TY - GEN
T1 - Automatic Pill Identification System based on Deep Learning and Image Preprocessing
AU - Ponte, Eric
AU - Amparo, Xavier
AU - Huang, Kuan
AU - Kwak, Daehan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The pharmaceutical industry annually distributes thousands of different prescription medications. However, the high volume of available medication increases the likelihood of errors during the dispensation process. These errors can result from distractions, incorrectly filed prescriptions, or similarities between pills. This paper proposes an automated system that employs computer vision to identify pills, aiming to enhance pill identification for pharmaceutical workers and consumers and reduce dispensing errors. The proposed approach involves creating a deep learning model using Keras, preprocessing pill images through an image data generator, and leveraging tools such as OpenCV and Paddle OCR to identify critical aspects of a pill, including its shape, color, and imprint. The ultimate goal is to develop a real-time pill identification system that can seamlessly integrate with video cameras, thereby facilitating smoother operations in high-volume medication dispensaries.
AB - The pharmaceutical industry annually distributes thousands of different prescription medications. However, the high volume of available medication increases the likelihood of errors during the dispensation process. These errors can result from distractions, incorrectly filed prescriptions, or similarities between pills. This paper proposes an automated system that employs computer vision to identify pills, aiming to enhance pill identification for pharmaceutical workers and consumers and reduce dispensing errors. The proposed approach involves creating a deep learning model using Keras, preprocessing pill images through an image data generator, and leveraging tools such as OpenCV and Paddle OCR to identify critical aspects of a pill, including its shape, color, and imprint. The ultimate goal is to develop a real-time pill identification system that can seamlessly integrate with video cameras, thereby facilitating smoother operations in high-volume medication dispensaries.
KW - CNN
KW - deep learning
KW - feature extraction
KW - image preprocessing
KW - pill identification
UR - http://www.scopus.com/inward/record.url?scp=85191149379&partnerID=8YFLogxK
U2 - 10.1109/CSCE60160.2023.00324
DO - 10.1109/CSCE60160.2023.00324
M3 - Conference contribution
AN - SCOPUS:85191149379
T3 - Proceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023
SP - 1969
EP - 1974
BT - Proceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023
Y2 - 24 July 2023 through 27 July 2023
ER -