Deep Feature Optimization for Enhanced Fish Freshness Assessment

2025-10-28

AI Summary

To address the subjectivity, low accuracy, and poor feature interpretability in visual assessment of fish freshness, this paper proposes a three-stage deep feature optimization framework. First, multi-source deep representations are extracted by fusing features from ResNet-50, DenseNet-121, EfficientNet-B0, ConvNeXt-Base, and Swin-Tiny. Second, LightGBM, Random Forest, and Lasso jointly perform efficient, complementary feature selection. Third, an ensemble of classical classifiers delivers the final discriminative decision. The framework significantly enhances both feature discriminability and model transparency. Evaluated on the FFE dataset, it achieves 85.99% classification accuracy—outperforming state-of-the-art methods by 8.69–22.78 percentage points. Its balanced integration of high performance and intrinsic interpretability establishes a novel paradigm for intelligent quality inspection of aquatic products.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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.

Problem

• Automating fish freshness assessment using deep visual representations
• Improving accuracy and feature transparency in freshness prediction
• Integrating deep learning with classical machine learning classifiers

Innovation

• Fine-tunes five vision architectures for baseline
• Combines deep features with classical classifiers
• Selects features using LGBM, Random Forest, Lasso