Authors
Heshalini Rajagopal1, *, Norrima Mokhtar1, Anis Salwa Mohd Khairuddin1,
Wan Khairunizam2, Zuwairie Ibrahim3, Asrul Bin Adam3, Wan Amirul Bin Wan
Mohd Mahiyidin1
1Department of Electrical Engineering, Faculty of Engineering, University
of Malaya, Malaysia
2School of Mechatronic Engineering, University of Malaysia Perlis, Malaysia
3College of Engineering, University of Malaysia Pahang, Malaysia
*Corresponding author. Email: [email protected]
Corresponding Author
Heshalini Rajagopal
Received 19 October 2020, Accepted 1 June 2021, Available Online 26 July
2021.
DOI
https://doi.org/10.2991/jrnal.k.210713.012
Keywords
Wood images; GLCM; Gabor; GGNR-IQA; NR-IQA
Abstract
Image Quality Assessment (IQA) is a vital element in improving the efficiency
of an automatic recognition system of various wood species. There is a
need to develop a No-Reference IQA (NR-IQA) system as a perfect and distortion
free wood images may be impossible to be acquired in the dusty environment
in timber factories. To the best of our knowledge, there is no NR-IQA developed
for wood images specifically. Therefore, a Gray Level Co-Occurrence Matrix
(GLCM) and Gabor features-based NR-IQA (GGNR-IQA) metric is proposed to
assess the quality of wood images. The proposed metric is developed by
training the support vector machine regression with GLCM and Gabor features
calculated for wood images together with scores obtained from subjective
evaluation. The proposed IQA metric is compared with a widely used NR-IQA
metric, Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and
Full Reference-IQA (FR-IQA) metrics. Results shows that the proposed NR-IQA
metric outperforms the BRISQUE and the FR-IQA metrics. Moreover, the proposed
NR-IQA metric is beneficial in wood industry as a distortion free reference
image is not needed to evaluate the wood images.
Copyright
© 2021 The Authors. Published by ALife Robotics Corp. Ltd
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license
(http://creativecommons.org/licenses/by-nc/4.0/).