4 papers
A Neural Network Looks at Leonardo's(?) Salvator Mundi
Steven J. Frank, Andrea M. Frank
We use convolutional neural networks (CNNs) to analyze authorship questions surrounding the works of Leonardo da Vinci -- in particular, Salvator Mundi, the world's most expensive…
Resource-Frugal Classification and Analysis of Pathology Slides Using Image Entropy
Steven J. Frank
Pathology slides of lung malignancies are classified using resource-frugal convolution neural networks (CNNs) that may be deployed on mobile devices. In particular, the challenging…
Analysis of Dutch Master Paintings with Convolutional Neural Networks
Steven J. Frank, Andrea M. Frank
Trained on the works of an artist under study and visually comparable works of other artists, convolutional neural networks can identify forgeries and provide attributions. They ca…
Salient Slices: Improved Neural Network Training and Performance with Image Entropy
Steven J. Frank, Andrea M. Frank
As a training and analysis strategy for convolutional neural networks (CNNs), we slice images into tiled segments and use, for training and prediction, segments that both satisfy a…