A Text Detection and Recognition System based on an End-to-End Trainable Framework from UAV Imagery
文献类型：会议论文
| 作者 | Qingtian Wu; Yimin Zhou |
| 出版日期 | 2018 |
| 会议日期 | 2018 |
| 会议地点 | Kuala Lumpur, Malaysia |
| 英文摘要 | In this paper, we present a UAV-based system for text (mainly English and Chinese) detection and recognition. Innovatively combing unmanned aerial vehicle with scene text recognition, the system can realize text detection and recognition in long-range air-plane images, providing an underlay for unmanned navigation and fast text information understanding. Robust text detection and accurate text recognition can be achieved by two contributions. First, a scalable engine is proposed to overlay English or Chinese text in different fonts into existing images to synthesize text images. Second, an end-to-end trainable framework combining Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) is adapted to recognize the variable-length text with a high accuracy. Experiments are performed with various videos shot in different time and outdoors to show that the proposed system can detect and recognise text information in UAV imagery robustly and effectively. |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/13851]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 推荐引用方式 GB/T 7714 | Qingtian Wu,Yimin Zhou. A Text Detection and Recognition System based on an End-to-End Trainable Framework from UAV Imagery[C]. 见:. Kuala Lumpur, Malaysia. 2018. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。