Back to Search Start Over

GLCM, an image analysis technique for early detection of biofilm.

Authors :
Malegori, Cristina
Franzetti, Laura
Guidetti, Riccardo
Casiraghi, Ernestina
Rossi, Riccardo
Source :
Journal of Food Engineering. Sep2016, Vol. 185, p48-55. 8p.
Publication Year :
2016

Abstract

Biofilm is a thin layer of microorganisms coated on a surface, linked by an extracellular matrix made by polysaccharides (EPS) synthesized by microorganisms themselves. The bacteria involved may deteriorate and impair the food and, if pathogenic, the microorganisms pose a risk to the consumer health. Biofilm has a particular resistance to detergents and antibiotics, making difficult its removal and surface sanification. In this work the potential of image texture, for the detection of biofilm in the early stages of development, was evaluated. The evaluation was carried out on specimens (10 × 10 cm) of steel, plastic and ceramic for food use. As biofilm forming microorganism Pseudomonas fluorescens was chosen. The specimens were placed in a photographic chamber, where images were acquired at regular time intervals, for 7 days. During the timeframe of image acquisition, biofilm formation was monitored by means of classical bacteriology. The images obtained were processed with ImageJ software for image analysis, creating a co-occurrence grey levels matrix (GLCM). The results were then processed with the software MATLAB using PLS Toolbox to perform principal component analysis (PCA). Results shown that image analysis can be a valuable tool for early detection of the biofilm development. The dynamic biofilm formation is strictly related to the samples material and in some cases, a selection of the GLCM features was needed to better distinguish clean and contaminated samples. This rapid and non-destructive method could be used for a rapid and constant monitoring of the hygienic condition of surfaces in food industry, also on-line. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
02608774
Volume :
185
Database :
Academic Search Index
Journal :
Journal of Food Engineering
Publication Type :
Academic Journal
Accession number :
115069609
Full Text :
https://doi.org/10.1016/j.jfoodeng.2016.04.001