机械工件数字识别的二值化算法研究

高潮; 常永鑫; 郭永彩

光电工程, 2010, 37 (6): 1, 网络出版: 2010-09-07

机械工件数字识别的二值化算法研究

Study on Binarization Algorithm for the Mechanical Workpiece Digital Recognition

论文大纲

高潮常永鑫郭永彩

作者单位

重庆大学光电技术及系统教育部重点实验室，重庆 400030

机械工件图像二值化全局阈值动态阈值 mechanical workpiece image binarization global threshold dynamic threshold

摘要

分析了基于LOG 算子的局部动态阈值和基于最大类间方差的全局阈值算法的基本原理，讨论了他们在机械工件数字识别中二值化的具体实现方法。针对动态阈值和全局阈值各自的优点，结合工件字符图像的特点，提出了LOG 算子的局部动态阈值和基于最大类间方差的全局阈值相结合的新方法：首先用LOG 算子的局部动态阈值算法增强字符的细节信息，较好的区分了易混淆的数字。然后利用最大类间方差的全局阈值算法对背景进行二值化。该综合算法的计算复杂度、执行时间、二值化效果以及适用范围等方面均有较佳表现，并已应用于实际系统，取得了较好的实验结果。

Abstract

The basic principles of algorithm based on the LOG operator’s local dynamic threshold and the maximum between clusters variance’s global thresholds are respectively analyzed. The specific algorithm of binarization is detailedly discussed in digital recognition of mechanical workpiece. For their advantages of dynamic threshold and global threshold and in view of the characteristics of workpiece character, a new method is proposed and combines the local dynamic threshold grounded on the LOG operator with the global threshold of maximum between clusters variance. To begin with, the confusing and resemblant figures characters can be easily distinguished by using local dynamic threshold algorithm of LOG operator to enhance the details of characters. And then the binarization of image background is executed by use of the global threshold algorithm of maximum between class clusters. The integrated algorithm has good performance in many aspects such as computational complexity, implementation time, binarization effects and the scope of application. It has been applied to the actual system and achieves good results.

参考文献

[1] . 利用Hough 变换和先验知识的车牌字符分割算法[J]. 计算机学报, 2004, 27(1): 130-135.

. Segmenting Characters of License Plate by Hough Transformation and the Prior Knowledge[J]. Chinese Journal of Comoputers, 2004, 27(1): 130-135.

[2] 田雪冰，韩绍坤. 零件钢印号码自动识别预处理算法研究[J]. 光学技术，2006，32(S1)：557-559.

TIAN Xue-bing，HAN Shao-kun. Image preprocess research on the automation recognition technology of workpiece steel seal number [J]. Optical Technique，2006，32(S1)：557-559.

[3] 周小龙，张小洪，冯欣. 基于视觉显著图的车牌定位算法[J]. 光电工程，2009，36(11)：145-150.

ZHOU Xiao-long，ZHANG Xiao-hong，FENG Xin. A Novel License Plate Localization Algorithm Based on Saliency Map [J]. Opto-Electronic Engineering，2009，36(11)：145-150.

[4] 刘成云，陈振学，马于涛. 自适应阈值的小波图像去噪[J]. 光电工程，2007，34(6)：77-81.

LIU Cheng-yun ， CHEN Zhen-xue ， MA Yu-tao. Adaptive wavelet thresholding method for image denoising [J]. Opto-Electronic Engineering，2007，34(6)：77-81.

[5] . 车牌图像自动识别系统预处理算法研究[J]. 武汉大学学报:工学版, 2006, 39(3): 131-134.

. Study on method of pre-processing on vehicle license plate image recognition system[J]. Engineering Journal of Wuhan University, 2006, 39(3): 131-134.

[6] 王延杰，宋建中. 一种实时自适应图像二值化方法[J]. 光学精密工程，1994，2(5)：17-21.

WANG Yan-jie，SONG Jian-zhong. An Adaptive Method for Image Binarization in Real-Time [J]. Optics and Precision Engineering，1994，2(5)：17-21.

[7] . Adaptive fingerprint image enhancement with fingerprint image quality analysis[J]. Image and Vision Computing(S0262-8856), 2006, 24(1): 101-110.

[8] . Two preprocessing techniques based on grey level and geometric thickness to improve segmentation results[J]. Pattern Recognition Letters(S0167-8655), 2006, 27(3): 160-166.

[9] . Automatic license plate recognition[J]. IEEE Transactions on Intelligent Transportation Systems(S1524-9050), 2004, 5(1): 42-53.

高潮, 常永鑫, 郭永彩. 机械工件数字识别的二值化算法研究[J]. 光电工程, 2010, 37(6): 1. GAO Chao, CHANG Yong-xin, GUO Yong-cai. Study on Binarization Algorithm for the Mechanical Workpiece Digital Recognition[J]. Opto-Electronic Engineering, 2010, 37(6): 1.

机械工件数字识别的二值化算法研究

关于本站 Cookie 的使用提示

全站搜索

机械工件数字识别的二值化算法研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索