[talks] Talk: Kristin J. Dana, Reflectance Gradients for Material Recognition

[Jianxiong Xiao]

Speaker: Prof. Kristin J. Dana http://www.ece.rutgers.edu/~kdana/Home.html

Date: Nov 9, 2015 (today)

Time: 12:30-13:30

Place: CS 402

Title:
Reflectance Gradients for Material Recognition

Abstract:

We introduce a novel method for using reflectance to identify
materials. Reflectance offers a unique signature of a material but is
challenging to measure and use for recognizing materials due to its
high-dimensionality.  Cameras can be used to capture reflectance, but
typically from a sparse set of viewing angles.  In this work,
one-shot reflectance is captured using a unique optical camera
measuring  dense reflectance disks where the pixel coordinates
correspond to surface viewing angles.  Angular gradients computed in
this  reflectance space  reveal the material class.  These reflectance
disks encode discriminative information for efficient and accurate
material recognition. We introduce a framework called reflectance
hashing that models the reflectance disks with dictionary learning and
binary hashing.  We demonstrate  the effectiveness of reflectance
hashing for material recognition with a number of real-world
materials.