Timezone: »

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
Xinghua Lou · Ken Kansky · Wolfgang Lehrach · CC Laan · Bhaskara Marthi · D. Phoenix · Dileep George

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #86 #None

We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods. In addition to transcribing text from challenging images, our method performs fine-grained instance segmentation of characters. We show that our model is more robust to both affine transformations and non-affine deformations compared to previous approaches.

Author Information

Xinghua Lou (Vicarious FPC Inc)
Ken Kansky (Vicarious FPC, Inc.)
Wolfgang Lehrach (Vicarious)
CC Laan
Bhaskara Marthi (Vicarious)
D. Phoenix
Dileep George (Vicarious)

Before cofounding Vicarious, Dileep was CTO of Numenta, an AI company he cofounded with Jeff Hawkins and Donna Dubinsky. Before Numenta, Dileep was a Research Fellow at the Redwood Neuroscience Institute. Dileep has authored 22 patents and several influential papers on the mathematics of brain circuits. Dileep's research on hierarchical models of the brain earned him a PhD in Electrical Engineering from Stanford University. He earned his MS in EE from Stanford and his BS from IIT in Bombay.

More from the Same Authors