基于YOLO_v3和Tesseract5.0的高铁摩擦片编码识别算法研究Research on high speed rail brake code recognition algorithm based on YOLO_v3 and Tesseract5.0
李文龙;汪日伟;
摘要(Abstract):
为了解决高铁摩擦片编码识别应用中的字符区域分割和方向矫正问题,本文提出了基于YOLO_v3和Tesserac5.0的字符识别算法.首先,利用YOLO_v3网络截取含有字符的感兴趣区域,其次利用本文提出的单行字符矫正算法对图像进行矫正.最后,将灰度化、阈值化后的字符图像输入到基于长短期记忆网络的Tesseract5.0算法中实现字符识别.实验结果表明,本算法有效解决了字符区域提取的问题,并解决了单行字符无法使用方向检测的问题.与传统算法相比具有较好的鲁棒性和较高的精度.
关键词(KeyWords): YOLO_v3;Tesseract5.0;角度纠正
基金项目(Foundation):
作者(Author): 李文龙;汪日伟;
Email:
DOI:
参考文献(References):
- [1]林辉,蔡秉华,张艺彬,等.基于HALCON的车牌识别技术研究[J].机电工程技术,2019,48(11):8-10,201.
- [2]冯玉田,侯玖廷,顾乐易.基于Tesseract-OCR的燃气表自动识别研究[J].电子测量技术,2019,42(21):82-86.
- [3]户其修.基于OCR开源框架的常用公式识别系统的研究与实现[D].北京:北京邮电大学,2019.
- [4] Baek Y,Lee B,Han D,et al. Character region awareness for text detection[C]//Computer Vision and Pattern Recognition. Long Beach, USA:IEEE,2019.
- [5] Ren S,He K,Girshick R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
- [6] Shi B,Bai X,Yao C. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(11):2298-2304.
- [7] Tian Z,Huang W,He T,et al. Detecting text in natural image with connectionist text proposal network[C]//European Conference on Computer Vision. Amsterdam,The Netherlands:Springer,Cham,2016.
- [8] Huang G,Liu Z,Maaten L V D,et al. Densely connected convolutional networks[C]//IEEE Conference on Computer Vision and Pattern Recognition. Hawaii,USA:IEEE,2017.
- [9] Graves A,Fernandez S,Gomez F. Connectionist temporal classification:Labelling unsegmented sequence data with recurrent neural networks[C]//Machine Learning,Proceedings of the Twenty-Third International Conference. Pennsylvania. USA:ACM,2006.
- [10] Smith R,Antonova D,Lee D S. Adapting the tesseract open source OCR engine for multilingual OCR[C]//International Workshop on Multilingual OCR. Barcelona. Spain:ACM,2009.
- [11]钱伟强. Tesseract视觉耦合支持向量机的字符识别算法[J].系统仿真技术,2016,12(3):218-222,249.
- [12] Redmon J,Farhadi A. YOLOv3:An incremental improvement[J]. arXiv:Computer Vision and Pattern Recognition,2018,2(4):76-83.
- [13]徐昆,朱国华,刘文凤,等. YOLO算法在目标姿态检测中的应用[J].电子技术与软件工程,2019,9(16):181-182.
- [14]戈嘉宇,刘为嵩.基于深度学习的身份证识别系统的设计与实现[J].电子世界,2020,27(2):109-109.
- [15] Smith R. An overview of the tesseract OCR engine[C]//International Conference on Document Analysis and Recognition. Curitiba,Brazil:IEEE,2007.