Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan
Dental impression tray is frequently used in dentistry to record patient’s oral structure for clinical oral diagnosis and treatment planning. Manual procedure of taking impressions is costly, time-consuming, and additionally, no research has been done to select dental impression tray from dental arc...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2021
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/14949/1/Muhammad_Asif.pdf http://studentsrepo.um.edu.my/14949/2/Muhammad_Asif.pdf http://studentsrepo.um.edu.my/14949/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.um.stud.14949 |
|---|---|
| record_format |
eprints |
| spelling |
my.um.stud.149492025-01-12T18:43:03Z Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan Muhammad Asif , Hasan QA75 Electronic computers. Computer science Dental impression tray is frequently used in dentistry to record patient’s oral structure for clinical oral diagnosis and treatment planning. Manual procedure of taking impressions is costly, time-consuming, and additionally, no research has been done to select dental impression tray from dental arch images using computer vision in real-life scenarios. In this spirit, an intelligent model is proposed based on computer vision and machine learning to select appropriate dental impression trays from maxillary arch images. A dataset of 52 patients’ maxillary arch images that matches one from 4 sizes of Kurten’s impression tray have been acquired. Various sets features such as, colors, textures, and shapes of the images were extracted to better characterize the maxillary arch images. Considering the importance of the features in describing the maxillary arch object and to improve the classification performance, a method based on multi-feature with ensemble classifier is proposed. Besides, the performance of a deep-learning based multilayer perceptron neural network is also investigated. The proposed multi-feature with ensemble classifier attained 92.31% precision, 91.75% recall, 91.75% accuracy, respectively, on the dataset. This clearly establishes the feasibility of this study. An illustration of a real-life application of the proposed model is also provided. 2021-09 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/14949/1/Muhammad_Asif.pdf application/pdf http://studentsrepo.um.edu.my/14949/2/Muhammad_Asif.pdf Muhammad Asif , Hasan (2021) Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan. Masters thesis, Universiti Malaya. http://studentsrepo.um.edu.my/14949/ |
| institution |
Universiti Malaya |
| building |
UM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Malaya |
| content_source |
UM Student Repository |
| url_provider |
http://studentsrepo.um.edu.my/ |
| topic |
QA75 Electronic computers. Computer science |
| spellingShingle |
QA75 Electronic computers. Computer science Muhammad Asif , Hasan Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| description |
Dental impression tray is frequently used in dentistry to record patient’s oral structure for clinical oral diagnosis and treatment planning. Manual procedure of taking impressions is costly, time-consuming, and additionally, no research has been done to select dental impression tray from dental arch images using computer vision in real-life scenarios. In this spirit, an intelligent model is proposed based on computer vision and machine learning to select appropriate dental impression trays from maxillary arch images. A dataset of 52 patients’ maxillary arch images that matches one from 4 sizes of Kurten’s impression tray have been acquired. Various sets features such as, colors, textures, and shapes of the images were extracted to better characterize the maxillary arch images. Considering the importance of the features in describing the maxillary arch object and to improve the classification performance, a method based on multi-feature with ensemble classifier is proposed. Besides, the performance of a deep-learning based
multilayer perceptron neural network is also investigated. The proposed multi-feature with ensemble classifier attained 92.31% precision, 91.75% recall, 91.75% accuracy, respectively, on the dataset. This clearly establishes the feasibility of this study. An illustration of a real-life application of the proposed model is also provided.
|
| format |
Thesis |
| author |
Muhammad Asif , Hasan |
| author_facet |
Muhammad Asif , Hasan |
| author_sort |
Muhammad Asif , Hasan |
| title |
Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| title_short |
Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| title_full |
Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| title_fullStr |
Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| title_full_unstemmed |
Image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / Muhammad Asif Hasan |
| title_sort |
image based dental impression tray selection from maxillary arches using multifeature with ensemble classifier / muhammad asif hasan |
| publishDate |
2021 |
| url |
http://studentsrepo.um.edu.my/14949/1/Muhammad_Asif.pdf http://studentsrepo.um.edu.my/14949/2/Muhammad_Asif.pdf http://studentsrepo.um.edu.my/14949/ |
| _version_ |
1823273186239709184 |
| score |
13.244413 |