|
Untitled Document
|
| Not a member yet? Register
for full benefits! |
|
|
|
|
|
|
Face Mining: Finding Who and When in Video
This story is from the category Graphics
Date posted: 29/04/2009
Pittsburgh Pattern Recognition, a start-up spun out from Carnegie Mellon University, has posted a face mining concept for the TV series Star Trek that allows for navigating video by character.
"We applied our state-of-the art algorithms in face detection, face tracking and face recognition to 67 Star Trek episodes over three seasons. This process automatically extracts all visible face tracks, and clusters these into a small number of same-person groupings. Currently, we recognize frontal or near-frontal tracks. In the near future, we will extend our results to non-frontal tracks as well."
See the full Story via external site: facemining.pittpatt.com
Most recent stories in this category (Graphics):
23/10/2012: How fear skews our spatial perception
30/09/2012: Taking mathematics to heart
07/09/2012: An Open Platform Improves Biomedical-Image Processing
10/08/2012: NASA's Curiosity Beams Back a Color 360 of Mars' Gale Crater
08/08/2012: What Makes Paris Look Like Paris? Software Finds Stylistic Core
08/08/2012: First BOSS Data: 3-D Map of 500,000 Galaxies, 100,000 Quasars
03/08/2012: Writing Graphics Software Gets Much Easier: New Programming Language Yields Code That’s Much Shorter and Clearer -- But Also Faster
02/08/2012: Software helps print video game characters in 3D
|
|
