Nordin, Hilman and Abdul Razak, Bushroa and Mokhtar, Norrima and Jamaludin, Mohd Fadzil (2022) A derivative oriented thresholding approach for feature extraction of mold defects on fine arts painting. In: International Conference on Artificial Life and Robotics.
Full text not available from this repository.Abstract
Identification of mold defects is an important step in the restoration of damaged paintings. The process is usually lengthy and depends heavily on the qualitative visual judgement of an expert restorer. This study proposes an automatic mold defect detection technique based on derivative and image analysis to assist in the restoration process. This new method, designated as Derivative Level Thresholding (DLT), combines binarization and detection algorithms to detect mold rapidly and accurately from scanned high-resolution images of a painting. The performance of the proposed method is compared to existing binarization techniques of Otsu’s Thresholding Method, Minimum Error Thresholding (MET) and Contrast Adjusted Thresholding Method. Experimental results from the analysis of 20 samples from high-resolution scans of 2 mold-stained painting have shown that the DLT method is the most robust with the highest sensitivity rate of 84.73 and 68.40 accuracy. © The 2022 International Conference on Artificial Life and Robotics (ICAROB2022).
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Funders: | Universiti Malaya, IIRG034B-2019 |
| Additional Information: | Cited by: 0; Conference name: 27th International Conference on Artificial Life and Robotics, ICAROB 2022; Conference date: 20 January 2022 through 23 January 2022; Conference code: 271609 |
| Subjects: | T Technology > T Technology (General) T Technology > TJ Mechanical engineering and machinery |
| Divisions: | Faculty of Engineering > Department of Electrical Engineering Faculty of Engineering > Department of Mechanical Engineering |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 19 Oct 2024 09:03 |
| Last Modified: | 19 Oct 2024 09:03 |
| URI: | http://eprints.um.edu.my/id/eprint/43251 |
Actions (login required)
 |
View Item |
