|本期目录/Table of Contents|

[1]李安翼,王学华*,刘 苏,等.基于线激光扫描成像技术的钢轨炉号识别算法[J].武汉工程大学学报,2018,40(03):325-328.[doi:10. 3969/j. issn. 1674?2869. 2018. 03. 019]
 LI Anyi,WANG Xuehua*,LIU Su,et al.Rail Number Recognition Algorithm Based on Line Laser Scanning Imaging Technology[J].Journal of Wuhan Institute of Technology,2018,40(03):325-328.[doi:10. 3969/j. issn. 1674?2869. 2018. 03. 019]
点击复制

基于线激光扫描成像技术的钢轨炉号识别算法(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
40
期数:
2018年03期
页码:
325-328
栏目:
机电与信息工程
出版日期:
2018-06-26

文章信息/Info

Title:
Rail Number Recognition Algorithm Based on Line Laser Scanning Imaging Technology
文章编号:
20180319
作者:
李安翼王学华*刘 苏王 灿张红霞刘 鑫申楷赟
武汉工程大学材料科学与工程学院,湖北 武汉 430205
Author(s):
LI Anyi WANG Xuehua* LIU Su WANG Can ZHANG Hongxia LIU Xing SHEN Kaiyun
School of Materials Science and Engineering, Wuhan Institute of Technology,Wuhan 430205, China
关键词:
线激光扫描成像钢轨字符识别算法多层神经网络
Keywords:
line laser scanning and imaging rail number recognition algorithm multi-layer neural network
分类号:
TP391
DOI:
10. 3969/j. issn. 1674?2869. 2018. 03. 019
文献标志码:
A
摘要:
为了解决人工识别钢轨炉号效率低下,费时费力等问题,采用非接触式线激光扫描成像的方法对钢轨炉号进行识别,结合C#和HALCON混合编程开发了字符识别系统。该系统以线激光传感器扫描的点云数据为基础重构钢轨廓面图像,通过对图像进行中值滤波、阈值分割、图像形态学处理、字符切分等处理操作获得字符图像,然后使用多层神经网络分类器对字符进行了识别。运行结果表明炉号字符一次识别率可达96%,解决了钢轨因污损、锈蚀导致的炉号误读问题,实现了高速钢轨焊前检测过程自动化。
Abstract:
To solve the problem of low efficiency, time-consuming and labor-consuming in the process of the rail number identification by manual, this paper proposes a method of non-contact line laser scanning and imaging to identify the rail number, and develops an identification system by using hybrid programming with?C#?language?and?HALCON. The line laser sensor was used to scan and reconstruct the profile of the rail surface, and the character image was pretreated through the process of median filtering, threshold segmentation, image morphological processing, and character segmentation, and the characters of the rail number were recognized by the Multilayer Perceptron Classifier. The results indicated that the recognition rate of the rail number character was up to 96%, which solved the problem of character recognition error due to corrosion and fouling, and the automatic detection of high-speed rail welding was realized.

参考文献/References:

[1] 唐崇伟,陈唐龙. 基于面阵相机的接触轨几何参数检测系统[J]. 电气化铁道,2012,23(3):42-44. [2] 王学华,王华龙,马凡杰. 柱面喷码字符的自动算法[J]. 武汉工程大学学报,2015,37(11):43-46. [3] 张笙,严云洋,李郁峰. 热红外与可见光视频融合的运动目标检测[J]. 计算机科学,2015,45(8):86-89. [4] 申屠理锋,唐安祥. 红外成像技术在转炉钢渣检测中的应用[J]. 激光与红外, 2012,42(11):1259-1262. [5] 吴晓红. 单层神经网络的高效学习算法研究[J]. 计算机科学与应用,1998(1):49-52. [6] 熊沈蜀,周兆英. 单层神经网络在参数估计中的应用[J]. 清华大学学报(自然科学版),1996,36(4):1-6. [7] 王刚,孙晓亮. 一种基于最佳相似点对的稳健模板匹配算法[J]. 光学学报,2017,37(3):281-287. [8] LIU X Z,FEN G Z. A kernel clustering algorithm for fast training of support vector machines[J]. Journal of Donghua University(English Edition),2011,28(1):53-56. [9] WANG Y,LU C J,ZUO C P.Coal mine safety production forewarning based on improved BP neural network[J]. International Journal of Mining Science and Technology,2015(2):319-324.[10] LIANG H D, HAN J H, GUO G H. Template matching algorithm of radar beam scan type recognition [J]. Journal of Electronics (China), 2014(2):100-106. [11] TIANY J,JU X C,QI Z Q,et al. Improved twin support vector machine[J]. Science China(Mathematics),2014,22(2):417-432. [12] ASHOK K P, PAVITRA H.? An adaptive approach for the reconstruction and modeling of as-built 3D pipelines from point clouds[J]. Automation in Construction, 2016,72(12):65-78[13] 鲍磊. 高速铁路钢轨质量评估[J]. 中国冶金, 2014(11):9-13. [14] IGOR D.BM3D filter in salt-and-pepper noise removal [J]. EURASIP Journal on Image and Video Processing, 2016 ,10(1):1-11. [15] 孙一帆,张敬磊,王丝丝. 因子分析与多层神经网络组合的酒驾辨识模型研究[J]. 中国安全科学学报,2017,27(7):127-132.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2017-11-27基金项目:武汉工程大学研究生创新基金项目(CX2016020)作者简介:李安翼,硕士研究生。E-mail:397615647@qq.com*通讯作者:王学华,博士,教授。E-mail:wang_xuehua@yahoo.com引文格式:李安翼,王学华,刘苏,等. 基于线激光扫描的钢轨炉号识别算法[J]. 武汉工程大学学报,2018,40(3):325-328,339.
更新日期/Last Update: 2018-06-28