<![CDATA[Assessing the purity of Luwak Coffee is a complex challenge due to its unique production and limited availability, as visual inspection is unreliable. This study explores the use of image processing and feature selection to classify Luwak Coffee purity by analyzing 11 color features including RGB, HSV, HSL, and Lab color spaces. Two classification methods k-Nearest Neighbors (k-NN) and Random Forest (RF) were optimized using six Bio-Inspired Algorithms (Differential Evolution, Firefly Algorithm, Flower Pollination Algorithm, Harris Hawk Algorithm, Jaya Algorithm, and Particle Swarm Optimization) to identify the most important features for classifying the purity of Luwak Coffee. The results revealed that feature selection significantly improved accuracy, with the Jaya Algorithm paired with k-NN achieving the highest accuracy (0.918) using only three features (R_Mean, B_Mean, and H_Mean). For RF, the Flower Pollination Algorithm yielded the best performance (0.899) with three features. The study demonstrates a classification method coupled with Bio-Inspired Algorithms for classifying Luwak Coffee purity providing high accuracy as a non-destructive method. These findings contribute to the development of reliable tools for classifying purity of Luwak Coffee]]>
Copyrights © 2025
