PT Unknown
AU Dena Bazazian
   Raul Gomez
   Anguelos Nicolaou
   Lluis Gomez
   Dimosthenis Karatzas
   Andrew Bagdanov
TI Improving Text Proposals for Scene Images with Fully Convolutional Networks
BT 23rd International Conference on Pattern Recognition Workshops
PY 2016
AB Text Proposals have emerged as a class-dependent version of object proposals – efficient approaches to reduce the search space of possible text object locations in an image. Combined with strong word classifiers, text proposals currently yield top state of the art results in end-to-end scene textrecognition. In this paper we propose an improvement over the original Text Proposals algorithm of [1], combining it with Fully Convolutional Networks to improve the ranking of proposals. Results on the ICDAR RRC and the COCO-text datasets show superior performance over current state-of-the-art.
ER