新加坡南洋理工大学Alex Chichung KOT教授来访并作报告

报告人：Alex Chichung KOT教授，新加坡南洋理工大学

时间：2014年12月25日（周四）上午10:30-12:00

          2014年12月30日（周二）上午 9:30-11:30

地点：北京交通大学九教北609会议室

报告主题：1、《Can we trust photos?》

                    2、《Current work in ROSE Lab》

摘要：1、With the fast proliferation of digital cameras and other image acquisition devices due to the advancement in digital photography technology, photos from the public may have good news values for making journalist reports. However, one big challenge is how to authenticate the photo contents from the public, which may come from unreliable sources. A large variety of forensics works have been proposed to address various forensic challenges based on different types of tell-tale signs. This talk introduces several techniques for: (1) Accurate detection of image demosaicing regularity as a general type of image forensics features. (2) Identification of various common image source models including digital still cameras, RAW conversion tools and the low-end mobile cameras; (3) Universal detection of a wide range of common image tampering. (4) Tampering detection for blur images. (5) EXIF file tampering or content manipulations, and (6) Prevention of the image recapturing threat. These techniques help expose common image forgeries, especially those easy-to-make forgeries, which can be hardly seen directly by human eyes. The common theme behind these forensics techniques is through statistical detection of some intrinsic image regularity or tampering anomalies.

2、The Rapid-Rich Object Search Laboratory (ROSE) is a 10-million joint collaboration between NTU and Peking University.  Its aim is to create one of the largest database of structured domain objects in Asia, and to develop rapid and rich object mobile search technology.  As mobile devices proliferate, internet searches are increasingly performed on tablets and smartphones. However, current mobile search is mainly based on text, with limited capability in describing real-world objects. In many situations, a picture taken with a mobile device is simply more descriptive.   The ROSE Lab has received $7.1 million in third-party  co-funding commitments, secured 8 partners (including Tencent, one of the largest Internet providers in Asia), developed 4 products (including the Image Recognition module for Tencent’s WeChat Smart Platform), and has more than 41 papers published. In this talk, the research activities will be introduced and some demoes will be shown.

报告人简介：Prof. Alex Kot has been with the Nanyang Technological University, Singapore since 1991. He headed the Division of Information Engineering for eight years before serving as the Vice Dean Research for the School of Electrical and Electronic Engineering. He is currently Professor and Associate Dean for College of Engineering. He is the Director of Rapid-Rich Object SEarch (ROSE) Lab. He has published extensively in the areas of signal processing for communication, biometrics, data-hiding, image forensics, information security. His new research area is in the domain object search and recognition.

Dr. Kot has served as Associate Editor for 9 IEEE Transactions and Journals including Signal Processing, Image Processing, Multimedia, Signal Processing Letters, Signal Processing Magazine, and Information, Forensics and Security. Dr. Kot has served the IEEE SP Society in various capacities such as the General Co-Chair for the 2004 IEEE International Conference on Image Processing (ICIP) and as a member in the IEEE Fellow Evaluation Committee. He now serves as the Vice-President for the IEEE Signal Processing Society. He is a member of IEEE SPS Board of Governors. He received the Best Teacher of the Year Award and is a co-author for several Best Paper Awards. He was the IEEE CASS Distinguished Lecturer in 2005 and 2006, IEEE SPS Distinguished Lecturer in 2014 and 2015, and is a Fellow of IES, a Fellow of IEEE, and a Fellow of Academy of Engineering, Singapore.