November 12, 2021

About the speaker

Dr. Yufeng Zheng has joined the University of Mississippi Medical Center faculty as an associate professor of Data Science in the John D. Bower School of Population Health since January 2021. He currently serves as a Graduate Program Director in the department.

Recipient of the B.S. in optical engineering in 1989, the M.S. in optical engineering/image processing in 1994 and the Ph.D. in optical engineering/image processing in 1997 from Tianjin University (one of 39 Project 985 Universities in China), Zheng served as a senior software engineer at Huawei Tech Company in Beijing from 1997-99 and senior CT imaging algorithm engineer at GE Hangwei Medical Systems Company in Beijing from 1999-2001 before moving to the U.S. A postdoctoral research associate at the University of Louisville, Kentucky, from 2001-05, Zheng joined the Alcorn State University faculty as an assistant professor in 2006 and earned promotion to associate professor in 2012 and professor in 2019. Patent holder of a face recognition system and method using face pattern words and face pattern bytes, Zheng has been well funded ($2.4M total) as the PIs of several research grants. The author or coauthor of three books, six book chapters, 24 articles in peer-reviewed journals and 56 journal papers, Zheng’s research interests include image procession and pattern recognition; neural network and artificial intelligence; information fusion (image/score fusion), biometrics (facial recognition); machine learning and computer vision; and computer-aided diagnosis (medical imaging).

Hope of AI -An Overview of CNN From Human Vision to Autonomous Applications

When talking about AI now, we always link to convolutional neural network (CNN). When mentioning AI applications we all know the story of CNN image classification based on ImageNet. CNNs have become very successful in many applications such as face recognition, voice recognition, language translation, and game playing. Do we really understand and then control CNNs? Is there any connection between CNNs and human vision? What is the trend of CNNs? This seminar begins with a review of popular CNN models: AlexNet, VGG-19, ResNet-101 and Inception- v3. Then dig in the CNN to explore their filters and features. The difference between CNN and traditional image processing will be highlighted. Several CNN applications and experimental results are presented, which include shape classification, cancer detection, vineyard canopy prediction, and night vision colorization.