
• Filed: 03/12/2013
• Issued: 09/15/2015
• Est. Priority Date: 05/18/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Westerman, Wayne C., Han, Byron B., Marciniak, Craig A.
• Primary Examiner(s): Lefkowitz, Sumati
• Assistant Examiner(s): PERLMAN, DAVID S
• Application Number:
  US13/797,970
• Publication Number:
  US 20130308838A1
• Time in Patent Office: 917 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/602 Providing cryptographic facilities or services
• CPC Class Codes: G06F 3/041 Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
• CPC Class Codes: G06V 40/12 Fingerprints or palmprints
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop

Abstract

A scannable object is sensed and scanned. A map is constructed based on the scan results. The map is compared to one or more stored templates. Results of the comparison are provided. In some implementations, a secured processor may construct the map and may provide reduced resolution (and/or other versions that contain less information) versions of the map and/or the stored templates to one or more other processors. The one or more other processors may determine a match-set based on matching between the reduced resolution map and stored templates. The secured processor may then identify whether or not a match exists between the map and any stored template based on the match-set.

Claims

1. A device, comprising:

at least one encrypted processor that is configured to determine an input map associated with a texture pattern and calculate a reduced resolution pattern based on the input map, and calculate one or more reduced resolution template patterns, each reduced resolution template pattern based on a respective stored encrypted template map; and

at least one unsecured processor, communicably connected to the at least one encrypted processor, that is configured to;

receive the reduced resolution pattern and the one or more reduced resolution template patterns and identify a match-set if a match exists between the reduced resolution pattern and at least one reduced resolution template pattern, wherein the at least one encrypted processor is further configured to receive the match-set and identify if a match exists between the input map and any stored encrypted template map that is associated with the match-set.

2. The device of claim 1, wherein the match-set includes an identity of each reduced resolution template pattern that matches the reduced resolution pattern or an identify of each stored encrypted template map associated with each reduced resolution template pattern that matches the reduced resolution pattern.

3. The device of claim 1, wherein the at least one second processor is configured to identify a plurality of possible matches.

4. The device of claim 1, wherein the at least one second processor is faster than the at least one encrypted processor.

5. The device of claim 1, wherein at least one of:

the reduced resolution pattern comprises at least one of a checksum generated from the texture pattern, a hash generated from the texture pattern, or a histogram generated from the texture pattern;

or

each reduced resolution template pattern comprises at least one of a checksum generated from the respective associated stored encrypted template map, a hash generated from the respective associated stored encrypted template map, or a histogram generated from the respective associated stored encrypted template map.

6. The device of claim 1, wherein the reduced resolution pattern includes sufficient information to identify a match-set between the reduced resolution pattern and the one or more reduced resolution template pattern patterns but not sufficient information to determine the input map from the reduced resolution pattern.

7. The device of claim 1, wherein each reduced resolution template pattern includes sufficient information to identify a match-set based on comparison of the reduced resolution pattern and the reduced resolution template pattern but not sufficient information to determine the respective associated stored encrypted template map.

8. The device of claim 1, further comprising at least one device scanner, communicably connected to the at least one encrypted processor that obtains the texture pattern by scanning at least one scannable object.

9. The device of claim 8, wherein the at least one scannable object comprises at least one fingerprint.

10. A method, comprising:

determining, utilizing at least one secure processor, an input map based on a scan input, wherein the scan input is associated with a texture pattern;

calculating a reduced resolution pattern, utilizing the at least one secure processor, based on the input map;

calculating one or more reduced resolution template patterns, utilizing the at least one secure processor, wherein each reduced resolution template pattern is based on a respective encrypted template map;

providing the reduced resolution pattern and the one or more reduced resolution template patterns to at least one general processor utilizing the at least one secure processor;

receiving, utilizing the at least one secure processor, a match-set identified by the at least one general processor if a match exists between the reduced resolution pattern and at least one reduced resolution template pattern; and

identifying, utilizing the at least one secure processor, whether a match exists between the input map and any encrypted template map that is associated with the match-set.

11. The method of claim 10, further comprising determining, utilizing the at least one general processor, whether the reduced resolution pattern matches at least one of the one or more of reduced resolution template patterns.

12. The method of claim 10, further comprising receiving the scan input utilizing the at least one secure processor.

13. The method of claim 10, further comprising providing a result based on determining if the input map matches one or more of the template maps utilizing the at least one secure processor.

14. The method of claim 10, wherein at least one of:

the reduced resolution pattern comprises at least one of a checksum generated from the texture pattern, a hash generated from the texture pattern, or a histogram generated from the texture pattern;

or

each reduced resolution template pattern comprises at least one of a checksum generated from the respective associated template map, a hash generated from the respective associated template map, or a histogram generated from the respective associated template map.

15. The method of claim 10, wherein the reduced resolution pattern includes sufficient information to identify a match-set between the reduced resolution pattern and the one or more reduced resolution template patterns but not sufficient information to determine the input map from the reduced resolution pattern.

16. The method of claim 10, wherein each reduced resolution template pattern includes sufficient information to identify a match-set based on comparison of the reduced resolution pattern and the reduced resolution template pattern but not sufficient information to determine the respective associated template map.

17. The method of claim 10, further comprising:

sensing for at least one scannable object; and

obtaining the scan input by scanning the at least one scannable object.

18. The method of claim 17, wherein the at least one scannable object comprises at least one fingerprint.

19. The method of claim 10, wherein the match-set includes an identity of each reduced resolution template pattern that matches the reduced resolution pattern or an identify of each template map that is associated with each reduced resolution template pattern that matches the reduced resolution pattern.