Fusion Structure with Compression,Halftoning,and Deep Learn
报告人：Prof. Jing-Ming Guo
Title: Advances on Image Retrieval: Fusion Structure with Compression, Halftoning, and Deep Learning
With the advances of the artificial intelligence, content-based image retrieval can be developed as multi-level schemes with low-level and high-level features. In this talk, the functions and extended advantages of the digital halftoning will be elaborated as the first stage. An extremely low complexity compression scheme will later be introduced by incorporating with digital halftoning. As most images are compressed and recorded in databases, compressed domain features are thus more intuitively borrowed to form the low-level features for the image retrieval. Conversely, features generated by deep learning can better characterize human perception through various operations such as convolution and pooling, and thus achieve effective feature descriptors. At the end of this talk, the fusion descriptors from the low-level and high-level features will be introduced. The performance of the designed image retrieval system will subsequently be demonstrated with practical examples.
Bio.: Prof. Guo is currently a Professor with the Department of Electrical Engineering and the Vice Dean of the College of Electrical Engineering and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan. He is also serving as the Director of the Innovative Business Incubation Center, Office of Research and Development. His research interests include multimedia signal processing, biometrics, computer vision, and digital halftoning. Dr. Guo is a senior member of the IEEE and a Fellow of the IET. He has been promoted as a Distinguished Professor in 2012 for his significant research contributions. He received the Outstanding Professor Award on Electrical Engineering from Chinese Institute of Electrical Engineering in 2016, the Best Paper Award from the International Computer Symposium in 2014, the Outstanding youth Electrical Engineer Award from Chinese Institute of Electrical Engineering in 2011, the Outstanding young Investigator Award from the Institute of System Engineering in 2011, the Best Paper Award from the IEEE International Conference on System Science and Engineering in 2011. Dr. Guo was the General Chair of IEEE International Conference on Consumer Electronics in Taiwan in 2015 and 2016, and was the Technical Program Chair for IEEE International Symposium on Intelligent Signal Processing and Communication Systems in 2012, IEEE International Symposium on Consumer Electronics in 2013, and IEEE International Conference on Consumer Electronics in Taiwan in 2014. Currently, he is Associate Editor of the IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, IEEE Signal Processing Letters, the Information Sciences, the Signal Processing, and Journal of Information Science and Engineering.