J
Jun-Cheng Chen
Researcher at Center for Information Technology
Publications - 99
Citations - 3459
Jun-Cheng Chen is an academic researcher from Center for Information Technology. The author has contributed to research in topics: Computer science & Facial recognition system. The author has an hindex of 23, co-authored 79 publications receiving 2355 citations. Previous affiliations of Jun-Cheng Chen include Rutgers University & University of Maryland, College Park.
Papers
More filters
Proceedings ArticleDOI
Frontal to profile face verification in the wild
Soumyadip Sengupta,Jun-Cheng Chen,Carlos D. Castillo,Vishal M. Patel,Rama Chellappa,David W. Jacobs +5 more
TL;DR: The aim of this data set is to isolate the factor of pose variation in terms of extreme poses like profile, where many features are occluded, along with other `in the wild' variations to suggest that there is a gap between human performance and automatic face recognition methods for large pose variations in unconstrained images.
Proceedings ArticleDOI
Unconstrained face verification using deep CNN features
TL;DR: An algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset as well as on the traditional Labeled Face in the Wild (LFW) dataset.
Journal ArticleDOI
Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms.
P. Jonathon Phillips,Amy N. Yates,Ying Hu,Carina A. Hahn,Eilidh Noyes,Kelsey Jackson,Jacqueline G. Cavazos,Géraldine Jeckeln,Rajeev Ranjan,Swami Sankaranarayanan,Jun-Cheng Chen,Carlos D. Castillo,Rama Chellappa,David White,Alice J. O'Toole +14 more
TL;DR: In a comprehensive comparison of face identification by humans and computers, it is found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test.
Proceedings ArticleDOI
An adaptive edge detection based colorization algorithm and its applications
TL;DR: By extracting reliable edge information, the proposed approach may prevent the colorization process from bleeding over object boundaries and integrate the proposed fast colorization scheme to a scribble-based colorization system, a modified color transferring system and a novel chrominance coding approach are investigated.
Journal ArticleDOI
Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans
Rajeev Ranjan,Swami Sankaranarayanan,Ankan Bansal,Navaneeth Bodla,Jun-Cheng Chen,Vishal M. Patel,Carlos D. Castillo,Rama Chellappa +7 more
TL;DR: An overview of deep-learning methods used for face recognition is provided and different modules involved in designing an automatic face recognition system are discussed and the role of deep learning for each of them is discussed.