基于小波钝化的嵌入式图像处理算法研究

周文辉; 宋晓莉; 程玉华

doi:10.3788/YJYXS20163111.1085

您当前的位置：

首页 >

文章列表页 >

基于小波钝化的嵌入式图像处理算法研究

显示与图像 | 更新时间：2020-08-12

- 基于小波钝化的嵌入式图像处理算法研究
- Embedded image processing algorithm based on wavelet passivation
- 液晶与显示 2016年31卷第11期页码：1085-1091
- 作者机构：
  
  1.电子科技大学中山学院, 广东中山 528402
  2.电子科技大学自动化工程学院, 四川成都 611731
- 作者简介：
  
  [ "周文辉(1972-), 男, 广东中山人, 硕士, 副教授, 主要从事嵌入式图像处理方面的研究。E-mail:zwhmailbox@tom.com" ]
  程玉华(1978-), 男, 2007年毕业于四川大学, 获工学博士学位, 现为电子科技大学自动化工程学院教授、测试技术及仪器研究所(教育部工程中心)电力与新能源技术教研室主任, 主要从事光电精密检测技术、电力系统自动化和新能源技术方面的研究
- 基金信息：
  
  广东高校省级重点平台和重大科研项目(2015KTSCX169);中山市社会公益科技研究重大项目(2016B2119);Provincial Key Platform and Major Research Fund for Guangdong Universities(2015KTSCX169);Major Projects of Social Welfare Science and Technology Research in Zhongshan(2016B2119)
- DOI：10.3788/YJYXS20163111.1085
  中图分类号： TP394.1
- 收稿日期：2016-06-27，
  
  录用日期：2016-9-10，
  
  纸质出版日期：2016-11
- 稿件说明：
移动端阅览
周文辉, 宋晓莉, 程玉华. 基于小波钝化的嵌入式图像处理算法研究[J]. 液晶与显示, 2016,31(11):1085-1091.

Wen-hui ZHOU, Xiao-li SONG, Yu-hua CHENG. Embedded image processing algorithm based on wavelet passivation[J]. Chinese journal of liquid crystals and displays, 2016, 31(11): 1085-1091.
周文辉, 宋晓莉, 程玉华. 基于小波钝化的嵌入式图像处理算法研究[J]. 液晶与显示, 2016,31(11):1085-1091. DOI： 10.3788/YJYXS20163111.1085.

Wen-hui ZHOU, Xiao-li SONG, Yu-hua CHENG. Embedded image processing algorithm based on wavelet passivation[J]. Chinese journal of liquid crystals and displays, 2016, 31(11): 1085-1091. DOI： 10.3788/YJYXS20163111.1085.

摘要

注塑模具保护系统普遍采用模板匹配图像处理算法，其存在实时性不强、精确度不高，以及对运行环境要求严苛等问题。论文提出了基于小波钝化的嵌入式模具保护图像处理算法，该算法运行于嵌入式平台，采用小波钝化的方法凸显待测残留物，无需进行模板匹配、图像配准和较正；提出了基于像素值统计的支持向量机检测算法，以适应嵌入式平台内存小的特点；引入支持向量机分类，有效解决了图像偏移带来的误差问题。MATLAB实验测得，该算法的模腔残留物检测平均准确率为85.71%，残留物检出平均耗时0.910 s。结果表明，采用小波钝化和支持向量机的嵌入式图像处理算法，无论在算法检测精度还是算法响应速度方面均优于以灰度共生矩阵匹配算法和差影法为代表的图像匹配算法。

Abstract

Injection mold protection systems generally use template matching image processing algorithms

which have shortcomings of poor real-time

low accuracy

and stringent requirement of operating environment. This paper presents an embedded mold protection image processing algorithm based on wavelet passivation. This algorithm runs on an embedded platform and highlights residues using the wavelet passivation method without template matching

image registration and correction. A SVM(Support Vector Machine) detection algorithm based on the statistic of pixel values is proposed to make it adapt to the small memory of the embedded platform. The SVM classification is introduced as an effective solution to effectively solve the error problem caused by image shift. Experimental results by MATLAB show that for residues detection

the proposed algorithm achieves an average accuracy rate of 85.71% and average detection time of 0.910 s. The results also show that this embedded image processing algorithm using wavelet passivation and SVM outperforms other image template algorithms represented by gray level co-occurrence matrix algorithms and difference image algorithms in terms of both detection accuracy and response speed.

