中文
Home / News & Events / Events / Content

Unconstrained Face Recognition

Release time:March 4, 2019

Topic:Unconstrained Face Recognition

Speaker: Prof. Anil K. Jain  (ACM Fellow, IEEE Fellow), Michigan State University

Time:9:30 AM, March 6

Venue:No. 8 Conference Room, New Main Building

Abstract:

Advancements in state-of-the-art face recognition (FR) algorithms can be credited to several factors, including the availability of faster processors and cheap storage, utilization of deep convolutional neural networks (DCNN), and the availability of large and increasingly challenging training and testing data. We present a brief overview of the evolution of publicly available face datasets, a characterization of each dataset, and summarize key observations that have enabled the tremendous improvements in FR performance, particularly for unconstrained FR. Publicly available benchmark face datasets can be categorized into three types based upon their collection method: controlled (e.g., ID card photos), limited unconstrained (e.g., social media postings), and unconstrained (e.g., surveillance videos). While automated solutions for controlled and limited unconstrained FR data are available, recognition of unconstrained faces is a challenge. In this talk we will present our ongoing work on unconstrained video-based face recognition.

Biography of the Speaker:

Anil K. Jain is a University Distinguished Professor at Michigan State University where he has taught since 1974. His area of research is pattern recognition, computer vision, and biometrics. ISI has designated him as a highly cited author (https://scholar.google.com/citations?user=g-_ZXGsAAAAJ&hl=en). Prof. Jain served as the Editor-in-Chief of the IEEE Transactions on Pattern Analysis & Machine Intelligence, the flagship journal in computer vision. He has been awarded Guggenheim, Humboldt Fulbright research and King Sun Fu awards. Prof. Jain was elected to the United States National Academy of Engineering, Indian National Academy of Engineering and the World Academy of Sciences.


School of Computer Science and Engineering