科研之友
微信
新浪微博
Facebook
分享链接
摘要
This letter proposes a new method for dense scene text detection anchor box labeling using single-shot multibox detection (SSD) as the base framework and VGG16 as the backbone, enhanced for scene text detection. This method can be further generalized to other detection tasks with various aspect ratios. We argue that the loU criterion used by the dense object detection framework may have low recall ratios in extreme aspect ratio cases and oriented objects, and we propose a new criterion of the anchor-labeling method for these kinds of objects. The result shows that this method has better performance on public datasets compared with the previous labeling methods.
- 出版日期2018-9
- 单位清华大学
