|本期目录/Table of Contents|

[1]洪汉玉,王澍,朱浩,等.低对比度嵌入型钢坯字符识别方法[J].武汉工程大学学报,2012,(12):38-43.[doi:103969/jissn16742869201212010]
　HONG Han yu,WANG Shu,ZHU Hao,et al.Recognition method for lowcontrast embedded billet characters[J].Journal of Wuhan Institute of Technology,2012,(12):38-43.[doi:103969/jissn16742869201212010]
点击复制

低对比度嵌入型钢坯字符识别方法(/HTML)
分享到：

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

卷:
期数:
2012年12期
页码:
38-43
栏目:
机电与信息工程
出版日期:
2013-01-11

文章信息/Info

Title:
Recognition method for lowcontrast embedded billet characters
文章编号:
16742869(2012)12003806
作者:
洪汉玉; 王澍; 朱浩; 俞喆俊
武汉工程大学图像处理与智能控制实验室，湖北 武汉 430205
Author(s):
HONG Hanyu; WANG Shu; ZHU Hao; YU Zhejun
Laboratory for Image Processing and Intelligent Control, Wuhan Institute of Technology, Wuhan 430205, China
关键词:
图像处理; 嵌入型钢坯字符; 区域填充; 形态学去噪
Keywords:
image processing;  embedded billet characters;  region filling;  morphology denoising
分类号:
TP391
DOI:
103969/jissn16742869201212010
文献标志码:
A
摘要:
针对嵌入型钢坯字符具有低对比度、边缘特征不稳定等特点，提出基于轮廓测度LoG算子.首先使用多角度的卷积模版对图像进行卷积运算，有效地增强了字符各方向上的边缘轮廓信息，通过对零交叉点的检测获得候选区域闭合的边缘轮廓，其次使用区域填充算法对闭合轮廓区域进行填充获得候选联通域，最后根据字符与噪声在形态学特征上的差异去除噪声，进而完成字符串信息的完整提取.实验结果表明，基于边缘检测的嵌入型钢坯号识别方法识别效率高，具有较高鲁棒性，检测结果中的字符信息保留完整，能够很好用于字符识别过程，为嵌入型钢坯字符在实际生产线的应用提供了的关键技术支持.
Abstract:
Aimed at the low contrast feature and irregular edge of embedded billet character, the LoG operator based on the measure of edge was proposed. At first, the convolution masks with multiple angles were used to enhance the edge information of characters in each direction, and the closed contours were extracted through the detection of zero crossing points; Secondly, the area filling method was used to obtain the candidate connected domains; At last, the noise was eliminated according to the difference with character in morphology, therefore the information of characters was completely extracted. The experimental results show that the recognition algorithm for embedded character has a good recognition rate and stability, the information of characters is kept completely in the detection results and can be well used for the process of character recognition, which provides the key technology for the practical application of embedded billet characters.

参考文献/References:

［1］Ulupinar, Faith. Refining edges detected by a LoG operator\[J\]. Computer Vision Graphics Image Process,1990,51(3):275298.
［2］Oie, Takhiro.Adaptive LaplacianGaussian filter method for edge detection and diameter estimation of coronary arteries on cineangiograms: Applications to phantom profiles\[J\].Stems and Computers in Japan，1992,23（12）：5565.
［3］贺强, 晏立. 基于LOG和Canny算子的边缘检测算法\[J\].计算机工程,2011, 37 (3):210212.
［4］Accame, Marco. Edge detection by point classification of Canny filtered images \[J\]. Signal Processing,1997,60(1):1122.
［5］张天序.成像自动目标识别\[M\].武汉：湖北科学技术出版社，2005.
［6］Andres Huertas, Gerard Medioni. Detection of intensity changes with subpixel accuracy using LaplacianGaussian Masks\[J\]. IEEE Transaction Pattern Analysis and Machine Intelligence，1986,8(5)：644651.
［7］吴章文，杨代伦. 区域填充极点判别算法\[J\]. 计算及辅助设计与图形学学报，2003,15(8): 979983.
［8］李仪芳，刘景琳. 基于连通域算法的区域测量 \[J\]. 科学技术与工程，2008，9(8)：24922494.
［9］洪汉玉，杨义军. 基于智能多代理的复杂场景钢坯字符切分算法\[J\].光电工程,2012，39(5):91100.
［10］杨义军，洪汉玉，章秀华，等. 重轨生产线钢坯字符识别方法 \[J\]. 武汉工程大学学报，2012，34(5)：6467.
［11］洪汉玉，俞喆俊，章秀华.复杂光照条件下钢坯字符检测方法\[J\].武汉工程大学学报，2012，34（6）：6568.
［12］洪汉玉.现代图像图形处理与分析\[M\].武汉：中国地质大学出版社，2011.
［13］VanVliet,LucasJ. Edge localization by MoG filters: multipleofGaussians\[J\].Pattern Recognition Letters,1994,15(5):485496.

