计算机应用研究
計算機應用研究
계산궤응용연구
APPLICATION RESEARCH OF COMPUTERS
2010年
2期
775-777,783
,共4页
邝泳聪%欧阳高飞%谢宏威%洪始良%杨锦荣
鄺泳聰%歐暘高飛%謝宏威%洪始良%楊錦榮
광영총%구양고비%사굉위%홍시량%양금영
自动光学检测%统计学习%贝叶斯决策%缺陷检测
自動光學檢測%統計學習%貝葉斯決策%缺陷檢測
자동광학검측%통계학습%패협사결책%결함검측
automatic optical inspection (AOI)%statistical learning%Bayesian decision%defects inspection
为了减少自动光学检测系统对用户经验的依赖,提出了一种基于统计分析的PCB组装缺陷特征学习方法.该方法通过对良品和不良品样本图像的统计学习优选出分类能力强的特征,再采用最小风险贝叶斯决策得到特征分类参数.实验结果表明,该算法有效地简化了用户检测程序的编程和调试,提高了AOI的使用效率和准确率.
為瞭減少自動光學檢測繫統對用戶經驗的依賴,提齣瞭一種基于統計分析的PCB組裝缺陷特徵學習方法.該方法通過對良品和不良品樣本圖像的統計學習優選齣分類能力彊的特徵,再採用最小風險貝葉斯決策得到特徵分類參數.實驗結果錶明,該算法有效地簡化瞭用戶檢測程序的編程和調試,提高瞭AOI的使用效率和準確率.
위료감소자동광학검측계통대용호경험적의뢰,제출료일충기우통계분석적PCB조장결함특정학습방법.해방법통과대량품화불량품양본도상적통계학습우선출분류능력강적특정,재채용최소풍험패협사결책득도특정분류삼수.실험결과표명,해산법유효지간화료용호검측정서적편정화조시,제고료AOI적사용효솔화준학솔.
In order to reduce the experience-dependence of automatic optical inspection (AOI),proposed a Bayesian-based features learning for PCB assembling defects inspection.By statistical learning images of good product sample and defective product sample,selected features with better ability of classification capacity,and based on the risk minimization of Bayesian,worked out the decision parameters for feature classing.Experimental results show that the proposed method effectively simplifies the programming and debugging of user inspection application,and greatly improves the efficiency and accuracy of AOI.