Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)
Xinghua Lou, Ken Kansky, Wolfgang Lehrach, CC Laan, Bhaskara Marthi, D. Phoenix, Dileep George
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.