Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (1): 161-167.DOI: 10.3778/j.issn.1002-8331.1910-0008

Previous Articles     Next Articles

Natural Scene Text Detection Combined with Bounding Box Calibration

FANG Chengzhi, HUO Xinglong, CHENG Youcheng   

  1. College of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
  • Online:2021-01-01 Published:2020-12-31

联合边界框校准的自然场景文本检测

方承志,火兴龙,程宥铖   

  1. 南京邮电大学 电子与光学工程学院,南京 210023

Abstract:

A text detection method based on deep learning is proposed for multi-directional text objects in natural scenes. When designing the anchor, the directional feature of the anchor is removed but the aspect ratio feature is preserved. When covering the same aspect ratio range, the number of anchors is reduced, thereby alleviating the influence of the imbalance of positive and negative samples in dense sampling. In  addition, in the post-processing stage of the method, a bounding box calibration algorithm is proposed, which uses the Maximally Stable Extremal Region(MSER) to obtain the character edge information, and then shrinks or expands the bounding box through rule-based logic judgment, thereby achieving the purpose of  bounding box calibration. The effectiveness of the proposed bounding box calibration algorithm is verified by testing and comparison on the public dataset ICDAR2015.

Key words: text detection, natural scene, category imbalance, bounding box calibration

摘要:

针对自然场景下多方向文本对象,提出一种基于深度学习的文本检测方法。该方法在设计锚框时剥离锚框的方向特征但保留其长宽比特征,在覆盖相同长宽比范围时,锚框设计数量减少,从而缓解采样密集时正负样本类别失衡的影响。在方法的后处理阶段,提出一种边界框校准算法,该算法利用最大稳定极值区域(MSER)获取字符边缘信息,通过基于规则的逻辑判断,对边界框进行收缩或膨胀操作,从而达到边界框校准目的。通过在公开数据集ICDAR2015上的测试与比较,验证了所提边界框校准算法的有效性。

关键词: 文本检测, 自然场景, 类别失衡, 边界框校准