Classification of Fish Ectoparasite Genus Gyrodactylus SEM Images Using ASM and Complex Network Model

• Main Authors: Ali, Rozniza, Jiang, Bo, Man, Mustafa, Hussain, Amir, Luo, Bin
• Format: Conference Object
• Language: unknown
• Published: Springer 2014
• Subjects: Gyrodactylus; classification; Active Shape Model; Complex Network; 004 Data processing & computer science; QA75 Electronic computers. Computer science; Atlantic salmon
• Online Access: https://doi.org/10.1007/978-3-319-12643-2_13; http://researchrepository.napier.ac.uk/Output/1793021

Active Shape Models and Complex Network method are applied to the attachment hooks of several species of Gyrodactylus, including the notifiable pathogen G. salaris, to classify each species to their true species type. ASM is used as a feature extraction tool to select information from hook images that can be used as input data into trained classifiers. Linear (i.e. LDA and K-NN) and non-linear (i.e. MLP and SVM) models are used to classify Gyrodactylus species. Species of Gyrodactylus, ectoparasitic monogenetic flukes of fish, are difficult to discriminate and identify on morphology alone and their speciation currently requires taxonomic expertise. The current exercise sets out to confidently classify species, which in this example includes a species which is notifiable pathogen of Atlantic salmon, to their true class with a high degree of accuracy. The results show that Multi-Layer Perceptron (MLP) is the best classifier for performing the initial classification of Gyrodactylus species, with an average of 98.36%. Using MLP classifier, only one species has been misallocated. It is essential, therefore, to employ a method that does not generate type I or type II misclassifications where G. salaris is concerned. In comparison, only K-NN classifier has managed to to achieve full classification on the G. salaris.