计算机应用 ›› 2013, Vol. 33 ›› Issue (05): 1463-1466.DOI: 10.3724/SP.J.1087.2013.01463

• 典型应用 • 上一篇    下一篇

基于Gabor特征与BP神经网络的屏幕显示自动校验系统

向荣,周慧娟   

  1. 浙江大学 数字技术及仪器研究所,杭州 310027
  • 收稿日期:2012-12-03 修回日期:2012-12-29 出版日期:2013-05-01 发布日期:2013-05-08
  • 通讯作者: 向荣
  • 作者简介:向荣(1988-),男,湖北嘉鱼人,硕士研究生,主要研究方向:视频监控系统、图像处理、模式识别;周慧娟(1987-),女,福建莆田人,硕士研究生,主要研究方向:视频监控系统、嵌入式系统Web。
  • 基金资助:

    国家863计划项目(2010AA09Z104)

Automatic on-screen-display verification system based on Gabor features and BP neural network

XIANG Rong,ZHOU Huijuan   

  1. Institute of Advanced Digital Technologies and Instrument, Zhejiang University, Hangzhou Zhejiang 310027, China
  • Received:2012-12-03 Revised:2012-12-29 Online:2013-05-08 Published:2013-05-01
  • Contact: XIANG Rong

摘要: 针对人工校验视频监控设备屏幕显示(OSD)效率低下、人力物力资源耗费大的问题,提出一种OSD自动校验系统,取代传统的人工校验方式。系统首先综合多种数理统计特征进行OSD定位,然后利用改进的Otsu算法进行精确字符分割并二值化,最后通过基于Gabor特征离线训练的改进型BP神经网络进行字符识别。实验结果表明,在确保92.7%识别率的前提下,该系统识别一帧OSD平均耗时53ms。

关键词: 屏幕显示校验, Gabor特征, BP神经网络, 字符分割, 快速二值化

Abstract: To deal with low efficiency and long-time consumption in verifying OSD (On-Screen-Display) of video devices, this paper devised an automatic OSD verification system. The system consisted of three parts. OSD area location was achieved by synthesizing statistical characteristics. Single character was then segmented based on improved Otsu algorithm. Finally, Gabor features and improved BP neural network were used to recognize these characters. The experimental results show that this system costs average 53ms per recognition of one frame with a recognition rate at 92.7%.

Key words: On Screen Display (OSD) verification, Gabor feature, Back Propagation (BP) neural network, character segmentation, quick binarying

中图分类号: