Published Research Paper

This research explores how convolutional neural networks (CNNs) can improve pill image recognition for medical retrieval systems, helping patients and practitioners identify unidentified medications through camera-equipped mobile devices.

The study proposes three CNN architectures: two hybrid models (CNN+SVM and CNN+kNN) and a ResNet-50 network. Various preprocessing steps using detection techniques including Gaussian filtering were applied to a dataset of 7,000 pill images from the National Library of Medicine.

The proposed CNN+kNN architecture achieved 90.8% accuracy, a roughly 10% improvement over existing methods, with a runtime of approximately 1 millisecond per execution.

I co-authored this paper with my former professor at Rochester Institute of Technology, Dubai. I handled the writing, experimentation, and findings, designing the methodology, running the model evaluations, and documenting the results.

This work strengthened my research and problem-solving mindset, bridging my background in computer science with real-world applications in healthcare technology.