Bringing Sketch Recognition into Your Hands

Authors:
Gabriele Nataneli;Petros Faloutsos
Affiliations:
University of California, Los Angeles;University of California, Los Angeles
Venue:
IEEE Computer Graphics and Applications
Year:
2011

Citing 0
Cited 2

Sketched symbol recognition using Latent-Dynamic Conditional Random Fields and distance-based clustering

Pattern Recognition
New grouping and fitting methods for interactive overtraced sketches

The Visual Computer: International Journal of Computer Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sketching is an important enabling technology for modern animation interfaces. The proposed method for analyzing sketches is flexible and works consistently across a variety of software and hardware platforms. Importantly, it suits mobile devices' restrictive requirements. The associated framework builds a semantic representation of informal drawings and uses this model along with other properties of the sketch to drive an output module. The method is robust and can run in real time even on devices with limited hardware resources. It has been implemented on a Nintendo DS, an iPhone, and a regular PC. An example application employs it to drive facial expressions. The associated video shows the interface used in real time on several distinct platforms and with different output modules.