TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild

by   Lluis Gomez-Bigorda, et al.
Universitat Autònoma de Barcelona

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 introduce a novel object proposals method that is specifically designed for text. We rely on a similarity based region grouping algorithm that generates a hierarchy of word hypotheses. Over the nodes of this hierarchy it is possible to apply a holistic word recognition method in an efficient way. Our experiments demonstrate that the presented method is superior in its ability of producing good quality word proposals when compared with class-independent algorithms. We show impressive recall rates with a few thousand proposals in different standard benchmarks, including focused or incidental text datasets, and multi-language scenarios. Moreover, the combination of our object proposals with existing whole-word recognizers shows competitive performance in end-to-end word spotting, and, in some benchmarks, outperforms previously published results. Concretely, in the challenging ICDAR2015 Incidental Text dataset, we overcome in more than 10 percent f-score the best-performing method in the last ICDAR Robust Reading Competition. Source code of the complete end-to-end system is available at https://github.com/lluisgomez/TextProposals


page 3

page 12

page 13

page 16

page 25

page 34

page 36

page 37


Object Proposals for Text Extraction in the Wild

Object Proposals is a recent computer vision technique receiving increas...

UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World

Synthetic data has been a critical tool for training scene text detectio...

Detecting Multi-Oriented Text with Corner-based Region Proposals

Previous approaches for scene text detection usually rely on manually de...

Reading Text in the Wild with Convolutional Neural Networks

In this work we present an end-to-end system for text spotting -- locali...

Learning to Segment Object Proposals via Recursive Neural Networks

To avoid the exhaustive search over locations and scales, current state-...

Random Boxes Are Open-world Object Detectors

We show that classifiers trained with random region proposals achieve st...

Neural Word Search in Historical Manuscript Collections

We address the problem of segmenting and retrieving word images in colle...

Please sign up or login with your details

Forgot password? Click here to reset