Abstract: A computer-implemented method for analyzing a thermographic image to detect an article of interest (AOI) comprises processing the image using a machine learning algorithm configured to detect the AOI and comprising a convolutional neural network (CNN); and displaying the image with location of the AOI being indicated if determined to be present. The CNN features a series pair of convolution modules configured to receive the image and form a reduced size feature map; an in-depth module thereafter and configured to learn correlations and contextual features of the image; and a superficial module after a first of the series convolution module pair and configured to extract features relevant to the AOI. Also, a computer-implemented method for generating synthetic training data based on authentic training data comprises a first neural network configured to generate the synthetic data and a second neural network configured to compare it to the authentic data to determine closeness.

Abstract: A computer-implemented method for analyzing a thermographic image to detect an article of interest (AOI) comprises processing the image using a machine learning algorithm configured to detect the AOI and comprising a convolutional neural network (CNN); and displaying the image with location of the AOI being indicated if determined to be present. The CNN features a series pair of convolution modules configured to receive the image and form a reduced size feature map; an in-depth module thereafter and configured to learn correlations and contextual features of the image; and a superficial module after a first of the series convolution module pair and configured to extract features relevant to the AOI. Also, a computer-implemented method for generating synthetic training data based on authentic training data comprises a first neural network configured to generate the synthetic data and a second neural network configured to compare it to the authentic data to determine closeness.