计算机科学
人工智能
帧(网络)
文本检测
计算机视觉
文本识别
跟踪(教育)
端到端原则
光学(聚焦)
模式识别(心理学)
图像(数学)
心理学
教育学
电信
光学
物理
作者
Xiaobing Wang,Yingying Jiang,Shuli Yang,Xiangyu Zhu,Wei Li,Pei Fu,Hua Wang,Zhenbo Luo
出处
期刊:Proceedings of the ... International Conference on Document Analysis and Recognition
[Institute of Electrical and Electronics Engineers]
日期:2017-11-01
卷期号:: 1255-1260
被引量:37
标识
DOI:10.1109/icdar.2017.207
摘要
Text detection and recognition in scene images and videos attract much attention in computer vision recently. However, most existing text detection and recognition methods only focus on static images. In this paper an end-to-end scene text recognition method based on multi frame tracking is proposed for text in videos, in which temporal information is employed to improve performance. First, an end-to-end text recognition method based on a unified deep neural network is used to detect and recognize text in each frame of the input video. Then, multi frame text tracking is employed through associations of texts in current frame and several previous frames to obtain final results. Experiments on ICDAR datasets demonstrate that the proposed method outperforms the state-of-the-art methods in end-to-end video text recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI