论文-6071-generative-shape-models-joint-text-recognition-and-segmentation-with-very-little-training-data.pdfVIP

Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data Xinghua Lou, Ken Kansky, Wolfgang Lehrach, CC Laan Vicarious FPC Inc., San Francisco, USA Bhaskara Marthi, D. Scott Phoenix, Dileep George Vicarious FPC Inc., San Francisco, USA Abstract Abstract: We demonstrate that a generative model for object shapes can achieve