Saved in:
Bibliographic Details
Main Authors: Hoang, Phi-Hung, Trinh, Nam-Thuan, Tran, Van-Manh, Phan, Thi-Thu-Hong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24814
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913081809960960
author Hoang, Phi-Hung
Trinh, Nam-Thuan
Tran, Van-Manh
Phan, Thi-Thu-Hong
author_facet Hoang, Phi-Hung
Trinh, Nam-Thuan
Tran, Van-Manh
Phan, Thi-Thu-Hong
contents Assessing fish freshness is vital for ensuring food safety and minimizing economic losses in the seafood industry. However, traditional sensory evaluation remains subjective, time-consuming, and inconsistent. Although recent advances in deep learning have automated visual freshness prediction, challenges related to accuracy and feature transparency persist. This study introduces a unified three-stage framework that refines and leverages deep visual representations for reliable fish freshness assessment. First, five state-of-the-art vision architectures - ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny - are fine-tuned to establish a strong baseline. Next, multi-level deep features extracted from these backbones are used to train seven classical machine learning classifiers, integrating deep and traditional decision mechanisms. Finally, feature selection methods based on Light Gradient Boosting Machine (LGBM), Random Forest, and Lasso identify a compact and informative subset of features. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate that the best configuration combining Swin-Tiny features, an Extra Trees classifier, and LGBM-based feature selection achieves an accuracy of 85.99%, outperforming recent studies on the same dataset by 8.69-22.78%. These findings confirm the effectiveness and generalizability of the proposed framework for visual quality evaluation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Feature Optimization for Enhanced Fish Freshness Assessment
Hoang, Phi-Hung
Trinh, Nam-Thuan
Tran, Van-Manh
Phan, Thi-Thu-Hong
Computer Vision and Pattern Recognition
Artificial Intelligence
68T07, 68U10
I.5.4
Assessing fish freshness is vital for ensuring food safety and minimizing economic losses in the seafood industry. However, traditional sensory evaluation remains subjective, time-consuming, and inconsistent. Although recent advances in deep learning have automated visual freshness prediction, challenges related to accuracy and feature transparency persist. This study introduces a unified three-stage framework that refines and leverages deep visual representations for reliable fish freshness assessment. First, five state-of-the-art vision architectures - ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny - are fine-tuned to establish a strong baseline. Next, multi-level deep features extracted from these backbones are used to train seven classical machine learning classifiers, integrating deep and traditional decision mechanisms. Finally, feature selection methods based on Light Gradient Boosting Machine (LGBM), Random Forest, and Lasso identify a compact and informative subset of features. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate that the best configuration combining Swin-Tiny features, an Extra Trees classifier, and LGBM-based feature selection achieves an accuracy of 85.99%, outperforming recent studies on the same dataset by 8.69-22.78%. These findings confirm the effectiveness and generalizability of the proposed framework for visual quality evaluation tasks.
title Deep Feature Optimization for Enhanced Fish Freshness Assessment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68T07, 68U10
I.5.4
url https://arxiv.org/abs/2510.24814