×

Face recognition in big data ecosystem using multiple recognition models

  • US 10,402,702 B2
  • Filed: 04/19/2018
  • Issued: 09/03/2019
  • Est. Priority Date: 08/04/2016
  • Status: Active Grant
First Claim
Patent Images

1. A computer program product comprising a non-transitory computer readable medium having computer readable program code embodied therewith for training a facial recognition modeling system using an extremely large data set of facial images, the program code executable by a computing processor to:

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

    optimize 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 a lower facial image set variance indicates to a closer correlation between a facial image and a set of facial images within a training set, and wherein a higher facial image set variance indicates a farther correlation between a facial image and a set of facial images within a training set, 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; 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, and wherein the facial recognition model has a highest variance between the facial image and a training set of the facial recognition model to insure that the facial recognition model has a more diverse sample.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×