Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/513238Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Md. Jan Nordin, Assoc. Prof. Dr. | |
| dc.contributor.author | Nada A. Rasheed (P64763) | |
| dc.date.accessioned | 2023-10-16T04:34:56Z | - |
| dc.date.available | 2023-10-16T04:34:56Z | - |
| dc.date.issued | 2016-06-20 | |
| dc.identifier.other | ukmvital:83260 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/513238 | - |
| dc.description | This problem is divided into two subtasks: the classification archaeological fragments into similar groups, and reconstruction each group into the original objects. Manually classify artifacts are often found to be randomly mixed with each other in archaeological excavation sites is a tedious task, because artifacts are commonly exceed thousands of fragments. Thus, the aim of this thesis is to find a solution for the accurate classification of ancient fragments into groups by computer assistance. To solve this problem, three methods have been proposed, each of which exploits the color and texture properties of the surfaces of the fragments. The first method involves a novel algorithm that classifies fragments based on the intersection of the RGB colors of the fragments; the texture is extracted based on a Gray Level Co-occurrence Matrix (GLCM), and classifies fragments depending on a novel method. The second method involves an algorithm, which first divides the 2D image into six sub-blocks of equal size, then extracts the Hue, Saturation and Value (HSV) colors from each sub-block as features, next classify fragments using Neural Network. The last method is an improvement of the previous method, that extracts HSV colors and GLCM textures as features, the fragments classify using k-Nearest Neighbor algorithm. All three algorithms were applied on a standard ceramic database, and the results achieved 96.1%, 89.6, and 89.6% respectively that are demonstrate promising results. The reconstruction of archaeological fragments in 3D geometry is an important problem in pattern recognition. Therefore, this research has implemented the algorithms to reconstruct real datasets using Neural Networks. The challenge of this work is to reconstruct the objects without previous knowledge about the part that should start the assembly; this greatly helps to avoid the presence of gaps created due to missing artifact fragments. The study utilized the geometric features of the fragments as important features to reconstruct the objects by classifying their fragments using a Neural Network model. The algorithms have been tested on several standard fragment datasets, and the yielded results demonstrated 100% precision, because it successfully reconstructed all of the fragments and even in cases of missing fragments.,Certification of Master's/Doctoral Thesis" is not available | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Reconstruction algorithms | |
| dc.subject | Archaeological fragments | |
| dc.subject | Colour | |
| dc.subject | Slope features | |
| dc.subject | Dissertations, Academic -- Malaysia | |
| dc.title | Classification and reconstruction algorithms of archaeological fragments using colour and slope features | |
| dc.type | Theses | |
| dc.format.pages | 213 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_83260+SOURCE1+SOURCE1.0.PDF Restricted Access | 396.67 kB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.