Face recognition in big data ecosystem using multiple recognition models
First Claim
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.
2 Assignments
0 Petitions
Accused Products
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.
25 Citations
10 Claims
-
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 Dependent Claims (2, 3, 4, 5)
-
-
6. A system comprising:
-
a computing processor; and a computer readable storage medium operationally coupled to the processor, the computer readable storage medium having computer readable program code embodied therewith to be executed by the computing processor, the computer readable program code configured 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 Dependent Claims (7, 8, 9, 10)
-
Specification