A Development of Medication Assist Device Based on Multi-Object Recognition

When the human population is experiencing a decline but the turnover rate of pharmacists in general hospitals is gradually increasing, department of pharmacy starts to import more modern technologies including automation and artificial intelligence to aid in the workflow. One of the lengthy and routine work is to count the number of remaining medications of each ward, which requires many pharmacists and technicians depends on the size of hospital. This study thereby introduces a design of a medication assist device with an integration of the machine vision and multiple object recognition algorithm. The work can be divided into hardware design, data collection, training and validation, respectively. The recognition algorithm is based on deep learning Faster RCNN, which can successfully identify 7 classes of the anesthetics often used with an accuracy of 99.03%. This pilot study presents the capability of medication recognition, and the potential to expand numbers of medication.