Blister Package Classification Using ResNet-101 for Identification of Medication
This research aimed to fine-Tune image classification with deep learning techniques to verify the dispensing of prescriptions in hospitals. The proposed approach will be able to help pharmacies reduce the errors that lead to patients receiving the wrong medications. The image classification model us...
Saved in:
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Published: |
2022
|
Subjects: | |
Online Access: | https://repository.li.mahidol.ac.th/handle/123456789/76707 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Mahidol University |
id |
th-mahidol.76707 |
---|---|
record_format |
dspace |
spelling |
th-mahidol.767072022-08-04T15:57:12Z Blister Package Classification Using ResNet-101 for Identification of Medication Narit Hnoohom Nagorn Maitrichit Pitchaya Chotivatunyu Virach Sornlertlamvanich Sakorn Mekruksavanich Anuchit Jitpattanakul University of Phayao King Mongkut's University of Technology North Bangkok Musashino University Mahidol University Computer Science Engineering Mathematics This research aimed to fine-Tune image classification with deep learning techniques to verify the dispensing of prescriptions in hospitals. The proposed approach will be able to help pharmacies reduce the errors that lead to patients receiving the wrong medications. The image classification model uses a double-side transformed image dataset with download from Highlighted Deep Learning (HDL) paper. The dataset collected two-hundred seventy-Two images for types of medicine blister packs, including 72 images of front-side and backside merged with a horizontal cropped background, which were used for training the model. The blister package image dataset uses a deep learning model with a ResNet-101 pre-Trained model from the TensorFlow framework. The experimental results indicated that the TensorFlow framework achieved higher precision, recall, and F1-score than the Caffe framework. A ResNet-101 model with histogram equalization in the front and backside has the highest accuracy at 100 percent. 2022-08-04T08:28:13Z 2022-08-04T08:28:13Z 2021-01-01 Conference Paper ICSEC 2021 - 25th International Computer Science and Engineering Conference. (2021), 406-410 10.1109/ICSEC53205.2021.9684590 2-s2.0-85125185670 https://repository.li.mahidol.ac.th/handle/123456789/76707 Mahidol University SCOPUS https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85125185670&origin=inward |
institution |
Mahidol University |
building |
Mahidol University Library |
continent |
Asia |
country |
Thailand Thailand |
content_provider |
Mahidol University Library |
collection |
Mahidol University Institutional Repository |
topic |
Computer Science Engineering Mathematics |
spellingShingle |
Computer Science Engineering Mathematics Narit Hnoohom Nagorn Maitrichit Pitchaya Chotivatunyu Virach Sornlertlamvanich Sakorn Mekruksavanich Anuchit Jitpattanakul Blister Package Classification Using ResNet-101 for Identification of Medication |
description |
This research aimed to fine-Tune image classification with deep learning techniques to verify the dispensing of prescriptions in hospitals. The proposed approach will be able to help pharmacies reduce the errors that lead to patients receiving the wrong medications. The image classification model uses a double-side transformed image dataset with download from Highlighted Deep Learning (HDL) paper. The dataset collected two-hundred seventy-Two images for types of medicine blister packs, including 72 images of front-side and backside merged with a horizontal cropped background, which were used for training the model. The blister package image dataset uses a deep learning model with a ResNet-101 pre-Trained model from the TensorFlow framework. The experimental results indicated that the TensorFlow framework achieved higher precision, recall, and F1-score than the Caffe framework. A ResNet-101 model with histogram equalization in the front and backside has the highest accuracy at 100 percent. |
author2 |
University of Phayao |
author_facet |
University of Phayao Narit Hnoohom Nagorn Maitrichit Pitchaya Chotivatunyu Virach Sornlertlamvanich Sakorn Mekruksavanich Anuchit Jitpattanakul |
format |
Conference or Workshop Item |
author |
Narit Hnoohom Nagorn Maitrichit Pitchaya Chotivatunyu Virach Sornlertlamvanich Sakorn Mekruksavanich Anuchit Jitpattanakul |
author_sort |
Narit Hnoohom |
title |
Blister Package Classification Using ResNet-101 for Identification of Medication |
title_short |
Blister Package Classification Using ResNet-101 for Identification of Medication |
title_full |
Blister Package Classification Using ResNet-101 for Identification of Medication |
title_fullStr |
Blister Package Classification Using ResNet-101 for Identification of Medication |
title_full_unstemmed |
Blister Package Classification Using ResNet-101 for Identification of Medication |
title_sort |
blister package classification using resnet-101 for identification of medication |
publishDate |
2022 |
url |
https://repository.li.mahidol.ac.th/handle/123456789/76707 |
_version_ |
1763489957298569216 |