• Chidipothu Sai Nikhil
• Ami Reddy Neha Reddy
• Chode Giridhar Krishna
• Mohd. Irfan

Accurate medication identification is crucial for patient safety, considering factors like pill colour, size, and shape. Environmental influences can lead to medication errors, necessitating quick and efficient pill identification methods. A proposed solution involves a trained system using Keras and TensorFlow for pill identification, employing object detection to interface with a pill database and leveraging pre-trained datasets for detailed information. This approach aims to gather datasets for automated medicine detection technology, validated through experiments. The innovative deep learning-based system, developed with Python and MobileNet architecture, achieves 98.00% accuracy in both training and validation, reducing human error and saving time for healthcare professionals. Patients benefit from reliable medication verification and access to comprehensive drug information. Rigorous testing confirms the system's reliability and effectiveness in preventing medical errors, enhancing patient care in healthcare settings.

Pill, Keras, Tensor Flow, Object detection, Medicine

"UTILISING MACHINE LEARNING MODELS FOR PILL DETECTION AND IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.e114-e117, May-2024, Available :http://www.jetir.org/papers/JETIR2405411.pdf

"UTILISING MACHINE LEARNING MODELS FOR PILL DETECTION AND IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppe114-e117, May-2024, Available at : http://www.jetir.org/papers/JETIR2405411.pdf