Improving Text Proposals for Scene Images with Fully Convolutional Networks
This work addresses scene text recognition, a domain-specific task in computer vision, and is incremental as it builds upon an existing method.
The paper tackled the problem of improving text proposals for scene text recognition by combining the original Text Proposals algorithm with Fully Convolutional Networks to enhance proposal ranking, achieving superior performance on ICDAR RRC and COCO-text datasets.
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.