A preliminary study on automated freshwater algae recognition and classification system

Abstract

BackgroundFreshwater algae can be used as indicators to monitor freshwater ecosystem condition. Algae react quickly and predictably to a broad range of pollutants. Thus they provide early signals of worsening environment. This study was carried out to develop a computer-based image processing technique to automatically detect, recognize, and identify algae genera from the divisions Bacillariophyta, Chlorophyta and Cyanobacteria in Putrajaya Lake. Literature shows that most automated analyses and identification of algae images were limited to only one type of algae. Automated identification system for tropical freshwater algae is even non-existent and this study is partly to fill this gap.ResultsThe development of the automated freshwater algae detection system involved image preprocessing, segmentation, feature extraction and classification by using Artificial neural networks (ANN). Image preprocessing was used to improve contrast and remove noise. Image segmentation using canny edge detection algorithm was then carried out on binary image to detect the algae and its boundaries. Feature extraction process was applied to extract specific feature parameters from algae image to obtain some shape and texture features of selected algae such as shape, area, perimeter, minor and major axes, and finally Fourier spectrum with principal component analysis (PCA) was applied to extract some of algae feature texture. Artificial neural network (ANN) is used to classify algae images based on the extracted features. Feed-forward multilayer perceptron network was initialized with back propagation error algorithm, and trained with extracted database features of algae image samples. System's accuracy rate was obtained by comparing the results between the manual and automated classifying methods. The developed system was able to identify 93 images of selected freshwater algae genera from a total of 100 tested images which yielded accuracy rate of 93%.ConclusionsThis study demonstrated application of automated algae recognition of five genera of freshwater algae. The result indicated that MLP is sufficient, and can be used for classification of freshwater algae. However for future studies, application of support vector machine (SVM) and radial basis function (RBF) should be considered for better classifying as the number of algae species studied increases.

Algae through the looking glass

“…Hence, automatic identification and enumeration of microalgae by means of image analysis are powerful tools for monitoring water body conditions and provide early warning signs. Many systems have been developed for these purposes (Blackburn, Hagstr€ om, Wikner, Cuadros-Hansson, & Bjørnsen, 1998;Culverhouse et al, 2006;Embleton, Gibson, & Heaney, 2003;Gorsky, Guilbert, & Valenta, 1989;Kamath et al, 2005;Mosleh, Manssor, Malek, Milow, & Salleh, 2012;Rodenacker, Hense, J€ utting, & Gais, 2006;Santhi, Pradeepa, Subashini, & Kalaiselvi, 2013;Verikas et al, 2012;Yao, Fei, Li, Kong, & Zhao, 2007), and in the following we will shortly describe the system built by our group (Coltelli, Barsanti, Evangelista, Frassanito, & Gualtieri, 2014;Coltelli et al, 2013). Our sys- Acquisition of microscope fields.…”

A Multi-Platform Optical Sensor for In Vivo and In Vitro Algae Classification

“…The identification and classification of algae are usually performed using microscopy, where more recent efforts have been put on automating the system for the rapid, accurate recognition, and classification of algae using image processing techniques such as segmentation, shape feature extraction, pigment structure determination, and neural network grouping [4,5,6,7] and literatures cited therein. The system is slow, expensive, difficult to implement in the field, mostly target specific types of algae, and/or may not work well when images contain too many objects.…”

InCoB2012 Conference: from biological data to knowledge to technological breakthroughs

“…[47] demonstrated divide-and-conquer, random and MaxMin sampling options to reduce the dimensions of large-scale genomic data. A Malaysian group reported the results of a freshwater algae classification feasibility study at a lake near Kuala Lumpur that utilized an artificial neural network approach in image processing of algae sizes and shapes [48]. A phylogenetic reconstruction by Biswal et al .…”