Abstract
The development of digital image processing techniques requires reliable image quality assessment (IQA) methods. Since images acquired by a camera often contain various distortions and their non-distorted versions are not available, a no-reference IQA (NR-IQA) technique should be used. Many popular methods are developed to assess artificially distorted images, available in benchmark databases. In this paper, a new large benchmark database, containing naturally distorted images captured with a digital camera, is introduced along with a new NR-IQA metric. The method uses a wide spectrum of local and global image features and their statistics to address a diversity of distortions. Among 80 employed features, 56 are introduced to the IQA for the first time, while the remaining statistics are used to further improve the quality prediction performance of the method. The obtained perceptual feature vector is used to provide a quality model with support vector regression technique. The experimental comparison of the method with the state-of-the-art IQA measures on the database reveals its superiority in terms of correlation with human scores.
Highlights
The recent growth of digital image processing techniques results in the need for the development of automatic image quality assessment (IQA) methods, aiming to replace tests with human subjects [3]
Depending on the availability of a distortion-free reference image, IQA metrics are divided into no-reference (NR), full reference (FR), and reduced reference (RR) techniques [3]
In order to predict the objective quality of an image, no-reference IQA (NR-IQA) methods often mimic properties of the human visual system (HVS) or use features sensitive to image distortions
Summary
The recent growth of digital image processing techniques results in the need for the development of automatic image quality assessment (IQA) methods, aiming to replace tests with human subjects [3]. In order to predict the objective quality of an image, NR-IQA methods often mimic properties of the human visual system (HVS) or use features sensitive to image distortions. A different approach can be found in techniques that are based on deep learning, in which feature extraction and learning steps are fused Since they require large databases for training or suffer from an architecture devoted to image recognition tasks, in these methods, image patches [2,6], objective scores of FR-IQA methods [6,12], fine-tuning [29], or handcrafted features [12] are typically employed. 4. A novel NR-IQA method that incorporates a reasonably small number of features and provides superior image quality prediction performance in comparison with the state-of-the-art methods is developed and described.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
