Convolutional neural network architectures performance evaluation for fish species classification


Citation

Ahmad Faisal Mohamad Ayob, . and Hamizah Ismail, . and Aidy @ Muhamed Shawal M Muslim, . and Mohamad Fakhratul Ridwan Zulkifli, . Convolutional neural network architectures performance evaluation for fish species classification. pp. 124-139. ISSN 2672-7226

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.


Download File

Full text available from:

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.

Additional Metadata

[error in script]
Item Type: Article
AGROVOC Term: Fish
AGROVOC Term: Ai (artificial intelligence)
AGROVOC Term: Data collection
AGROVOC Term: Experiments
AGROVOC Term: Sampling
AGROVOC Term: Marine sciences
Depositing User: Mr. AFANDI ABDUL MALEK
Last Modified: 24 Apr 2025 00:55
URI: http://webagris.upm.edu.my/id/eprint/9982

Actions (login required)

View Item View Item