A comprehensive comparative analysis of chicken meat classification techniques through machine learning models

This study develops a digital image processing technique to distinguish between fresh and rotten chicken. Chicken freshness has a significant impact on public health and industry sustainability. This study uses a multi-stage approach including data acquisition, preprocessing, feature extraction, and classification. A total of 1,000 chicken images were obtained, consisting of 800 images for training and 200 images for testing, with a proportion of 80:20. Feature extraction was performed using a combination of the HSI (Hue, Saturation, Intensity) color model to capture the color characteristics of chicken and the Local Binary Pattern (LBP) to extract texture information. Classification was performed using the K-Nearest Neighbor (KNN) algorithm with various K values and distance metrics. The experimental results show that the combination of color and texture features provides higher accuracy than using either feature alone. The best model using HSI and LBP feature extraction with K = 1 and K = 3 in the Euclidean distance metric achieved the highest accuracy of 95.4%. With a promising level of accuracy, this method can be applied in automated inspections in the poultry supply chain, improving food safety and helping consumers make better purchasing decisions. However, the main challenge in this study is the variation in lighting during image capture, which causes the fresh and rotten chicken feature values to overlap, thus hindering perfect classification.