标签：xpl explore rem ref ring his evel further sequence
CTPN方法的主要贡献：
1.cast the problem of text detection into localizing a sequence of fine-scale text proposals.
“We develop an anchor regression mechanism that jointly predicts vertical location and text/non-text score of each text proposal, resulting in an excellent localization accuracy. "
2.propose an in-network recurrence mechanism that elegantly connects sequential text roposals in the convolutional feature maps.
"This connection allows out detector to explore meaningful context information of text line, making it powerful to detect extremely chanllenging text reliably."
3.both methods are integrated seamlessly to meet the nature of text sequence, resulting in a unified end-to-end trainable model.
"Our method is able to handle muti-scale and multi-lingual text in a single process, avoiding further post filtering or refinement."
4."our method achieves new state-of-the-art results on a number of benchmarks, significantly improving recent results (e.g., 0.88F-measure over 0.83 on the ICDAR 2013, and 0.61 F-measure over 0.54 on the ICDAR 2015). Furthermore, it is computationally efficient, resulting in a 0.14s/image running time(on the ICDAR 2013) by using the very deep VGG16 model
标签：xpl explore rem ref ring his evel further sequence
原文地址：https://www.cnblogs.com/J14nWe1/p/14631321.html
