TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)(2018)

引用 4|浏览66
暂无评分
摘要
We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images. (2) The extracted contour information can be used for better scene text detection. We propose two ways for learning the contour task together with the scene text detection: (1) as an auxiliary task and (2) as multi-task cascade. Extensive experiments with different benchmark datasets demonstrate that both designs improve the performance of a state-of-the-art scene text detector and that a multi-task cascade design achieves the best performance.
更多
查看译文
关键词
Task analysis,Semantics,Proposals,Feature extraction,Detectors,Image edge detection,Image segmentation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要