A MACHINE VISION SYSTEM USING IMMUNO‐FLUORESCENCE MICROSCOPY FOR RAPID RECOGNITION OF SALMONELLA TYPHIMURIUM

Abstract

The objective of this research was to develop an automated system using image processing and statistical modeling techniques to identify and enumerate bacteria on slides containing Salmonella typhimurium. Pictures of bacterial cells were acquired with a CCD camera attached to a motorized fluorescence microscope. A shape boundary modeling technique, based on the use of circular autoregressive model parameters, was used. A minimum‐distance classifier was trained with ten images belonging to each shape class (rod shape and circle shape). Experimental results showed that the model parameters could be used as descriptors of shape boundaries detected in digitized binary images of bacterial cells. In spite of the advantages of human vision, the differences between the computer and a bacteriologist in recognizing and counting of Salmonella cells were less than 8%. The computer analyzed each image in approximately 5 s (a total of 2 h including sample preparation), while the bacteriologist spent an average of 1 min for each image.

Rapid Detection of Microorganisms Using Image Processing Parameters and Neural Network

“…An image analysis procedure was developed (Schonholzer et al 2002) for the detection of bacterial cells in foods. This technique was improved (Trujillo et al 2001) by using a multi-plane focusing algorithm. Advantages of the confocal microscope were elaborated over the light microscope (Takeuchi and Frank 2001) and provided the applications of confocal microscopy.…”

“…Geometrical parameters alone cannot be used for identification and classification of microorganisms as microorganisms can have varied geometrical parameters in their growth phase. Also, the cells can be in random orientations on the slide when their images are captured (Trujillo et al 2001;Huang 1999). Therefore, there is a requirement to incorporate optical and textural features from image analysis.…”

Textural Characteristics of Five Microorganisms for Rapid Detection Using Image Processing

“…2002) for bacterial cells in foods. This technique has been improved (Trujillo et al. 2001) by using a multiplane focusing algorithm.…”

“…Geometrical parameters alone cannot be used for identification and classification of microorganisms as microorganisms can have varied geometrical parameters in their growth phase. Also, the cells can be in random orientations on the slide when their images are captured (Huang 1999; Trujillo et al. 2001).…”

A survey for the applications of content-based microscopic image analysis in microorganism classification domains

“…The work in Trujillo et al (2001) applies image segmentation, shape features and a minimum-distance classifier to solve a two-class MM classification problem. In the experiment, ten images of each class are used for training the classifier, and 758 MMs are used for testing.…”