Deep Feature Optimization for Enhanced Fish Freshness Assessment

TL;DR

This paper presents a three-stage deep feature optimization framework that significantly improves fish freshness assessment accuracy using visual data, combining multiple neural architectures, classical classifiers, and feature selection methods.

Contribution

It introduces a novel multi-stage approach that refines deep visual features and combines them with traditional classifiers for more reliable fish freshness evaluation.

Findings

Achieved 85.99% accuracy on FFE dataset, surpassing previous methods by up to 22.78%.

Demonstrated the effectiveness of combining Swin-Tiny features with LGBM-based feature selection.

Validated the framework's generalizability for visual quality assessment tasks.

Abstract

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.