DEVELOPMENT OF IMAGE PROCESSING SCHEME FOR BACTERIAL CLASSIFICATION BASED ON OPTIMAL DISCRIMINANT FEATURE
The objective of the current work is to develop anautomatic tool to identify microbiological data types usingcomputer vision and pattern recognition. Current systems relyon the subjective reading of profiles by a human expert. Thisprocess is time-consuming and prone to errors. Bacteriophage(phage) typing & Fluorescent imaging methods are used toextract representative feature profiles and identify the bacterialtypes. For feature selection of Bacterial identification system, themost successful method seems to be the appearance-basedapproach, which generally operates directly on images orappearances of bacterial objects. The image segmentation,Linear Discriminant Analysis (LDA), Direct Fractional LDA(DFLDA) and Principal Component Analysis (PCA) are thepowerful tools used for feature extraction. Then the principalcomponents are analyzed by DFLDA and simple NearestNeighbor Classifier technique is used to identify the type ofbacteria. The effectiveness of the proposed method has beenverified through experimentation using fifty popular bacterialimage databases.
S.Prabakar K.Porkumaran J.Samson Isaac
Research Scholar, Dept.of BME, Sri Ramakrishna Engg.College,Coimbatore-22.India Vice Principal, Dr.N.G.P.Institute of Technology, Coimbatore-35.India Department of Biomedical Engineering, Sri Ramakrishna Engineering College, Coimbatore-22,India
国际会议
成都
英文
1-4
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）