Template fusion system and method

• US 10,558,886 B2
• Filed: 11/15/2017
• Issued: 02/11/2020
• Est. Priority Date: 11/15/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Glover, Raymond
• Primary Examiner(s): Tsai, Tsung Yin
• Application Number:
  US15/813,274
• Publication Number:
  US 20190147287A1
• Time in Patent Office: 818 Days
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/772 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
• CPC Class Codes: G06V 10/803 of input or preprocessed data
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/50 Maintenance of biometric data or enrolment thereof

Abstract

A method, computer program product, and computing system for receiving a plurality of images of a subject. The plurality of images of the subject may be processes to generate one or more templates. A fused template may be generated from the one or more templates based upon, at least in part, a stopping criterion.

Claims

1. A computer-implemented method, executed on a computing device, comprising:

receiving, at the computing device, a plurality of images of a subject;

processing the plurality of images of the subject to generate one or more templates, wherein the one or more templates each include one or more elements; and

generating a fused template from the one or more templates, based upon, at least in part, a stopping criterion, wherein generating the fused template includes generating a probability density function, based upon, at least in part, a subset of the one or more templates, wherein the subset of the one or more templates includes at least one of a probability density and the probability density function for each respective dimension of the one or more elements.

2. The computer-implemented method of claim 1, wherein generating the probability density function includes:

initializing the subset of the one or more templates with at least one template from the one or more templates;

constructing a sample matrix of the subset of the one or more templates; and

generating at least one mean vector and at least one variance vector from the sample matrix.

3. The computer-implemented method of claim 2, wherein generating the probability density function includes:

determining an average standard error of the mean for the probability density function; and

adding at least one additional template to the subset of the one or more templates based upon, at least in part, the stopping criterion and the average standard error of the mean of the probability density function.

4. The computer-implemented method of claim 1, further comprising:

comparing the fused template to at least one database template based upon, at least in part, a Bhattacharyya distance between the fused template and the at least one database template.

5. The computer-implemented method of claim 4, wherein comparing the fused template includes comparing the fused template to the at least one database template to identify the subject in the plurality of images of the subject from a plurality of subjects identified in the at least one database template.

6. The computer-implemented method of claim 4, wherein comparing the fused template includes comparing the fused template to the at least one database template to verify whether the subject in the plurality of images of the subject is the subject identified in the at least one database template.

7. A computer program product residing on a non-transitory computer readable medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:

receiving a plurality of images of a subject;

processing the plurality of images of the subject to generate one or more templates, wherein the one or more templates each include one or more elements; and

generating a fused template from the one or more templates, based upon, at least in part, a stopping criterion, wherein generating the fused template includes generating a probability density function, based upon, at least in part, a subset of the one or more templates, wherein the subset of the one or more templates includes at least one of a probability density and the probability density function for each respective dimension of the one or more elements.

8. The computer program product of claim 7, wherein generating the probability density function includes:

initializing the subset of the one or more templates with at least one template from the one or more templates;

constructing a sample matrix of the subset of the one or more templates; and

generating at least one mean vector and at least one variance vector from the sample matrix.

9. The computer program product of claim 8, wherein generating the probability density function includes:

determining an average standard error of the mean for the probability density function; and

adding at least one additional template to the subset of the one or more templates based upon, at least in part, the stopping criterion and the average standard error of the mean of the probability density function.

10. The computer program product of claim 7, further comprising instructions for:

comparing the fused template to at least one database template based upon, at least in part, a Bhattacharyya distance between the fused template and the at least one database template.

11. The computer program product of claim 10, wherein comparing the fused template includes comparing the fused template to the at least one database template to identify the subject in the plurality of images of the subject from a plurality of subjects identified in the at least one database template.

12. The computer program product of claim 10, wherein comparing the fused template includes comparing the fused template to the at least one database template to verify whether the subject in the plurality of images of the subject is the subject identified in the at least one database template.

13. A computing system comprising one or more processors and one or more memories, wherein the computing system is configured to perform operations comprising:

receiving a plurality of images of a subject;

processing the plurality of images of the subject to generate one or more templates, wherein the one or more templates each include one or more elements; and

generating a fused template from the one or more templates, based upon, at least in part, a stopping criterion, wherein generating the fused template includes generating a probability density function, based upon, at least in part, a subset of the one or more templates, wherein the subset of the one or more templates includes at least one of a probability density and the probability density function for each respective dimension of the one or more elements.

14. The computing system of claim 13, wherein generating the probability density function includes:

initializing the subset of the one or more templates with at least one template from the one or more templates;

constructing a sample matrix of the subset of the one or more templates; and

generating at least one mean vector and at least one variance vector from the sample matrix.

15. The computing system of claim 14, wherein generating the probability density function includes:

determining an average standard error of the mean for the probability density function; and

adding at least one additional template to the subset of the one or more templates based upon, at least in part, the stopping criterion and the average standard error of the mean of the probability density function.

16. The computing system of claim 13, wherein the operations further comprise:

comparing the fused template to at least one database template based upon, at least in part, a Bhattacharyya distance between the fused template and the at least one database template.

17. The computing system of claim 16, wherein comparing the fused template includes comparing the fused template to the at least one database template to identify the subject in the plurality of images of the subject from a plurality of subjects identified in the at least one database template.