# Improving Text Proposals for Scene Images with Fully Convolutional Networks

Source: [Improving Text Proposals for Scene Images with Fully Convolutional Networks](<https://www.sota2.com/research/paper/68fa63201e209131ce9fd118>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:34:16.778Z

Authors: Dena Bazazian, Raul Gomez, Anguelos Nicolaou, Lluis Gomez, Dimosthenis Karatzas, Andrew D. Bagdanov

Published: 2017-02-16T18:56:53.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1702.05089>)

[PDF](<https://arxiv.org/pdf/1702.05089.pdf>)