<![CDATA[Rapid and non-invasive anemia detection is crucial, especially in regions with limited laboratory facilities. The conjunctiva of the eye serves as a promising visual indicator for anemia through the analysis of color and texture. This study aims to analyze and compare the performance of three image classification methods K-Nearest Neighbors (KNN), YOLOv8, and YOLOv11 in detecting anemia using conjunctival images. The CP-AnemiC dataset was employed, consisting of 710 original images, later expanded to 3,550 images through augmentation. KNN utilized color features extracted from the CIE LAB color space, while YOLOv8 and YOLOv11 leveraged automatic feature extraction using convolutional neural networks. Evaluation metrics included accuracy, precision, recall, and F1-score. The results indicate that YOLOv8 achieved the best performance with 93.4% accuracy and a 94.5% F1-score, followed by YOLOv11 with 93.0% accuracy and a 94.2% F1-score. In contrast, KNN obtained an accuracy of only 85.7%. YOLOv8 demonstrated fast and accurate detection, while YOLOv11 exhibited more stable training behavior. These findings highlight that deep learning models particularly YOLOv8 and YOLOv11 are highly promising for implementing efficient, accurate, and practical conjunctival image–based anemia detection systems. This research contributes by presenting an explicit comparative analysis between the classical method (KNN) and the latest deep learning models (YOLOv8 and YOLOv11) in the specific context of conjunctival image classification.]]>
