Feature Fusion for Scene Text Detection

被引：4

作者：

Zhu, Zhen ^{[1
]}

Liao, Minghui ^{[1
]}

Shi, Baoguang ^{[1
]}

Bai, Xiang ^{[1
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Hubei, Peoples R China

来源：

2018 13TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS) | 2018年

基金：

中国国家自然科学基金;

关键词：

Oriented; Faster R-CNN; Feature fusion;

D O I：

10.1109/DAS.2018.60

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A significant challenge in scene text detection is the large variation in text sizes. In particular, small text are usually hard to detect. This paper presents an accurate oriented text detector based on Faster R-CNN. We observe that Faster R-CNN is suitable for general object detection but inadequate for scene text detection due to the large variation in text size. We apply feature fusion both in RPN and Fast R-CNN to alleviate this problem and furthermore, enhance model's ability to detect relatively small text. Our text detector achieves comparable results to those state of the art methods on ICDAR 2015 and MSRA-TD500, showing its advantage and applicability.

引用

页码：193 / 198

页数：6

共 41 条

[11] [Anonymous], 2016, P EUROPEAN C COMPUTE
[12] [Anonymous], 2015, CORR
[13] [Anonymous], 2016, ARXIV PREPRINT
[14] [Anonymous], 2016, P CVPR
[15] [Anonymous], 2015, ICCV
[16] [Anonymous], 2014, IEEE T IMAGE PROCESS, DOI DOI 10.1109/TIP.2014.2353813
[17] [Anonymous], 2017, P CVPR
[18] [Anonymous], 2017, P AAAI
[19] Busta M., 2017, P ICCV
[20] Dai J, 2016, PROCEEDINGS 2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), P1796, DOI 10.1109/ICIT.2016.7475036

← 1 2 3 4 5 →