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 

Next Frontier of AI
Tolga Kurtoglu
3 May 2017 - 4 May 2017 | Istanbul, Turkey
Conferences & Talks  

Tutorial: Printing 3D Functional Objects and Devices
14 May 2017
Conferences & Talks  

Defining Your IoT Strategy: Executives as IoT Adoption Influencers (panel)
Markus Larsson, Speaker
17 May 2017 | Santa Clara, CA
Conferences & Talks  

Thinking About Security and Privacy with AI and ML (panel)
Raj Minhas, Moderator
17 May 2017 | Santa Clara, CA
Conferences & Talks