液晶与显示2016，Vol.31Issue(11)：1085-1091,7.DOI:10.3788/YJYXS20163111.1085
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
摘要
Abstract
Injection mold protection systems generally use template matching image processing algo-rithms,which have shortcomings of poor real-time,low accuracy,and stringent requirement of oper-ating 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 re-sults by MATLAB show that for residues detection,the proposed algorithm achieves an average accu-racy 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 al-gorithms represented by gray level co-occurrence matrix algorithms and difference image algorithms in terms of both detection accuracy and response speed.关键词
模具保护/图像处理/小波钝化/支持向量机Key words
mold protection/image processing/wavelet passivation/SVM分类
信息技术与安全科学引用本文复制引用
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):1085-1091,7.基金项目
广东高校省级重点平台和重大科研项目(No．2015KTSCX169) （No．2015KTSCX169）
中山市社会公益科技研究重大项目(No．2016B2119) Supported by Provincial Key Platform and Major Research Fund for Guangdong Universities (No．2015KTSCX169) （No．2016B2119）
Major Projects of Social Welfare Science and Technology Research in Zhongshan City (No．2016B2119) （No．2016B2119）
