Image analysis as a tool for quantitative phycology: a computational approach to cyanobacterial taxa identification

Abstract

Image analysis as a tool for quantitative phycology: a computational approach to cyanobacterial taxa identification Abstract In the following work we discuss the application of image processing and pattern recognition to the field of quantitative phycology. We overview the area of image processing and review previously published literature pertaining to the image analysis of phycological images and, in particular, cyanobacterial image processing. We then discuss the main operations used to process images and quantify data contained within them. To demonstrate the utility of image processing to cyanobacteria classification, we present details of an image analysis system for automatically detecting and classifying several cyanobacterial taxa of Lake Biwa, Japan. Specifically, we initially target the genus Microcystis for detection and classification from among several species of Anabaena. We subsequently extend the system to classify a total of six cyanobacteria species. Highresolution microscope images containing a mix of the above species and other nontargeted objects are analyzed, and any detected objects are removed from the image for further analysis. Following image enhancement, we measure object properties and compare them to a previously compiled database of species characteristics. Classification of an object as belonging to a particular class membership (e.g., "Microcystis," "A. smithii," "Other," etc.) is performed using parametric statistical methods. Leave-one-out classification results suggest a system error rate of approximately 3%.

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

“…In Walker and Kumagai (2000), a method is proposed to classify six cyanobacteria species in a CBMIA framework, where image segmentation and enhancing are first done, then 136 shape features are extracted and five of them are selected using a sequential forwardselection/backward-elimination algorithm, lastly a Bayes decision classifier is designed to identify different WMs. In the experimental step, an overall classification error of 2.3% is obtained.…”

“…The one on the right possesses high discriminatory power-the two distributions have little overlap. Features whose class-conditioned distributions overlap the least will have greater discriminatory power (Walker and Kumagai 2000) are used for classifying WMs. Lastly, around 1700 images are used to test the classification performance of this approach, and a mean accuracy of 78.66% is achieved.…”

“…Hence, we apply feature selection methods to shorten it for saving computation cost or extract the essential information. For example, in the work of Walker and Kumagai (2000), a 136 dimensional feature vector is shortened into a five dimensional new feature vector by the feature selection (see Fig. 16).…”

Protecting Human Health from Airborne Biological Hazardous Material by an Automatic Image Acquisition and Interpretation System

“…In [3], an image analysis method was described for the identification of colonies of nine different Penicillium species as seen after growth on a standard medium. In [4], a study of image analysis based on fluorescence microscopy images was described for the improvement of the exposure assessment of airborne microorganism.…”

“…The most used feature descriptors are the area size and the shape factor of circularity. The color information was used only in [3], and was neglected in all other studies. Not all publications included microscopic images of the microorganism; therefore, we cannot evaluate the quality of the images.…”