Rajagopal, Heshalini and Mokhtar, Norrima and Mohd Khairuddin, Anis Salwa and Khairunizam, Wan and Ibrahim, Zuwairie and Bin Adam, Asrul and Wan Mohd Mahiyidin, Wan Amirul Bin (2021) Gray Level Co-Occurrence Matrix (GLCM) and Gabor features based No-Reference Image Quality Assessment for wood images. In: 26th International Conference on Artificial Life and Robotics, ICAROB 2021, 21 - 24 January 2021, Beppu, Oita.
Full text not available from this repository.Abstract
Image Quality Assessment (IQA) is an imperative element in improving the effectiveness of an automatic wood recognition system. There is a need to develop a No-Reference-IQA (NR-IQA) system as a distortion free wood images are impossible to be acquired in the dusty environment in timber factories. Therefore, a Gray Level Co-Occurrence Matrix (GLCM) and Gabor features-based NR-IQA, GGNR-IQA algorithm is proposed to evaluate the quality of wood images. The proposed GGNR-IQA algorithm is compared with a well-known NR-IQA, Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Full-Reference-IQA (FR-IQA) algorithms, Structural Similarity Index (SSIM), Multiscale SSIM (MS-SSIM), Feature SIMilarity (FSIM), Information Weighted SSIM (IW-SSIM) and Gradient Magnitude Similarity Deviation (GMSD). Results shows that the GGNR-IQA algorithm outperforms the NR-IQA and FR-IQAs. The GGNR-IQA algorithm is beneficial in wood industry as a distortion free reference image is not required to pre-process wood images.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Funders: | None |
| Uncontrolled Keywords: | Gabor; GGNR-IQA; GLCM; NR-IQA; Wood images |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Faculty of Engineering > Department of Electrical Engineering |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 17 Oct 2023 07:25 |
| Last Modified: | 17 Oct 2023 07:25 |
| URI: | http://eprints.um.edu.my/id/eprint/35416 |
Actions (login required)
 |
View Item |
