主题报告：应用模式识别技术去提高人们的健康、安全与生活质量
Pattern Recognition Technologies to Enhance the Health, Security, and Quality of Life
报告人：Rangachar Kasturi [University of South Florida IEEE Fellow]
报告时间：7月 06日（周五）14: 10～15: 10
报告地点：上海大学延长校区行健楼734室
邀请人：骆祥峰副研究员
报告摘要：
Humans have outstanding abilities to interpret patterns in data captured by our senses. Current machines are notoriously inept in pattern recognition abilities leading to frustrations we all experience. The field of Pattern Recognition strives to enhance the abilities of machines to extract meaningful information from data through automated analysis. We have pattern recognition technologies in action when a checkout clerk scans the barcode on a product; a retinal scan authentication permits access to a secure facility; a fingerprint database identifies a criminal suspect; a convicted criminal is released after DNA evidence clears him/her of the crime; a fragile historic document becomes a searchable file in a digital library; a brain tumor’s precise location is computed to aid the physician"s decision; and the potential paths of hurricanes are estimated. Such innovations have had a profound impact for over fifty years on the quality of life of citizens of the world and have resulted in products and services in the information technology, security, and health-care industries. Yet we have barely scratched the surface of the potential of these innovative applications and economic opportunities that pattern recognition systems are poised to deliver in the next few decades. For example, there are no systems today to automatically search and retrieve that special picture or that video clip based on your description of what you are looking for; face recognition systems perform poorly when presented with images taken with different lighting conditions; human operators are still tasked with monitoring for that rare suspicious activity by staring at a wall of monitors fed by many surveillance cameras, and specific sets of genes which contribute to increased risk for cancer remain unknown. We present an overview of the state of the art of pattern recognition technologies and briefly describe the research challenges and opportunities presented by this exciting discipline.
Brief Biography:
Rangachar Kasturi is a Professor of Computer Science and Engineering at the University of South Florida and served as its chair from 2003 to 2007. After receiving his PhD from Texas Tech University in 1982, he served as a professor at Penn State until 2003. Kasturi was president of the International Association for Pattern Recognition (IAPR) from 2002-04 and was president of the IEEE Computer Society in 2008. His research interests are in Computer Vision, Pattern Recognition and Document Image Analysis. He is a Fellow of both the IEEE and the IAPR.