Computing That Serves

Colloquium presented by Walter Scheirer


Thursday, February 27, 2020 - 11:00am


Walter Scheirer


Bryan Morse

Colloquium presented by Walter Schreirer

Thursday, February 27th, 2020

11:00am in 1170 TMCB

Host: Bryan Morse




The subtleties of human perception, as measured by vision scientists through the use of psychophysics, are important clues to the internal workings of visual recognition. For instance, measured reaction time can indicate whether a visual stimulus is easy for a subject to recognize, or whether it is hard. In this talk, I consider how to incorporate psychophysical measurements of visual perception into the loss function of a deep neural network being trained for a recognition task, under the assumption that such information can enforce consistency with human behavior. As a case study to assess the viability of this approach, I look at the problem of handwritten document transcription. While good progress has been made towards automatically transcribing modern handwriting, significant challenges remain in transcribing historical documents. This talk describes work towards a comprehensive transcription solution for Medieval manuscripts that combines networks trained using our novel loss formulation with natural language processing elements. In a baseline assessment, reliable performance is demonstrated for the standard IAM and RIMES datasets. Further, the talk goes on to show feasibility for the approach on a previously published dataset and a new dataset of digitized Latin manuscripts, originally produced by scribes in the Cloister of St. Gall around the middle of the 9th century.


Walter J. Scheirer, Ph.D. is an Assistant Professor in the Department of Computer Science and Engineering at the University of Notre Dame. Previously, he was a postdoctoral fellow at Harvard University, with affiliations in the School of Engineering and Applied Sciences, Dept. of Molecular and Cellular Biology and Center for Brain Science, and the director of research & development at Securics, Inc., an early stage company producing innovative computer vision-based solutions. He received his Ph.D. from the University of Colorado and his M.S. and B.A. degrees from Lehigh University. Dr. Scheirer has extensive experience in the areas of computer vision, machine learning and image processing. His overarching research interest is the fundamental problem of recognition, including the representations and algorithms supporting solutions to it.