Classification of Freshwater Zooplankton by Pre-trained Convolutional Neural Network in Underwater Microscopy

Abstract

Zooplankton is enormously diverse and fundamental group of microorganisms that exists in almost every freshwater body, determining its ecology and play a vital role in food chain. Considering the significance of zooplankton, the study of freshwater zooplankton is very essential which intensely relies on the classification of images. However, the routine manual analysis and classification is laborious, time consuming and expensive, and poses a significant challenge to experts. Thus, for recent decade much research is focused on the development of underwater imaging technologies and intelligent classification system of zooplankton. This work presents devotion to observation of freshwater zooplankton by designed underwater microscope and modeling the system for automatic classification among four different taxa. Unlike most of the existing zooplankton image classification systems, this model is trained on a comparatively small dataset collected from freshwater by designed underwater microscope. Transfer learning of pretrained AlexNet Convolutional Neural Network (CNN) model proved to be a potential approach in the system design. Among four networks trained over two datasets, the best overall classification accuracy of up to 93.1%, comparable to other existing systems was achieved on test dataset (92.5% for Calanoid and Cyclopoid (Female), 90% for Cyclopoid (Male) and 97.5% for Daphnia). Graphical User Interface (GUI) of the model constructed on MATLAB, makes it easy for the users to collect images for building database, train network and to classify images of different taxa. Moreover, the designed system is adaptable to the addition of more classes in the future.

Deep Learning Classification of Lake Zooplankton

“…The mentioned methods for automated plankton classification were principally deployed in salt-water coastal habitats. To our knowledge, the only previous work performing image classification on freshwater images is Hong et al ( 2020 ), where the data does not come from an automated system, and they study a small balanced dataset sorted in four categories (daphnia, calanoid, female cyclopoid, male cyclopoid), and obtain a maximum classification accuracy of 93%.…”

Underwater Spectral Imaging System Based on Liquid Crystal Tunable Filter

“…It is widely used for military, remote sensing detection [2], marine observation purposes [3], etc. In the 21st century, marine observation became an important debate and research topic [4,5], which presently relies on different techniques, such as satellite remote sensing based on spectral imaging, and underwater target detection based on acoustics and optical imaging. Although the methods mentioned above are well developed and can carry out continuous observation on a large scale, there are difficulties associated with underwater observation.…”

Development of Coral Investigation System Based on Semantic Segmentation of Single-Channel Images

“…[ 10 , 11 ] such as recognition, classification, and semantic segmentation, can be carried rapidly without interruption with such automatic detection and judgment [ 12 , 13 ]. To date, several researches have been reported, using the application of such detection techniques combined with different imaging methods in the aquatic environment [ 14 , 15 ]. For the coral study, both spectral imaging and RGB imaging techniques have been used to get morphological features.…”