Classification of Rastrelliger kanagurta and Rastrelliger brachysoma using Convulational Neural Network (CNN)

Abstract Mackerel is an important commercial caught fish for local fishermen, including Rastrelliger kanagurta and brachysoma . However, to distinguish these two species rather difficult because of their similar appearance. Convolutional Neural Network (CNN) a deep learning method that can be used classify images. One parameters contributing the level accuracy layers number applied in CNN architecture. This study aims those using with range five convolutional architectures i.e CNN1, CNN2, CNN3 CNN4, respectively. In this study, 434 images were as training group 217 each class. The validation consisted 21 class test 19 results showed provided best respectively 100% 92.6%. lowest value loss 0.000057 0.49. values models different testing reached 94.7%.