基于自适应特征提取的数显仪表识别系统

发布时间：2018-06-16 02:48

本文选题：数显仪表识别 + 自适应特征提取　；参考：《现代电子技术》2017年24期

【摘要】：为了适应数显仪表各种不同的室外环境,建立了自适应于不同光照条件下的仪表自动识别系统。针对数显仪表图像的点亮区域多为红色,不亮部分偏灰白的特征,设计基于RGB彩色空间滤波方法,较好地保留了点亮区域的亮度信息;并提出改进的最大类间方差法,实现了数显仪表图像字符的自适应提取。根据数显仪表数字特征信息,采用穿线识别法,实现了数显仪表的自动识别。通过大量实测实验表明,提出的自适应特征提取算法对不同角度、不同光照环境拍摄的仪表图像都有良好的适应性,应用于数显仪表自动识别系统可得到95%的识别准确率,平均运行时间为1.136 s。
[Abstract]:In order to adapt to all kinds of outdoor environment of digital display instrument, an automatic instrument recognition system is established, which adapts to different illumination conditions. In view of the fact that the lighting area of the digital display instrument image is mostly red and the partial gray is not bright, a color space filtering method based on RGB is designed to better retain the brightness information of the illuminated area, and an improved maximum inter-class variance method is proposed. The adaptive character extraction of digital display instrument image is realized. According to the digital characteristic information of digital display instrument, the automatic recognition of digital display instrument is realized by using the method of wire piercing recognition. A large number of experiments show that the proposed adaptive feature extraction algorithm has good adaptability to the instrument images taken from different angles and different illumination environments, and the recognition accuracy of 95% can be obtained by applying it to the automatic recognition system of digital display instruments. The average running time is 1.136 s.
【作者单位】：华北水利水电大学电力学院;华北水利水电大学信息工程学院;
【基金】：国家自然科学基金资助项目(51609086) 河南省科技攻关项目(142300410173)
【分类号】：TM930;TP391.41

【相似文献】