Quantcast

Improving Text Proposals for Scene Images with Fully Convolutional Networks

Research paper by Dena Bazazian, Raul Gomez, Anguelos Nicolaou, Lluis Gomez, Dimosthenis Karatzas, Andrew D. Bagdanov

Indexed on: 16 Feb '17Published on: 16 Feb '17Published in: arXiv - Computer Science - Computer Vision and Pattern Recognition



Abstract

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 text recognition. In this paper we propose an improvement over the original Text Proposals algorithm of Gomez and Karatzas (2016), 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.