您现在的位置:首页>新闻中心>科研动态

科研动态

【医学部学术讲座】——Image Recognition: from Subspace Approach and Sparse Coding to Deep Learning

文章来源: 作者: 发布时间:2017年06月02日 点击数: 字体:

主讲嘉宾: Xudong Jiang 新加坡南洋理工大学 终身副教授

时间: 2017年6月16日下午 2:30 – 4:00

地点: 深圳大学南校区医学院附楼报告厅

主持人: 雷柏英 讲师

主讲嘉宾简介:

Xudong Jiang the B.Eng. and M.Eng. degrees from the University of Electronic Science and Technology of China (UESTC), in 1983 and 1986, respectively, and the Ph.D. degree from Helmut Schmidt University, Hamburg, Germany, in 1997, all in electrical engineering. He joined Nanyang Technological University (NTU), Singapore, as a faculty member, in 2004, where he served as the Director of the Centre for Information Security from 2005 to 2011. He is currently a Tenured Associate Professor with the School of EEE, NTU. He holds seven patents and has authored over 150 papers with 30 papers in the IEEE journals, including 8 papers in IEEE Trans. Image Processing, 5 papers in IEEE Trans. Pattern Analysis and Machine Intelligence, and 3 papers in IEEE Trans. Signal Processing. His research interests include image processing, pattern recognition, computer vision, machine learning, and biometrics. Currently, he is an Elected Voting Member of the IFS Technical Committee of the IEEE Signal Processing Society and serves as an Associate Editor of the IEEE Trans. Image Processing, IEEE Signal Processing Letters and IET Biometrics.

报告内容简介:

Image recognition handles high-dimensional data that contains rich information. Fully utilizing the rich information in image undoubtedly increases the possibilities of solving difficult real world problems such as identifying people, object and biomedical image analysis. Machine learning from the training database is a solution to extract effective features from the high dimensional image for classification. This speech reviews various research efforts and technologies developed in solving difficult real world vision and image recognition problems. The speech will be far more than just PCA and LDA. The sparse representation-based classifier (SRC) significantly differentiates itself from the other classifiers aspects. The analysis of the merits and limitations of SRC pave the way for us to investigate how the recent developments solve problems and overcome the limitations of SRC, which bring the sparse representation-based image classification to a significantly higher level. Finally, deep learning in vision and image recognition, CNN, is explored and its merits and limitations are investigated.

【打印文章】 【添加收藏】