<![CDATA[Contrast Limited Adaptive Histogram Equalization (CLAHE) is widely used to enhance image contrast, but it has limitations in improving edge sharpness and may amplify noise. Meanwhile, Unsharp Masking (USM) is effective for edge enhancement, yet it is less optimal when applied to low-contrast images. To address these weaknesses, this study proposes a hybrid image enhancement method combining CLAHE and USM for coffee beans quality analysis. The dataset consists of four classes: Biji-Kopi Normal (normal), Biji-Kopi Pecah (broken), Biji-Kopi Hitam (black), and Biji-Kopi Berlubang (hollow). All images were trained at a resolution of 512×512 pixels for 2000 iterations without transfer learning to ensure fair and unbiased evaluation. Histogram-based analysis demonstrates significant improvements after enhancement, including a 50.19% increase in mean intensity, a 217.9% increase in variance, a 78.38% rise in standard deviation, and a 22% increase in skewness, along with a 37.42% reduction in kurtosis. Performance evaluation using YOLOv4-Tiny shows that the proposed method improves AP50 from 96.51 to 97.7 and AP75 from 59.91 to 66.24, while AP95 remains unchanged at 0.01. The most notable improvements are observed at AP70 to AP90, indicating that the hybrid approach not only enhances classification performance but also strengthens object localization accuracy, making it effective for coffee bean defect detection.]]>
Copyrights © 2026
