<![CDATA[Object detection is a crucial component in the development of automated systems in the healthcare domain, particularly in pharmaceutical applications such as pill identification and management. One of the main challenges in image-based pill detection systems is achieving high accuracy and robust generalization under variations in pill shape, color, and illumination conditions. This study applies the Faster R-CNN framework with an AlexNet backbone to detect and classify pill objects in digital images. The model is trained using multiple epoch configurations to analyze the effect of training duration on detection performance. Experimental results show that the proposed approach achieves an accuracy of up to 98%, demonstrating strong detection capability. Increasing the number of training epochs improves the stability and consistency of pill recognition. These results indicate that AlexNet-based Faster R-CNN is effective for pharmaceutical applications, particularly in drug distribution, packaging, and pill counting systems that require high precision and reliability.]]>
Copyrights © 2025
