Face recognition in big data ecosystem using multiple recognition models

• US 10,395,146 B2
• Filed: 04/19/2018
• Issued: 08/27/2019
• Est. Priority Date: 08/04/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Asati, Somnath, Naganna, Soma Shekar, Seth, Abhishek, Tomar, Vishal, Yellareddy, Shashidhar R.
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US15/957,884
• Publication Number:
  US 20180239994A1
• Time in Patent Office: 495 Days
• Field of Search: 382115, 382117, 382118, 382124, 382128, 382159, 382209, 382278, 340 552, 340 553, 340 583
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06F 18/21355 nonlinear criteria, e.g. embedding a manifold in a Euclidean space
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/285 Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/87 using selection of the recognition techniques, e.g. of a classifier in a multiple classifier system
• CPC Class Codes: G06V 10/95 structured as a network, e.g. client-server architectures
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

A system trains a facial recognition modeling system using an extremely large data set of facial images, by distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system. The system optimizes a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models. The system selectively matches each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models. The system reduces the time associated with training the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.

Claims

1. A computer-implemented method of training a facial recognition modeling system using an extremely large data set of facial images, the method comprising:

distributing a plurality of facial recognition models across a plurality of nodes within the facial recognition modeling system; and

optimizing a facial matching accuracy of the facial recognition modeling system by increasing a facial image set variance among the plurality of facial recognition models, wherein, to optimize the facial matching accuracy of the facial recognition modeling system, the program code when executed is further operable to;

match each facial image of the data set of facial images with at least one of the facial recognition models;

determine the least closely matching facial image associated with a maximum eigenvector distance between the facial image and each most closely matching facial image of the plurality of facial recognition models; and

insert a facial image of the data set of facial images into a facial recognition model of the plurality of facial recognition models, wherein the facial recognition model is associated with a least closely matching facial image.

2. The method of claim 1 wherein distributing the plurality of facial recognition models across the plurality of nodes in the facial recognition modeling system comprises:

providing a variety of facial recognition models for the plurality of facial recognition models wherein the plurality of facial recognition models operate independently from each other.

3. The method of claim 1 wherein distributing the plurality of facial recognition models across the plurality of nodes in the facial recognition modeling system comprises:

allowing each of the plurality of facial recognition models to determine when re-training of the facial recognition model is required.

4. The method of claim 1 wherein distributing the plurality of facial recognition models across the plurality of nodes in the facial recognition modeling system comprises:

allowing each of the plurality of facial recognition models to determine when to split a single facial recognition model into at least two facial recognition models.

5. The method of claim 1 wherein distributing the plurality of facial recognition models across the plurality of nodes in the facial recognition modeling system comprises:

assigning a facial characteristic recognition task to at least one specialty model in the plurality of facial recognition models.

6. The method of claim 5 wherein assigning the facial characteristic recognition task to the at least one specialty model in the plurality of facial recognition models comprises:

detecting a facial characteristic in at least one facial image of the extremely large data set of facial images; and

inserting the at least one facial image into the at least one specialty model to increase the facial matching accuracy of the at least one specialty model with respect to the facial characteristic.

7. The method of claim 1 wherein optimizing the facial matching accuracy of the facial recognition modeling system by increasing the facial image set variance among the plurality of facial recognition models comprises:

increasing a facial matching model accuracy associated with each of the plurality of facial recognition models by selectively matching each facial image within the extremely large data set of facial images with at least one of the plurality of facial recognition models.

8. The method of claim 7 wherein increasing the facial matching model accuracy associated with each of the plurality of facial recognition models comprises:

computing a correlation between a facial image within the extremely large data set of facial images and a most closely matching facial image within each of the plurality of facial recognition models; and

determining a least closely matching facial image associated with a farthest correlation between the facial image and each of the most closely matching facial images.

9. The method of claim 1′

wherein increasing the facial matching model accuracy associated with each of the plurality of facial recognition models comprises;

calculating an eigenvector distance between a facial image within the extremely large data set of facial images and a most closely matching facial image within each of the plurality of facial recognition models; and

determining a least closely matching facial image associated with a maximum eigenvector distance between the facial image and each of the most closely matching facial images.

10. The method of claim 7 wherein increasing the facial matching model accuracy associated with each of the plurality of facial recognition models comprises:

reducing a time associated with a training of the facial recognition modeling system by load balancing the extremely large data set of facial images across the plurality of facial recognition models while improving the facial matching accuracy associated with each of the plurality of facial recognition models.