Gray level co-occurrence matrix (Glcm) and gabor features based no-reference image quality assessment for wood images

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.