Automatic Pill Identification System based on Deep Learning and Image Preprocessing

Eric Ponte, Xavier Amparo, Kuan Huang, Daehan Kwak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1969-1974
Number of pages6
ISBN (Electronic)9798350327595
DOIs
StatePublished - 2023
Event2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023 - Las Vegas, United States
Duration: 24 Jul 202327 Jul 2023

Publication series

NameProceedings - 2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023

Conference

Conference2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023
Country/TerritoryUnited States
CityLas Vegas
Period24/07/2327/07/23

Keywords

  • CNN
  • deep learning
  • feature extraction
  • image preprocessing
  • pill identification

Fingerprint

Dive into the research topics of 'Automatic Pill Identification System based on Deep Learning and Image Preprocessing'. Together they form a unique fingerprint.

Cite this