arXiv Analytics

Sign in

arXiv:1705.05483 [cs.CV]AbstractReferencesReviewsResources

WordFence: Text Detection in Natural Images with Border Awareness

Andrei Polzounov, Artsiom Ablavatski, Sergio Escalera, Shijian Lu, Jianfei Cai

Published 2017-05-15Version 1

In recent years, text recognition has achieved remarkable success in recognizing scanned document text. However, word recognition in natural images is still an open problem, which generally requires time consuming post-processing steps. We present a novel architecture for individual word detection in scene images based on semantic segmentation. Our contributions are twofold: the concept of WordFence, which detects border areas surrounding each individual word and a novel pixelwise weighted softmax loss function which penalizes background and emphasizes small text regions. WordFence ensures that each word is detected individually, and the new loss function provides a strong training signal to both text and word border localization. The proposed technique avoids intensive post-processing, producing an end-to-end word detection system. We achieve superior localization recall on common benchmark datasets - 92% recall on ICDAR11 and ICDAR13 and 63% recall on SVT. Furthermore, our end-to-end word recognition system achieves state-of-the-art 86% F-Score on ICDAR13.

Related articles: Most relevant | Search more
arXiv:1612.08185 [cs.CV] (Published 2016-12-24)
Deep Probabilistic Modeling of Natural Images using a Pyramid Decomposition
arXiv:1812.07059 [cs.CV] (Published 2018-12-06)
Simultaneous Recognition of Horizontal and Vertical Text in Natural Images
arXiv:1412.6626 [cs.CV] (Published 2014-12-20)
The local low-dimensionality of natural images