A pooling based scene text proposal technique for scene text reading in the wild

PATTERN RECOGNITION

卷:87

Article

Dinh NguyenVan^1,5  Lu, Shijian²  Tian, Shangxuan³  Ouarti, Nizar^1,5  Mokhtari, Mounir^4,5 

[1] Univ Paris 06, Sorbonne Univ, 4 Pl Jussieu, F-75252 Paris 05, France

[2] Nanyang Technol Univ, Nanyang Ave, Singapore 639798, Singapore

[3] Tencent Co LTD, Gaoxinnanyi Ave,Southern Dist Hitech Pk, Shenzhen 518057, Peoples R China

[4] Inst Mines Telecom, 37-39 Rue Dareau, F-75014 Paris, France

[5] CNRS, Image & Pervas Access Lab, UMI 2955, I2R, 1 Fusionopolis Way,21-01 Connexis South Tower, Singapore 138632, Singapore

关键词: Scene text proposal;    Pooling based grouping;    Scene text detection;    Scene text reading;    Scene text spotting;   

DOI  :  10.1016/j.patcog.2018.10.012

来源: Elsevier

【 摘 要 】

Automatic reading texts in scenes has attracted increasing interest in recent years as texts often carry rich semantic information that is useful for scene understanding. In this paper, we propose a novel scene text proposal technique aiming for accurate reading texts in scenes. Inspired by the pooling layer in the deep neural network architecture, a pooling based scene text proposal technique is developed. A novel score function is designed which exploits the histogram of oriented gradients and is capable of ranking the proposals according to their probabilities of being text. An end-to-end scene text reading system has also been developed by incorporating the proposed scene text proposal technique where false alarms elimination and words recognition are performed simultaneously. Extensive experiments over several public datasets show that the proposed technique can handle multi-orientation and multi-language scene texts and obtains outstanding proposal performance. The developed end-to-end systems also achieve very competitive scene text spotting and reading performance. (C) 2018 Elsevier Ltd. All rights reserved.

【 授权许可】

Free