<![CDATA[Abstract Beauty cotton products come in different quality levels, and subsequently is important to categorize, especially in the area of cosmetics, and face care. Manual assessments of cotton quality are often subjective and not always accurate, this is why an automatic classification system is needed. The purpose of this study is to classify beauty cotton based on their images based on texture using Gray Level Co-occurrence matrix (GLCM) and K-Nearest Neighbors (K-NN). The dataset comprises of 600 cotton images of three different brands, Sariayu, Watson, and Selection. Each image was transformed to grayscale, resized to 100 ยด 100 pixels, and then the texture features were derived which consist of contrast, correlation, energy, and homogeneity. The classification results show that the maximum performance was achieved at K = 5 with 81% accuracy, these results show that the image-based texture approach can classify cotton quality automatically and objectively and has possibilities in future systems for cosmetic products quality evaluation systems.]]>
Copyrights © 2025
