Dr. Yao-Jen (Kevin) Chang has been with the Siemens Healthineers as a senior key expert scientist since 2011, where he conducts research on 3D computer vision and machine learning. From 2009 to 2011, he was with the School of Electrical and Computer Engineering, Cornell University as a research associate focusing on multi-view computer vision and content-based information retrieval. From 2007 to 2009, he was with the Department of Electrical and Computer Engineering, Carnegie Mellon University as a research scientist focusing on image-based synthesis and modeling. From 2003 to 2007, he served as a researcher and the vision team group leader at the Advanced Technology Center, Information & Communications Research Labs, Industrial Technology Research Institute, where he led research on real-time video-realistic speech animation and video surveillance. His research interests include computer vision, computer graphics, machine learning, and computational photography. Dr. Chang received his Ph.D. degree from the Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan in 2002.

Physics-based Computer Vision: 

Reformulate the structure from motion framework to incorporate the refractive distortion model for multi-view 3D scene reconstruction under the refractive plane.

Active Learning for Interactive 3D Reconstruction: 

Apply the active learning framework widely adopted in CBIR to the interactive 3D scene reconstruction. By quantifying the uncertainty of each region’s geometry inferred by the energy minimization, our algorithm requests feedbacks from a user to provide intuitive geometric cues on the most informative regions; thereby effectively reducing human's efforts for interactive 3D reconstruction.
 

Active Image-based Rendering with Robot-based Imaging Testbed:

Design mobile robots for active capturing and rendering of environments. 

Embedded Video Surveillance: 

Investigate distributed video surveillance networks based on miniaturized smart cameras capable of performing on-board visual analysis and video streaming. 

Software Development Toolkit for Video Surveillance:

Investigate a video surveillance architecture and framework for rapid development of video surveillance applications for home care, home security, and parking lot services.

Image-based Videorealistic Speech Animation: 

Investigate a user adaptation method for creation of image-based speech animation of a novel person with limited video corpus.

Algorithms for Key Generation based on Biometrics: 

Develop a biometrics-based cryptographic key generation mechanism for generating cryptographic keys on resource-constrained handheld devices.