Object Proposals for Text Extraction in the Wild

TL;DR

This paper explores the application of Object Proposals techniques to scene text understanding, introducing a new method tailored for text that outperforms existing generic approaches in quality and efficiency.

Contribution

A novel Object Proposals algorithm specifically designed for text, demonstrating superior performance over generic methods in scene text extraction.

Findings

Our method produces higher quality word proposals.

It is more efficient than existing generic Object Proposals methods.

The source code is publicly available for further research.

Abstract

Object Proposals is a recent computer vision technique receiving increasing interest from the research community. Its main objective is to generate a relatively small set of bounding box proposals that are most likely to contain objects of interest. The use of Object Proposals techniques in the scene text understanding field is innovative. Motivated by the success of powerful while expensive techniques to recognize words in a holistic way, Object Proposals techniques emerge as an alternative to the traditional text detectors. In this paper we study to what extent the existing generic Object Proposals methods may be useful for scene text understanding. Also, we propose a new Object Proposals algorithm that is specifically designed for text and compare it with other generic methods in the state of the art. Experiments show that our proposal is superior in its ability of producing good quality word proposals in an efficient way. The source code of our method is made publicly available.