System and method for pleographic recognition, matching, and identification of images and objects

• US 9,542,618 B2
• Filed: 08/11/2015
• Issued: 01/10/2017
• Est. Priority Date: 09/12/2008
• Status: Expired due to Fees

• Current Assignee: Michael Shutt
• Original Assignee: Michael Shutt
• Inventors: Shutt, Michael
• Primary Examiner(s): Le, Vu
• Assistant Examiner(s): WOLDEMARIAM, AKLILU K
• Application Number:
  US14/822,974
• Publication Number:
  US 20150347868A1
• Time in Patent Office: 518 Days
• Field of Search: 382/115, 382/218, 382/305, 382/306, 382/103, 382/165, 382/217, 382/219, 382/233, 382/284, 715/700, 715/835
• US Class Current: 1/1
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces

Abstract

The inventive data processing system and method enable recognition, matching, and/or identification of images and/or of objects, utilizing at least one novel pleographic data processing technique.

Claims

1. A computer-implemented method to be performed by a computer processing system for identifying whether an identification image matches a previously-presented reference image, the method comprising:

implementing the following steps by one or more computer processors;

in an enrollment stage;

receiving a plurality of reference images;

for each reference image of the plurality of reference images;

generating a formation template for the reference image having an array of response function values representing a plurality of points included in the reference image;

generating a dynamic threshold for the formation template, wherein the dynamic threshold is a function of uniqueness of the array of response function values in the formation template; and

storing the formation template and the dynamic threshold for the formation template in the computer processing system among a plurality of formation templates and associated dynamic thresholds generated for the plurality of reference images;

in a recognition stage;

receiving an identification image;

generating an identification template for the identification image having an array of response function values representing a plurality of points in the identification image;

performing matching runs against the plurality of formation templates and associated dynamic thresholds, wherein the identification image is considered identified against a particular formation template when a particular dynamic threshold associated with the particular formation template is exceeded,

wherein a response function used in generating the plurality of formation templates and the identification template includes strong neighbor/area fragment overlapping.

2. The computer-implemented method of claim 1, wherein a response function used in generating the plurality of formation templates and the identification template includes separate pixel matching contributions.

3. The computer-implemented method of claim 1, wherein in the performing matching runs of the identification template against the plurality of formation templates and associated dynamic templates further comprises coarsening the identification template and the plurality of formation templates during one or more preliminary matching runs to identify a subset of the plurality of formation templates likely to present a match for the identification template.

4. The computer implemented method of claim 1, wherein the identification image is received from a user of an automotive keyless access system.

5. The computer implemented method of claim 1, wherein the identification image is received from a user of a home keyless access system.

6. The computer implemented method of claim 1, wherein the identification image is received from a user of a gun control system.

7. The computer implemented method of claim 1, wherein the identification image is received from a user of point-of-sale account system.

8. A computer-implemented system for identifying whether an identification image matches a previously-presented reference image, the system comprising:

implementing the following steps by one or more computer processors;

in an enrollment stage;

receiving a plurality of reference images;

for each reference image of the plurality of reference images;

generating a formation template for the reference image having an array of response function values representing a plurality of points included in the reference image;

generating a dynamic threshold for the formation template, wherein the dynamic threshold is a function of uniqueness of the array of response function values in the formation template; and

storing the formation template and the dynamic threshold for the formation template in the computer processing system among a plurality of formation templates and associated dynamic thresholds generated for the plurality of reference images;

in a recognition stage;

receiving an identification image;

generating an identification template for the identification image having an array of response function values representing a plurality of points in the identification image;

performing matching runs against the plurality of formation templates and associated dynamic thresholds, wherein the identification image is considered identified against a particular formation template when a particular dynamic threshold associated with the particular formation template is exceeded,

wherein a response function used in generating the plurality of formation templates and the identification template includes strong neighbor/area fragment overlapping.

9. The computer-implemented system of claim 8, wherein a response function used in generating the plurality of formation templates and the identification template includes separate pixel matching contributions.

10. The computer implemented system of claim 8, wherein the identification image is received from a user of an automotive keyless access system.

11. The computer implemented system of claim 8, wherein the identification image is received from a user of a home keyless access system.

12. The computer implemented system of claim 8, wherein the identification image is received from a user of a gun control system.

13. The computer implemented system of claim 8, wherein the identification image is received from a user of point-of-sale account system.