Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression

doi:10.1109/TIP.2018.2855399

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 模式分析与学习团队

	Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression
	He, Wenhao1,2 ; Zhang, Xu-Yao1,2 ; Yin, Fei1,2 ; Liu, Cheng-Lin1,2,3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2018-11-01
卷号	27 期号:11 页码:5406-5419
关键词	Fully Convolutional Network Scene Text Detection Multi-oriented Multi-task
DOI	10.1109/TIP.2018.2855399
文献子类	Article
英文摘要	Multi-oriented and multi-lingual scene text detection plays an important role in computer vision area and is challenging due to the wide variety of text and background. In this paper, first, we point out the two key tasks when extending convolutional neural network (CNN)-based object detection frameworks to scene text detection. The first task is to localize the text region by a downsampled segmentation-based module, and the second task is to regress the boundaries of text region determined by the first task. Second, we propose a scene text detection framework based on fully convolutional network with a bi-task prediction module, in which one is a pixel-wise classification between the text and non-text and the other is pixel-wise regression to determine the vertex coordinates of quadrilateral text boundaries. Post-processing for word-level detection is based on non-maximum suppression, and for the line-level detection, we design a heuristic line segments grouping method to localize long text lines. We evaluated the proposed framework on various benchmarks, including multi-oriented and multi-lingual scene text data sets, and achieved the state-of-the-art performance on most of them. We also provide abundant ablation experiments to analyze several key factors in building high performance CNN-based scene text detection systems.
WOS关键词	NATURAL IMAGES
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000442340100005
资助机构	National Natural Science Foundation of China (NSFC)(61721004 ; NVIDIA NVAIL Program ; 61411136002 ; 61733007 ; 61633021)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/21861]
专题	自动化研究所_模式识别国家重点实验室_模式分析与学习团队
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	He, Wenhao,Zhang, Xu-Yao,Yin, Fei,et al. Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(11):5406-5419.
APA	He, Wenhao,Zhang, Xu-Yao,Yin, Fei,&Liu, Cheng-Lin.(2018).Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(11),5406-5419.
MLA	He, Wenhao,et al."Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.11(2018):5406-5419.