Can Chen, Ph.D.

Senior R&D Engineer

Can Chen, Ph.D. is a senior R&D engineer working remotely on Kitware’s Computer Vision Team. She focuses on developing tools for object-based detection, feature detection, motion pattern learning, and anomaly detection.

Prior to working at Kitware, Can was an R&D engineer for DGene. She was the lead algorithm developer for a deep learning-based SmartRoto system. SmartRoto aimed to alleviate manual labor for movie post-production by at least 50% using high-quality annotation. Users could select one or more targets with bounding boxes in a video, then output the tracked matte for each frame. She developed a new foreground segmentation network and a background extraction network and proposed an instance segmentation network that improved the segment boundary accuracy.

During her time at DGene, Can also was the team leader for a deep learning-based face reenactment project. She generated a 3D face representation from a 2D image for both the source actor from a single image. Then, the source’s expressions were deformation transferred to enact the target’s 3D face.

Can was a graduate intern at Honeywell while she was working on her Ph.D. She was involved in the DARPA MediFor project, where she detected manipulations introduced by the artificial blurring of images. She developed a deep learning framework for detecting and localizing forgeries (splicing and retouching) in photos via camera response function analysis. She also proposed a novel CNN framework to distinguish images that had a naturally shallow depth of field from images that were manipulated (e.g. iPhone portrait mode with dual-lens). Can built a new dataset of 178 camera response functions from modern digital cameras to analyze camera response functions, identify different camera sources, and evaluate camera response function modeling methods.

Can received her Ph.D. in computer science from the University of Delaware. She received both her master’s and bachelor’s degrees in electrical engineering from Harbin Institute of Technology.

 

Education

Ph.D. in computer science from the University of Delaware

M.S. in electrical engineering from Harbin Institute of Technology

B.S. in electrical engineering from Harbin Institute of Technology

Get to Know Can

What made you want to become a Kitwarean? I first found Kitware when I was working on the MediFor project, and I was inspired by the projects they were working on. I wanted to be on their collaborative and innovative team, continue to create great work, and grow within the company by learning new skills.

What do you love most about what you do? I love to work with computer vision because I’m a visual person, I like pictures and paintings. As people say, a picture is worth a thousand words. I love to work with deep learning because I’m a very curious person and I like to understand how things work or why things are the way they are. What can be more interesting than learning how the human brain works? I also like to brainstorm and think out of the box for my concepts. My job can be very challenging at times, but it pushes me and my senses to my full potential.

Share something interesting about yourself that is not on your resume. I’m a big LEGO fan. I have been playing with LEGOs since I was four years old. On weekends, I like to build or design my LEGO city. I design my own architecture modules based on the beautiful architecture I see in the real world. I currently have five ongoing model projects.

Publications

Can’s publication list is below. To see all of Kitware’s computer vision publications, please visit the Computer Vision Publications page.

  1. C. Chen, S. McCloskey, and J. Yu, "Analyzing Modern Camera Response Functions," in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 2019.
  2. C. Chen, S. McCloskey, and J. Yu, "Focus manipulation detection via photometric histogram analysis," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
  3. C. Chen, S. McCloskey, and J. Yu, "Image splicing detection via camera response function analysis," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017.
  4. S. Tin, J. Ye, M. Nezamabadi, and C. Chen, "3D reconstruction of mirror-type objects using efficient ray coding," in 2016 IEEE International Conference on Computational Photography (ICCP), 2016. [URL]
  5. H. Lin, C. Chen, S. Kang, and J. Yu, "Depth Recovery from Light Field Using Focal Stack Symmetry," in 2015 IEEE International Conference on Computer Vision (ICCV), 2015. [URL]
  6. C. Chen, H. Lin, Z. Yu, S. Kang, and J. Yu, "Light Field Stereo Matching Using Bilateral Statistics of Surface Cameras," in 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014. [URL]

Bibliography generated 2021-08-24-04:04:06 (4679)