Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt
Vertebrate fossils/remains became recently significant in various study fields for determining the ecological biodiversity. However, with the great abundance of fossils/remains and their classes, there is a difficulty in identifying and detecting these classes. Hence, in this paper, an accurate mach...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Journal of Taibah University for Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/16583655.2022.2096391 |
| _version_ | 1811324260382146560 |
|---|---|
| author | Hussien A. Abdelaziz Mohammed Sallah Ahmed Elgarayhi Fatma E. Al-Tahhan |
| author_facet | Hussien A. Abdelaziz Mohammed Sallah Ahmed Elgarayhi Fatma E. Al-Tahhan |
| author_sort | Hussien A. Abdelaziz |
| collection | DOAJ |
| description | Vertebrate fossils/remains became recently significant in various study fields for determining the ecological biodiversity. However, with the great abundance of fossils/remains and their classes, there is a difficulty in identifying and detecting these classes. Hence, in this paper, an accurate machine learning classification technique is presented to differentiate automatically some types of 3D vertebrate remain images. A computed tomography (CT) scanner is utilized to construct a dataset of 3D images of some vertebrate remains found in Egypt. Adaptive enhancement and segmentation processes are applied to the dataset. The different selected geometric features are then extracted. Thus, the extracted features are classified using suitable machine learning classifiers (SVM, KNN, DTs). The automatic detection for the remains class, according to the extracted features, is obtained using the confusion matrix for the training and testing data points and the receiver operating characteristic (ROC) curve. The results confirmed an accurate technique with high performance. |
| first_indexed | 2024-04-13T14:09:52Z |
| format | Article |
| id | doaj.art-88fa7a5971c14dd5a042bcbeb3188d3e |
| institution | Directory Open Access Journal |
| issn | 1658-3655 |
| language | English |
| last_indexed | 2024-04-13T14:09:52Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Taibah University for Science |
| spelling | doaj.art-88fa7a5971c14dd5a042bcbeb3188d3e2022-12-22T02:43:48ZengTaylor & Francis GroupJournal of Taibah University for Science1658-36552022-12-0116163264510.1080/16583655.2022.2096391Accurate automatic classification system for 3D CT images of some vertebrate remains from EgyptHussien A. Abdelaziz0Mohammed Sallah1Ahmed Elgarayhi2Fatma E. Al-Tahhan3Applied Mathematical Physics Research Group, Physics Department, Faculty of Science, Mansoura University, Mansoura, EgyptApplied Mathematical Physics Research Group, Physics Department, Faculty of Science, Mansoura University, Mansoura, EgyptApplied Mathematical Physics Research Group, Physics Department, Faculty of Science, Mansoura University, Mansoura, EgyptMathematics Department, Faculty of Science, Mansoura University, Mansoura, EgyptVertebrate fossils/remains became recently significant in various study fields for determining the ecological biodiversity. However, with the great abundance of fossils/remains and their classes, there is a difficulty in identifying and detecting these classes. Hence, in this paper, an accurate machine learning classification technique is presented to differentiate automatically some types of 3D vertebrate remain images. A computed tomography (CT) scanner is utilized to construct a dataset of 3D images of some vertebrate remains found in Egypt. Adaptive enhancement and segmentation processes are applied to the dataset. The different selected geometric features are then extracted. Thus, the extracted features are classified using suitable machine learning classifiers (SVM, KNN, DTs). The automatic detection for the remains class, according to the extracted features, is obtained using the confusion matrix for the training and testing data points and the receiver operating characteristic (ROC) curve. The results confirmed an accurate technique with high performance.https://www.tandfonline.com/doi/10.1080/16583655.2022.2096391Machine learning (ML)vertebrate remains from EgyptK-nearest neighbour (KNN)decision tree (DT)support vector machine (SVM)features and segmentation |
| spellingShingle | Hussien A. Abdelaziz Mohammed Sallah Ahmed Elgarayhi Fatma E. Al-Tahhan Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt Journal of Taibah University for Science Machine learning (ML) vertebrate remains from Egypt K-nearest neighbour (KNN) decision tree (DT) support vector machine (SVM) features and segmentation |
| title | Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt |
| title_full | Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt |
| title_fullStr | Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt |
| title_full_unstemmed | Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt |
| title_short | Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt |
| title_sort | accurate automatic classification system for 3d ct images of some vertebrate remains from egypt |
| topic | Machine learning (ML) vertebrate remains from Egypt K-nearest neighbour (KNN) decision tree (DT) support vector machine (SVM) features and segmentation |
| url | https://www.tandfonline.com/doi/10.1080/16583655.2022.2096391 |
| work_keys_str_mv | AT hussienaabdelaziz accurateautomaticclassificationsystemfor3dctimagesofsomevertebrateremainsfromegypt AT mohammedsallah accurateautomaticclassificationsystemfor3dctimagesofsomevertebrateremainsfromegypt AT ahmedelgarayhi accurateautomaticclassificationsystemfor3dctimagesofsomevertebrateremainsfromegypt AT fatmaealtahhan accurateautomaticclassificationsystemfor3dctimagesofsomevertebrateremainsfromegypt |