关键词

Keywords

references

OTAKE H. Injection molding machine using servo motor and having mold protecting function:US, 4710119[P]. 1987-12-01. http://www.freepatentsonline.com/4710119.html

RUI Y N, WANG M, ZUO D W, et al. The research on the method of ultrasonic and electric spark combined to machine diamond cupping mould[J]. Key Engineering Materials, 2006, 315-316:10-14.

WANG B, LI J, WANG C, et al. Applications on nanocomposite coating technology in plastic injection mould cavity surface treatment[J]. Advanced Materials Research, 2012, 418-420:812-817.

徐长杰. 基于机器视觉的模具保护技术研究与实现[D].武汉:华中科技大学,2013. http://cdmd.cnki.com.cn/Article/CDMD-10487-1014025758.htm

XU C J.Injecting mold protection method based on machine vision[D]. Wuhan:Huazhong University of Science and Technology, 2013. (in Chinese)

任景明,彭勇刚,韦巍. 基于光线和位置补偿的注塑机残留物图像检测方法[J]. 传感器与微系统, 2013,32(9):12-15.

REN J M, PENG Y G, WEI W. Detection method for injection molding machine residual product image based on light and position compensation[J]. Transducer and Microsystem Technologies , 2013, 32(9):12-15. (in Chinese)

彭娟. 基于机器视觉的模具检测系统技术研究[D].镇江:江苏科技大学,2013.

PENG J.Research of mold detection system based on machine vision[D]. Zhenjiang:Jiangsu University of Science and Technology, 2013. (in Chinese)

詹长明. 注塑行业中模具监视系统的设计与开发[D].厦门:厦门大学,2009. http://dspace.xmu.edu.cn/handle/2288/45359

ZHAN C M.Design and development of the mold monitoring system in plastic injection industry[D]. Xiamen:Xiamen University, 2009. (in Chinese)

马琳. 基于机器视觉的模具残留物检测系统研究[D].上海:东华大学,2015. http://cdmd.cnki.com.cn/Article/CDMD-10255-1015032610.htm

MA L.Research of residuum detection system based on industrial machine Vision[D]. Shanghai:Donghua University, 2015. (in Chinese)

陈燕芹,段锦,祝勇,等. 基于纹理特征的图像复杂度研究[J]. 中国光学, 2015,8(3):407-414.

CHEN Y Q, DUAN J, ZHU Y, et al. Research on the image complexity based on texture features[J]. Chinese Optics, 2015, 8(3):407-414. (in Chinese)

胡朱华,张瑞林,张晓文,等. 注塑生产中残留物监测系统的研究[J]. 工业控制计算机, 2011,24(5):54-55.

HU Z H, ZHANG R L, ZHANG X W, et al. Research on residue monitoring system in injection molding production[J]. Industrial Control Computer, 2011, 24(5):54-55. (in Chinese)

许佳佳. 结合Harris与SIFT算子的图像快速配准算法[J]. 中国光学, 2015,8(4):574-581.

XU J J. Fast image registration method based on Harris and SIFT algorithm[J]. Chinese Optics, 2015, 8(4):574-581. (in Chinese)

姜旭飞. 基于DM6437的模具监视系统设计与实现[D].杭州:浙江工业大学,2013. http://cdmd.cnki.com.cn/Article/CDMD-10337-1013365124.htm

JIANG X F.Design and implementation of DM6437-based mold monitoring systems[D]. Hangzhou:Zhejiang University of Technology, 2013. (in Chinese)

郑贤良,刘瑞雪,夏明亮,等. 液晶自适应光学视网膜校正成像技术研究[J]. 中国光学, 2014,7(1):98-104.

ZHENG X L, LIU R X, XIA M L, et al. Retinal correction imaging system based on liquid crystal adaptive optics[J]. Chinese Optics, 2014, 7(1):98-104.

陈莹,朱明. 多子直方图均衡微光图像增强及FPGA实现[J]. 中国光学, 2014,7(2):225-233.

CHEN Y, ZHU M. Multiple sub-histogram equalization low light level image enhancement and realization on FPGA[J]. Chinese Optics, 2014, 7(2):225-233.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

TFT-LCD表面Mura缺陷的AOI检测研究进展

基于OpenCV的双波长光纤导引光在高精度装调上的应用

基于FPGA的分段近似双边滤波算法设计与实现

基于改进YOLOv7的小目标焊点缺陷检测算法

健身行为的人体姿态估计及动作识别