Leveraging Feature Fusion of Image Features and Laser Reflectance for Automated Fish Freshness Classification

Abstract

Highlights What are the main findings? A novel method for three-level fish freshness classification was developed by combining single-wavelength (940 nm) laser reflectance and deep learning-based RGB image features. This method uses a low-cost, consumer-grade laser sensor and can potentially be integrated into smartphone-level platforms in the future. The proposed multimodal approach achieved average accuracy of 88.44% in classifying fish freshness into three levels (Day 1, Day 2, Day 3). What are the implications of the main finding? The fusion of laser and image data significantly improves the reliability and objectivity of freshness detection compared to single-modality approaches. This study provides a comprehensive dataset and an effective framework that can support future research in non-destructive food quality classification.Highlights What are the main findings? A novel method for three-level fish freshness classification was developed by combining single-wavelength (940 nm) laser reflectance and deep learning-based RGB image features. This method uses a low-cost, consumer-grade laser sensor and can potentially be integrated into smartphone-level platforms in the future. The proposed multimodal approach achieved average accuracy of 88.44% in classifying fish freshness into three levels (Day 1, Day 2, Day 3). What are the implications of the main finding? The fusion of laser and image data significantly improves the reliability and objectivity of freshness detection compared to single-modality approaches. This study provides a comprehensive dataset and an effective framework that can support future research in non-destructive food quality classification.Abstract Fish is important for human health due to its high nutritional value. However, it is prone to spoilage due to its structural characteristics. Traditional freshness assessment methods, such as visual inspection, are subjective and prone to inconsistency. This study proposes a novel, cost-effective hybrid methodology for automated three-level fish freshness classification (Day 1, Day 2, Day 3) by integrating single-wavelength laser reflectance data with deep learning-based image features. A comprehensive dataset was created by collecting visual and laser data from 130 mackerel specimens over three consecutive days under controlled conditions. Image features were extracted using four pre-trained CNN architectures and fused with laser features to form a unified representation. The combined features were classified using SVM, MLP, and RF algorithms. The experimental results demonstrated that the proposed multimodal approach significantly outperformed single-modality methods, achieving average classification accuracy of 88.44%. This work presents an original contribution by demonstrating, for the first time, the effectiveness of combining low-cost laser sensing and deep visual features for freshness prediction, with potential for real-time mobile deployment.