Deep Learning for Automatic Object Recognition
In this talk, I explain how deep learning is used to automatically recognize objects. Object recognition is important for different applications including robots (the ability of robots to naturally interact with the environment), autonomous driving (obstacle detection), and image search (finding images on the Internet). I will show how deep learning can be used for facial expression analysis including automatic emotion recognition, and age/gender estimation. From a live video stream (webcam), automatic emotion recognition is demonstrated in real-time. Finally, 3D face reconstruction is explained and a live demo is given.
Theo Gevers is a Full Professor of Computer Vision at the University of Amsterdam, The Netherlands and a part-time Full Professor at the Computer Vision Center (UAB), Barcelona, Spain. He was granted a VICI-award (for excellent researchers) from the Dutch Organisation for Scientific Research. He is the founder of Sightcorp and 3DUniversum (spin-off's of the University of Amsterdam) and Visual Tagging Services (spin-off of the Computer Vision Center, Barcelona). His main research interests are in the fundamentals of content-based image retrieval, colour image processing and computer vision specifically in the theoretical foundation of geometric and photometric invariants.