Title

Human Centered Computer Vision

Abstract

Abstract

Facial image processing and analysis is the task of automatically analyzing face images in order to acquire information about the depicted persons. This includes a person’s identity, emotional state, facial gestures, age, and gender. The large number of European projects that involves facial image processing as a part shows its crucial role in a wide range of application domains, such as security, smart environments, human-computer interfaces, and content-based image and video analysis. Considering the advanced security needs of the society and the shift to the paradigm of human-centered computing for natural interfaces, the interest in face processing is expected to continue with increasing pace. In this talk Dr. Ekenel is going to present an overview of facial image processing and analysis research activities, as well as their recent work on deep learning @ SiMiT Lab (http://simitlab.itu.edu.tr/). The covered topics will be about face alignment, face recognition, facial expression analysis and their applications. Deep learning topics like transfer learning, dataset bias, domain adaptation, and context adaptation will also be discussed.

Biography: Dr. Ekenel (http://web.itu.edu.tr/~ekenel/) is an Associate Professor at the Department of Computer Engineering in Istanbul Technical University in Turkey and a Host Professor at the Signal Processing Lab 5 of École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland. He received his Ph.D. degree in Computer Science from the University of Karlsruhe (TH) in 2009. He has founded the Facial Image Processing and Analysis group (http://face.cs.kit.edu/) at the Department of Computer Science in Karlsruhe Institute of Technology. He was the task leader for face recognition in several large-scale European projects. His face analysis technology has been used by several research labs and companies and has taken part in several demo and press events. He has received the EBF European Biometric Research Award in 2008 for his contributions to the field of face recognition and with the systems they have developed with his team, he received the Best Demo Award at the IEEE International Conference on Automatic Face and Gesture Recognition in 2008. Since January 2011, he has been coordinating the Benchmarking Facial Image Analysis Technologies (BeFIT) initiative and he is the primary organizer of the BeFIT workshops 2011 and 2012.

Supervisor(s)

Supervisor(s)

Assoc. Prof. Hazım Ekenel

Date and Location

Date and Location

2019-04-18;16:00:00-BMB5

Category

Category

Seminar