Roger Zimmermann

Director of MMRL Lab, Assosciate Professor at NUS, Singapore


Biography


Roger Zimmermann is an Associate Professor with the Computer Science Department at the National University of Singapore (NUS). He is also a deputy director with the Interactive and Digital Media Institute (IDMI) at NUS and co-director of the Centre of Social Media Innovations for Communities (COSMIC). He holds a Ph.D. and an M.S. degree in Computer Science from the University of Southern California (USC). Among his research interests are mobile video management, streaming media architectures, distributed systems, spatio-temporal data management and location-based services. He has co-authored seven patents and more than two-hundred peer-reviewed articles in the aforementioned areas. He received the Best Paper Awards at the IEEE International Symposium on Multimedia (ISM) 2012 and the ACM SIGSPATIAL International Workshop on GeoStreaming (IWGS) 2016. Roger is on the editorial boards of the IEEE Multimedia Communications Technical Committee (MMTC) R-Letter and the Springer International Journal of Multimedia Tools and Applications (MTAP). He is also an associate editor for the ACM Transactions on Multimedia journal (ACM TOMM) and he has been elected to serve as Secretary of ACM SIGSPATIAL for the term 1 July 2014 to 30 June 2017. He has served on the conference program committees of many leading conferences and as reviewer of many journals. Recently he was the general chair of the ACM Multimedia Systems 2014 and the IEEE ISM 2015 conferences, and TPC co-chair of the ACM TVX 2017 conference.




Generic placeholder image

Abstract


Machine Learning for Image Processing in Healthcare


Many aspects of healthcare are undergoing rapid evolution and facing many challenges. Computer vision and image processing methods have progressed tremendously within the last few years. One of the reasons is the excellent performance that machine learning algorithms are achieving in many the fields of image processing, especially through deep learning techniques. There exists various application areas where computer-based image classification and object detection methods can make meaningful contributions. Yet, these data-intensive methods encounter a unique set of challenges in the medical domain – which often suffer from a scarcity of large public datasets and still require reliable analysis with high precision. This talk will present some recent work in the area of image analytics for cervical cancer screening in the context of low resource settings. The work is in collaboration with Dr. Pamela Tan from Singapore’s KK Hospital and MobileODT, a medical device and software-enabled services company. In this joint project, our group’s work focuses on machine learning algorithms for the medical analysis of cervix images acquired via unconventional consumer imaging devices like smartphones, based on their appearance and for the purpose of screening cervical cancer precursor lesions. The talk will present our methodology and some preliminary results.