home › event - a graph lattice approach to maintaining dense collections of subgraphs as image features

EVENT:

A graph lattice approach to maintaining dense collections of subgraphs as image features
Conferences & Talks

 

description

Document classification and indexing methods depend on having informative image features. This paper shows how large families of complex features can be built out of simpler ones through construction of a graph lattice -- a hierarchy of related subgraphs linked in a lattice. A graph lattice enables efficiency gains that make it possible to effectively employ bag-of-words methods for document classification using high-dimensional feature vectors. Each feature is itself a subgraph, and a feature vector is a count of occurrences of subgraphs in the image. The graph lattice enables methods for adaptively growing a feature space of subgraphs tailored to observed document genres. We demonstrate the approach through classification of forms containing rectilinear line art.

 

upcoming events   view all 

Additive Manufacturing for Electronics “Beyond Moore”
Janos Veres
5 December 2016 | San Francisco, CA
Conferences & Talks  

Metamaterial Frequency-Adaptive Steerable Technology (M-FAST)
6 December 2016 - 8 December 2016 | London, United Kingdom
Conferences & Talks  

The Future of Work
Stephen Hoover
12 December 2016 | Stanford, CA
Conferences & Talks  

Connecting through Play: Tech to Augment In-Person Interaction
Katherine Isbister
15 December 2016 | George E. Pake Auditorium, PARC
PARC Forum