CONVOLUTIONAL NEURAL NETWORK ARCHITECTURES PERFORMANCE EVALUATION FOR FISH SPECIES CLASSIFICATION

Abstract

Fish image classification tool is important in the field of ichthyology. In this paper, we present a fish image classification benchmark comparison across different types of convolutional neural network (CNN). CNN extracts features from labeled image data to solve classification problems. CNN models were trained to classify fish images using transfer learning with data augmentation. CNN models consisting of AlexNet, GoogLeNet, and ResNet were incorporated in the benchmark tests. A dataset of 18,000 fish images across 18 categores, were split into 5,400 images for validation (30%) and 12,600 images for training (70%) dataset. Such neural network models show high accuracy up to 99.85% (AlexNet), 96.39% (GoogLeNet) and 99.51% (ResNet-50). To evaluate the performance of each framework, the analysis presented consists of classification accuracy, learning curve, validation test, top-five prediction and confusion matrix. The work presented here has shown its potential to contribute towards accurate development of state-of-the-art fish classification tools. It is envisioned that these CNN algorithms have the potential to assist in fish image classification problems with high accuracy despite visually similar features of images in the dataset.