Bank of America Corporation
System for integration of a hexagonal image processing framework within a technical environment

Abstract:

Systems, computer program products, and methods are described herein for integration of a hexagonal convolutional neural network (H-CNN) within an image processing technical environment. The present invention is configured to initiate a hexagonal convolutional neural network (H-CNN); train the H-CNN using the first set of digital images; train the S-CNN in the image processing technical environment using the first set of digital images; classify a second set of digital images using the S-CNN using the second set of parameters; electronically receive an indication that the S-CNN has misclassified at least one of the second set of digital images; transform the at least one of the second set of digital images misclassified by the S-CNN as additional training data for the H-CNN; and re-train the H-CNN with the additional training data, wherein re-training the H-CNN further comprises modifying the first set of parameters for classification.