We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
联合边界框校准的n然场s文本柃测.
- Authors
方承志; 火兴龙; 程宥铖
- 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.
- Publication
Journal of Computer Engineering & Applications, 2021, Vol 57, Issue 1, p161
- ISSN
1002-8331
- Publication type
Article
- DOI
10.3778/j.issn.l002-8331.1910-0008