Premium
TEXTURAL CHARACTERISTICS OF FIVE MICROORGANISMS FOR RAPID DETECTION USING IMAGE PROCESSING
Author(s) -
KUMAR S.,
MITTAL G.S.
Publication year - 2009
Publication title -
journal of food process engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.507
H-Index - 45
eISSN - 1745-4530
pISSN - 0145-8876
DOI - 10.1111/j.1745-4530.2007.00207.x
Subject(s) - microorganism , computer science , computer vision , artificial intelligence , biology , bacteria , genetics
A rapid and cost‐effective technique for identification and classification of microorganisms was explored using fluorescence microscopy and image analysis. After staining the microorganisms with fluorescent dyes (diamidino‐2‐phenyl‐indole [DAPI] and acridine orange [AO], images of the microorganisms were captured using a charge‐coupled device camera attached to a light microscope. Textural features were extracted from the images. Fluorescence emission from Bacillus thuringiensis is the highest compared with other microbes, and the emission from Lactobacillus brevis is the lowest. Various microorganisms can be differentiated using various textural features from images using AO or DAPI dye. Many textural features of the images obtained from the two dyes were different.PRACTICAL APPLICATIONS Conventional microbial detection methods take considerable time and are laborious. Rapid methods are required so that pathogens and spoilage microorganisms in foods and water can be identified and counted in a much shorter time. This work investigates image processing techniques particularly based on textural properties of the images of microorganisms. Images of microorganisms in samples can be captured using light microscopes after concentrating using centrifuge or membrane separation devices. This work will assist in developing a commercial method for rapid detection of microbes in food samples.