文章编号:1005-5630(2023)02-0008-10DOI:10.3969/j.issn.1005-5630.2023.002.002基于粒子群优化算法的水源微生物自动识别闵新港,黄邵祺,游少杰,戴博(上海理工大学光电信息与计算机工程学院,上海200093)摘要:水源微生物检测在水源生物安全监测等方面具有非常重要的意义,而传统的显微镜观测等方法存在效率低、需要专业人员操作等不足,为此提出了一种水源微生物自动识别方法。采集水样,并制作水源微生物图像集,编写全自动与半自动两种图像分割算法用于提取目标微生物区域,并提取6种图像特征。基于以上特征数据,研究水源微生物识别模型的优化问题:首先,优化部分特征参数;接着,融合所有特征,建立粒子群优化算法的支持向量机(supportvectormachineoptimizedbyparticleswarmoptimization,PSO-SVM)微生物识别模型,并与其他识别算法进行比较。结果表明,相比于其他3种算法,PSO-SVM能更有效地识别各种微生物,其平均识别率达到97.08%。关键词:微生物识别;图像分割;粒子群算法;支持向量机中图分类号:X835文献标志码:AAutomaticrecognitionofwatersourcemicroorganismsbasedonparticleswarmoptimizationalgorithmMINXingang,HUANGShaoqi,YOUShaojie,DAIBo(SchoolofOptical-ElectricalandComputerEngineering,UniversityofShanghaiforScienceandTechnology,Shanghai200093,China)Abstract:Thedetectionofwatersourcemicroorganismsisofgreatsignificancetothebiosafetyofwatersourceandsoon.However,thetraditionalmethodssuchasmicroscopicobservationareinefficientandneedprofessionalpersonnel.Therefore,anautomaticrecognitionmethodofmicro-organismsinwatersourceisproposed.Watersampleswerecollectedandamicroorganismsimagesetwasmade.Automaticandsemi-automaticimagesegmentationalgorithmswereproposedtoextractthetargetmicroorganismsarea,and6featureswereextracted.Themodeloptimizationproblemofwatermicroorganismsclassificationprocesswasstudied.First,theparametersofafewfeatureswereoptimized.Then,allthefeatureswerefused,andamicroorganismsrecognitionmodelofsupportvectormachineoptimizedbyparticleswarmoptimization(PSO-SVM)wasestablishedandcomparedwithotherrecognitionalgorithms.Theresultsshowthat,comparedwiththeother3recognitionalgorithms,PSO-SVMcanrecognizedifferentkindsof...