[1]周戈,曾智.采用不变矩图像匹配与直方图的仪表识别算法[J].华侨大学学报(自然科学版),2017,38(2):225-228.[doi:10.11830/ISSN.1000-5013.201702017]
　ZHOU Ge,ZENG Zhi.Instrument Recognition Algorithm Using Invariant Moment Image Matching and Histogram[J].Journal of Huaqiao University(Natural Science),2017,38(2):225-228.[doi:10.11830/ISSN.1000-5013.201702017]
点击复制

采用不变矩图像匹配与直方图的仪表识别算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第38卷
期数:
2017年第2期
页码:
225-228
栏目:
出版日期:
2017-03-20

文章信息/Info

Title:
Instrument Recognition Algorithm Using Invariant Moment Image Matching and Histogram
文章编号:
1000-5013(2017)02-0225-04
作者:
周戈1;  曾智2
1. 重庆青年职业技术学院 信息工程系, 重庆 400712;2. 中国科学院 自动化研究所, 北京 100190
Author(s):
ZHOU Ge1;  ZENG Zhi2
1. Department of Information Engineering, Chongqing Youth Vocational and Technical College, Chongqing 400712, China; 2. Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
关键词:
机床仪表;  识别算法;  不变矩;  直方图;  图像匹配;  反投影
Keywords:
machine instrument;  recognition algorithm;  invariant moment;  histogram;  image matching;  back projection
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201702017
文献标志码:
A
摘要:
为了解决当前仪表识别算法在机床仪表状态信号多变、实时性强的环境下状态识别错误的不足,设计一种基于不变矩图像匹配与直方图的在线仪表识别算法.首先,基于不变矩特征,通过图像的重心坐标获取其中心不变矩,设计图像匹配算子,并根据仪表灯的匹配度量值定位当前状态信号位置.然后,根据定位到的信号中心点坐标,提取出状态信号外接最小矩形.最后,依据信号灯颜色的直方图特性,计算出反投影直方图,实现对状态信号颜色的判断.实验结果表明:与当前机床仪表识别技术相比,面对机床仪表状态信号多变的环境时,文中算法具有更高的识别精度.
Abstract:
In order to solve the problem of failure to identify the instrument status in current instrument identification algorithm under the condition of the state signal of the machine instrument changing and the strong real-time performance, an online instrument recognition algorithm based on invariant moment image matching and histogram was designed. Firstly, image matching operator was designed by obtaining its center invariant moments with the condition through the gravity coordinates of image based on invariant moment feature, and the position of the current status signal was located according to the matching measure of the instrument light. Then the minimum rectangle of the state signal was extracted according to the coordinates of the center point of the signal, and finally, the back projection of histogram was calculated according to the characteristic of the color of the signal light obtaining the color judgment of status signal. The experimental results show that: this algorithm had a higher recognition accuracy facing the changing environment of the state signal of the machine tool compared with the current machine instrument identification technology.

参考文献/References:

[1] 李红卫,杨东升,孙一兰.智能故障诊断技术研究综述与展望[J].计算机工程与设计,2013,34(2):632-637.
[2] 李学聪,汪仁煌,刘洪江.指针表刻度中心直线拟合方法研究 [J].计算机工程与设计,2012,33(7):2726-2729.
[3] HU Ying,LIU Guizhong.Instrument identification and pitch estimation in multi-timbre polyphonic musical signals based on probabilistic mixture model decomposition [J].Journal of Intelligent Information Systems, 2013,40(1):141-158.
[4] MEISTER H,LANDWEHR M,LANG-ROTH R.Examination of spectral timbre cues and musical instrument identification in cochlear implant recipients[J].Cochlear Implants International,2014,15(2):78-86.
[5] 于向阳.仪表监控识别系统中实时性和准确性的研究[J].光学技术,2015,17(32):427-430.
[6] 房桦,明志强,周云峰.一种适用于变电站巡检机器人的仪表识别算法[J].自动化与仪表,2013,11(5):246-249.
[7] SHAHRUL N Y,LAKHMI J.An insect classification analysis based on shape features using quality threshold ARTMAP and moment invariant[J].Applied Intelligence,2012,37(1):12-30.
[8] ZENG Jinle,ZOU Yirong,DU Dong.Research on a visual weld detection method based on invariant moment features[J].Industrial Robot,2015,42(2):117-128.
[9] 王亚林.嵌入式智能仪器仪表弱故障信号的有效检测[J].计算机仿真,2014,18(15):42-47.
[10] NIKOLOVA M,WEN Youwei,CHAN R.Exact histogram specification for digital images using a variational approach[J].Journal of Mathematical Imaging and Vision,2013,46(3):309-325.
[11] 何林远.基于计算机视觉的座舱仪表识别检测方法[J].中南大学学报(自然科学版),2014,23(2):271-276.

相似文献/References:

[1]吕书龙,刘文丽.试卷识别码的集成设计与识别算法[J].华侨大学学报(自然科学版),2017,38(3):397.[doi:10.11830/ISSN.1000-5013.201703020]
　LYU Shulong,LIU Wenli.Integrated Design and Recognition Algorithm of Identification Codes in Examination Paper[J].Journal of Huaqiao University(Natural Science),2017,38(2):397.[doi:10.11830/ISSN.1000-5013.201703020]

备注/Memo

备注/Memo:
收稿日期: 2016-03-18
通信作者: 周戈(1978-),男,副教授,主要从事图像处理与目标识别、数据挖掘的研究.E-mail:cqzhouge511qn@sina.com.
基金项目: 重庆市科技攻关计划项目(2011CJ0782); 重庆市信息产业发展政策研究重点项目(K2011-52)
更新日期/Last Update: 2017-03-20