Fish Species Image Classification Using Convolutional Neural Networks

Abstract

This paper demonstrates the classification of various fish species using different machine learning methods. By incorporating machine learning algorithms, modeling, and training, the project classifies fish species using neural networks with the help of multiple features like length, width, and more. Ultimately, this project attempts to analyze the differences between determining fish species with PyTorch and TensorFlow. Convolutional Neural Networks (CNN) is a powerful algorithm used in image classification problems. Python has various libraries which can be used to build a model for the same purpose; the ultimate goal of this study is to see whether using different libraries will affect the accuracy. I would like to see whether new and more advanced methods can be used to classify large schools of fish rather than only in labs. I developed separate Python codes using PyTorch and TensorFlow individually. Using each code, I obtained results and, in the end, performed a comparative study between both to come to my conclusion. My main findings were that PyTorch gave a more accurate prediction than TensorFlow. I believe this was the case because the PyTorch code incorporated neural networks with more layers, so it increased the training and validation accuracy. From here, it is evident that while neither method necessarily possesses setbacks, PyTorch has a significant edge in accuracy (99.75% to 87.22%). Therefore, when scientists apply classification with CNN, PyTorch may be more optimal for producing better results.