Abstract
The image quality assessment has been widely used in image processing. Several researches have been developed and carried considering the Human Visual System (HVS). Under the hypothesis that human visual perception is extremely adapted to retrieve structural information from a scene, the SSIM index is the most widely used in this area, which leads to a better correlation with HVS. Despite its robustness the SSIM presents some limitations in the presence of blur affecting images. In this study, we propose an improved version of the SSIM for blur image assessment. The idea is to combine gradient based SSIM score with that of the structural information of the blur. Experimental results show a good performance.
Highlights
Fact, the index of the universal image quality that can assess various distortions is not yet on the horizon and
We use objective methods based on the measurement of the perceived quality of an image. These methods measure the error between a distorted image and a reference image using a range of known properties of the Human Visual System (HVS) by operating the concept of HSV which the human eye is very fitting to retrieve the structural information of an image
The mean of Structural Similarity (SSIM) values is represented by a non uniform curve which contains a decreasing part followed by an increasing part (Fig. 6)
Summary
Fact, the index of the universal image quality that can assess various distortions is not yet on the horizon and. Several methods have been suggested in the literature (Li and Bovik, 2010) trying to overcome the drawbacks of subjective measures (Redi et al, 2010) These indicators provide quality results in concordance with human judgment which requires the integration of the major properties of the Human Visual System (HVS). The aim of this study is offers a quality index for all well known distortions, but rather to focus on especially the blur artifact. Such artifact mainly affects main characteristics such as edges which are high frequencies in the image that is mainly due to the fact that generally higher frequencies are alleviated by the components on the first compression process. Reduced Reference (RR) (Li and Wang, 2009; Ma et al, 2012) and No Reference (NR) (Peng and Doermann, 2012; Saad et al, 2012)
Sign-in/Register to view highlights & summary 
Published Version (
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