A close to Real-Time Intelligent System for Enumerating Total Viable Bacteria Based on Pattern Recognition Technology

Abstract:

In this paper, a novel close to real-time artificial intelligent system for enumerating Total Viable Bacteria (TVB) in drinking water was developed by using pattern recognition and machine vision technology. In order to identify the viable bacteria accurately, four shape features including circularity ratio, eccentricity, rectangularity, and compact degree, and four color features (G_Rsd, B_Rsd, H_Rsd, S_Rsd) of the stained viable bacteria image were extracted. An optimal artificial neural network was used as the bacterial recognition classifier, whose inputs were the extracted feature parameters and output was bacteria signal or non-bacteria signal. By using this intelligent system, TVB counts in each sample can be enumerated within 1 h, but the traditional Aerobic Plate Count (APC) method will take us 48 h. The comparative test also indicated that the counting results by two methods are closely correlated (R²=0.9942). This close to real-time accurate information may contribute to melioration and instauration of drinking water safety systems and risk management for TVB.

• Periodical: Applied Mechanics and Materials (Volume 741)
• Pages: 344-349
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.741.344
• Online since: March 2015
• Authors: Yun Ding*, Yong Guang Yin
• Keywords: Feature Parameters, Machine Vision, Pattern Recognition, Rapid Detection, Total Viable Bacteria

References

[1] Lepeuple A S, Gilouppe S, Pierlot E, et al. Rapid and automated detection of fluorescent total bacteria in water samples. International Journal of Food Microbiology, 2004, 92: 327-332.

DOI: 10.1016/j.ijfoodmicro.2003.08.013

[2] Martins E A, Germano P M L. Microbiological indicators for the assessment of performance in the hazard analysis and critical control points (HACCP) system in meat lasagna production. Food Control, 2008, 19: 764-771.

DOI: 10.1016/j.foodcont.2007.08.001

[3] Te Griffel M C, Meeuwisse J, de Jong P. Control of milk processing based on rapid detection of micro-organisms. Food Control, 2001, 12: 305-309.

DOI: 10.1016/s0956-7135(01)00009-3

[4] Tan B K, Watson I A, Parton R, et al. A real-time monitoring and detection instrument for analysis of the effects of O3 on bioluminescent Escherichia coli on agar surfaces—potential applications to the food industry. Innovative Food Science & Emerging Technologies, 2005, 6: 183-188.

DOI: 10.1016/j.ifset.2004.12.003

[5] Metcalfe A M, Marshall D L. Capacitance method to determine the microbiological quality of raw shrimp (Penaeus setiferus). Food Microbiology, 2004, 21: 361-364.

DOI: 10.1016/j.fm.2003.09.002

[6] Dubois J, Lewis E N, Fry Jr F S, et al. Bacterial identification by near-infrared chemical imaging of food-specific cards. Food Microbiology, 2005, 22: 577-583.

DOI: 10.1016/j.fm.2005.01.001

[7] Yin Y G, Ding Y. A close to real-time prediction method of total coliform bacteria in foods based on image identification technology and artificial neural network. Food Research International, 2009, 42: 191-199.

DOI: 10.1016/j.foodres.2008.10.006

[8] Information on http: /en. wikipedia. org/wiki/HSL_and_HSV.

[9] Cai Y J, Chen X H. The edge detection based on morphology. Computer Applications and Software, 2009, 26: 213-214.

[10] Freeman H. On the encoding of arbitrary geometric configuration. IRE Transactions on Electronic Computer, 1961, 10: 260-268.

[11] Du C J, Sun D W. Multi-classification of pizza using machine vision and support vector machine. Journal of Food Engineering, 2008, 86: 234-242.

DOI: 10.1016/j.jfoodeng.2007.10.001

[12] Schraft H, Watterworth L A. Enumeration of heterotrophs, fecal coliforms and Escherichia coli in water: comparison of 3MTM Petrifilm plates with standard plating procedures. Journal of Microbiological Methods, 2005, 60: 335-342.

DOI: 10.1016/j.mimet.2004.10.008