Enhanced Fish Freshness Classification with Incremental Handcrafted Feature Fusion

TL;DR

This paper introduces a handcrafted feature fusion approach for fish freshness classification, combining color and texture descriptors, which significantly outperforms previous deep learning methods in accuracy and reliability.

Contribution

The study presents a novel incremental feature fusion method using handcrafted descriptors from fish eye images, enhancing freshness assessment accuracy over existing deep learning approaches.

Findings

LightGBM achieved 77.56% accuracy, 14.35% higher than previous baseline.

ANN reached 97.49% accuracy, surpassing prior best by 20.19%.

Handcrafted features provide a robust, interpretable solution for fish freshness evaluation.

Abstract

Accurate assessment of fish freshness remains a major challenge in the food industry, with direct consequences for product quality, market value, and consumer health. Conventional sensory evaluation is inherently subjective, inconsistent, and difficult to standardize across contexts, often limited by subtle, species-dependent spoilage cues. To address these limitations, we propose a handcrafted feature-based approach that systematically extracts and incrementally fuses complementary descriptors, including color statistics, histograms across multiple color spaces, and texture features such as Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrices (GLCM), from fish eye images. Our method captures global chromatic variations from full images and localized degradations from ROI segments, fusing each independently to evaluate their effectiveness in assessing freshness. Experiments on the Freshness of the Fish Eyes (FFE) dataset demonstrate the approach's effectiveness: in a standard train-test setting, a LightGBM classifier achieved 77.56% accuracy, a 14.35% improvement over the previous deep learning baseline of 63.21%. With augmented data, an Artificial Neural Network (ANN) reached 97.49% accuracy, surpassing the prior best of 77.3% by 20.19%. These results demonstrate that carefully engineered, handcrafted features, when strategically processed, yield a robust, interpretable, and reliable solution for automated fish freshness assessment, providing valuable insights for practical applications in food quality monitoring.