in office

 Ko Nishino, Ph.D.

  Department of Computer Science
  College of Computing and Informatics
  Drexel University


  • Check out our latest papers on material recognition:
    • Material Recognition from Local Appearance in Global Context
      G. Schwartz and K. Nishino [ arXiv ]
    • Integrating Local Material Recognition with Large-Scale Perceptual Attribute Discovery
      G. Schwartz and K. Nishino [ arXiv ]
  • Updated PSReg to work with the latest FOX Toolkit, in case there is anybody still interested in the code.
  • Our new paper on discovering visual material traits: intermediate representations of local material appearance (what makes materials look the way they look). Our key idea is to probe human material perception via simple yes/no questions to extract the underlying representation that enables visual discrimination of materials locally (i.e., without knowledge of global context like object shape). We confirm that the discovered visual attributes can be combined with boolean algebra to match semantically meaningful attributes (e.g., smooth and shiny).
    • Automatically Discovering Local Visual Material Attributes
      G. Schwartz and K. Nishino,
      in Proc. of IEEE Conference on Computer Vision and Pattern Recognition CVPR'15, Jun., 2015 [ PDF ]
    Please also check out our preceding work on fully-supervised visual material traits.
    • Visual Material Traits: Recognizing Per-Pixel Material Context
      G. Schwartz and K. Nishino,
      in Proc. of Color and Photometry in Computer Vision (Workshop held in conjunction with ICCV'13), Dec., 2013. [ Paper PDF ] [ Slides PDF ]
    We have also released our annotations of the Flickr Materials Database which we used for these research projects.
    Visual Material Traits: Trait Annotations: We have augmented the Flickr Materials Database (FMD) of Sharan et al. with binary mask annotations for 13 visual material traits. We consistently annotated FMD images with material trait masks that highlight only local regions indiciative of each trait.
  • A talk I gave this summer that summerizes our research towards material recognition.

    Material Recognition from Images (Invited Talk at Shitsukan Symposium 2014)

  • Please check out code/database. We make available many of our code and data used in our research.

I am a Professor of Computer Science at Drexel University. Prior to joining Drexel in fall 2005, I was a postdoctoral research scientist at Columbia University. I received all my degrees from The University of Tokyo: both BE and ME in Information and Communication Engineering from the Department of Electrical and Electronical Engineering in 1997 and 1999, respectively, and PhD in Computer Science from the Department of Computer Science in 2002.

My research interests primarily lie in computer vision. In particular, I strive to develop novel models and computational algorithms to better extract, understand, and regenerate visual information from photographs and videos. To this end, my main focus centers on leveraging intrinsic structures of visual data -- the latent structures that can be found in the geometry, radiometry, and motion of real-world scenes that are not necessarily apparent to our naked eyes.

Curriculum Vitæ


Department of Computer Science
Drexel University
3141 Chestnut Street,
Philadelphia, PA 19104

Office: University Crossings 100G
Tel: (215) 895-2678
Fax: (215) 895-0545

Group Members

PhD Students Gabe Schwartz
Leizer Teran
Paras Wadaker
Past Students Steve Lombardi (PhD CS, September 2015, Oculus Research)
Geoff Oxholm (PhD CS, June 2014, Adobe Research)
Louis Kratz (PhD CS, June 2012, Curalate)
Prabin Bariya (MS CS, June 2011)
Ian Johnston (BS Math, June 2010, Boston University)
John Novatnack (MS CS, June 2008, Google)