Computer vision applications are everywhere. At SAS alone, we have developed solutions in the manufacturing, transportation, health care and retail industries, to name a few. Given the intrinsically sensitive nature of image data, concerts for privacy have become more prevalent. This session will show how we apply principles of trustworthy AI in computer vision solutions. We will explore the concepts of privacy-by-design in practice and show how it applies to a use case that involves tracking people. When AI is applied in situations that directly impact lives, we need to take extra precautions in designing our solutions from both a modeling and deployment perspective.