相似文献/References:

[1]杨述斌,陈艳菲,程莉.交替滤波的加权形态边缘检测算法[J].武汉工程大学学报,2009,(07):88.
　YANG Shu bin,CHEN Yan fei,CHEN Li.Weight adding morphological edge detection algorithm based on alternate filtering[J].Journal of Wuhan Institute of Technology,2009,(12):88.
[2]陈念,李进,王海晖,等.双目立体视觉测量系统的研究与实现[J].武汉工程大学学报,2011,(05):101.[doi:10.3969/j.issn.16742869.2011.05.026]
　CHEN Nian,LI Jin,WANG Haihui,et al.Research and implementation of measurement system based on binocular stereo vision[J].Journal of Wuhan Institute of Technology,2011,(12):101.[doi:10.3969/j.issn.16742869.2011.05.026]
[3]宋得成１,２,徐国庆１,等.暗原色先验图像去雾改进算法[J].武汉工程大学学报,2014,(12):68.[doi:10. 3969/j. issn. 1674-2869. 2014. 012. 013]
　SONG De-cheng,XU Guo-qing,LU Jian-yong.Improved image defogging based on priori dark color[J].Journal of Wuhan Institute of Technology,2014,(12):68.[doi:10. 3969/j. issn. 1674-2869. 2014. 012. 013]
[4]秦襄培,刘　莉,郭亚娟,等.镀层厚度的自动测定[J].武汉工程大学学报,2015,37(01):64.[doi:10. 3969/j. issn. 1674-2869. 2015. 01. 014]
　,,et al.Ａｕｔｏｍａｔｉｃ ｍｅａｓｕｒｅｍｅｎｔ ｏｆ ｃｏａｔｉｎｇ ｔｈｉｃｋｎｅｓｓ[J].Journal of Wuhan Institute of Technology,2015,37(12):64.[doi:10. 3969/j. issn. 1674-2869. 2015. 01. 014]
[5]刘昌辉,帅　考,杨维荣.嵌入式视觉的测距系统设计[J].武汉工程大学学报,2015,37(04):65.[doi:10. 3969/j. issn. 1674-2869. 2015. 0４. 014]
　,Ｄｅｓｉｇｎ ｏｆ ｄｉｓｔａｎｃｅ ｍｅａｓｕｒｅｍｅｎｔ ｓｙｓｔｅｍ ｂａｓｅｄ ｏｎ ＡＲＭ ｅｍｂｅｄｄｅｄ ｖｉｓｉｏｎ[J].Journal of Wuhan Institute of Technology,2015,37(12):65.[doi:10. 3969/j. issn. 1674-2869. 2015. 0４. 014]
[6]王学华,王华龙,马凡杰,等.柱面喷码字符的自动识别算法[J].武汉工程大学学报,2015,37(11):43.[doi:10. 3969/j. issn. 1674-2869. 2015. 1１. 009]
　-,-,-,et al.Ａｕｔｏｍａｔｉｃ ｒｅｃｏｇｎｉｔｉｏｎ ａｌｇｏｒｉｔｈｍ ｏｆ ｃｙｌｉｎｄｒｉｃａｌ ｐｒｉｎｔｉｎｇ ｃｈａｒａｃｔｅｒ[J].Journal of Wuhan Institute of Technology,2015,37(12):43.[doi:10. 3969/j. issn. 1674-2869. 2015. 1１. 009]
[7]顾天雄,朱福龙*,程国开,等.隧道衬砌渗漏水红外特征模拟试验及图像处理[J].武汉工程大学学报,2017,39(01):96.[doi:10. 3969/j. issn. 1674?2869. 2017. 01. 017]
　GU Tianxiong,ZHU Fulong*,CHENG Guokai,et al.Simulation Experiment on Infrared Radiation Feature of Tunnel Lining Seepage and Image Processing[J].Journal of Wuhan Institute of Technology,2017,39(12):96.[doi:10. 3969/j. issn. 1674?2869. 2017. 01. 017]
[8]王仕仙,陈绪兵*.焊接轨迹跟踪控制中的深度视觉研究进展[J].武汉工程大学学报,2023,45(04):378.[doi:10.19843/j.cnki.CN42-1779/TQ.202303003]
　WANG Shixian,CHEN Xubing*.Progress in Vision Technology in Welding Trajectory and Control[J].Journal of Wuhan Institute of Technology,2023,45(12):378.[doi:10.19843/j.cnki.CN42-1779/TQ.202303003]

备注/Memo

备注/Memo:
收稿日期：20121116基金项目：国家自然科学基金面上项目(50975211，61175013)；湖北省自然科学基金创新群体项目（2012FFA046）；湖北省教育厅科学技术研究项目(Q20121507)作者简介：洪汉玉(1964)，男，湖北阳新人，教授，博士.研究方向：图像处理与目标识别.
更新日期/Last Update: