8 March 2018 Scene text detection by leveraging multi-channel information and local context
Author Affiliations +
Proceedings Volume 10609, MIPPR 2017: Pattern Recognition and Computer Vision; 106090K (2018) https://doi.org/10.1117/12.2284295
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China
As an important information carrier, texts play significant roles in many applications. However, text detection in unconstrained scenes is a challenging problem due to cluttered backgrounds, various appearances, uneven illumination, etc.. In this paper, an approach based on multi-channel information and local context is proposed to detect texts in natural scenes. According to character candidate detection plays a vital role in text detection system, Maximally Stable Extremal Regions(MSERs) and Graph-cut based method are integrated to obtain the character candidates by leveraging the multi-channel image information. A cascaded false positive elimination mechanism are constructed from the perspective of the character and the text line respectively. Since the local context information is very valuable for us, these information is utilized to retrieve the missing characters for boosting the text detection performance. Experimental results on two benchmark datasets, i.e., the ICDAR 2011 dataset and the ICDAR 2013 dataset, demonstrate that the proposed method have achieved the state-of-the-art performance.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Runmin Wang, Runmin Wang, Shengyou Qian, Shengyou Qian, Jianfeng Yang, Jianfeng Yang, Changxin Gao, Changxin Gao, } "Scene text detection by leveraging multi-channel information and local context", Proc. SPIE 10609, MIPPR 2017: Pattern Recognition and Computer Vision, 106090K (8 March 2018); doi: 10.1117/12.2284295; https://doi.org/10.1117/12.2284295


Back to Top