ALEXANDRIA, Va., June 4 -- United States Patent no. 12,322,161, issued on June 3, was assigned to Teledyne FLIR Commercial Systems Inc. (Goleta, Calif.).
"Closed loop automatic dataset creation systems and methods" was invented by Pierre Boulanger (Goleta, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Various techniques are provided for training a neural network to classify images. A convolutional neural network (CNN) is trained using training dataset comprising a plurality of synthetic images. The CNN training process tracks image-related metrics and other informative metrics as the training dataset is processed. The trained inference CNN may then be tested using a validation dataset of real images ...