Abstract
The purpose of the image quality assessment is to evaluate image quality consistently with human’s subjective evaluation. In image quality assessment, many structural features have been used to measure the quality degradation of an image. However, most of the existing image quality assessment methods are block-based, which ignores the features among neighboring blocks. In this paper, we argue that the human visual system perceives distortions not only depends on local structural (intra-block structure) distortions, but also relates to the structural distortions of their neighborhoods (inter-block texture). Based on this insight, we propose a novel image quality assessment method, called the diffusion speed structure similarity (DSSIM), by considering both intra-block structure and inter-block texture. Specifically, to characterize the inter-block texture, we devise a novel visual feature based on the image diffusion speed. To measure the changes of the intra-block structure, we adopt the image gradient magnitude. Furthermore, to differentiate the importance of a local region, we devise a weighting function based on the image diffusion speed. Extensive experimental results on six benchmark databases demonstrate that our proposed method yields a better performance than the state-of-the-art methods.
Highlights
The image quality assessment has become a widely used method to improve the performance of image processing and computer vision applications
We adopt the image gradient magnitude to measure the changes of the intra-block structure
PERFORMANCE EVALUATION We conduct the experiment on five benchmark FR-Image Quality Assessment (IQA) databases, and compare diffusion speed structure similarity (DSSIM) with the state-of-the-art, the comparison is conducted based on four evaluation criteria, i.e., the Spearman rank order correlation coefficient (SROCC), Kendall rank order correlation coefficient (KROCC), Pearson linear correlation coefficient (PLCC), and root mean squared error (RMSE)
Summary
The image quality assessment has become a widely used method to improve the performance of image processing and computer vision applications (e.g., image enhancement, compression, restoration, and reproduction [1]–[3]). Since the structural information is recognized as an important feature to simulate HVS, some structure-based methods are proposed In these methods, the structural similarity (SSIM) [1] index is considered to be one of the most representative FR-IQA. A local block with high structure value in smooth-region would have a higher impact on HVS than that in texture region This indicates that the inter-block texture has an important impact on HVS’s image distortion perception. The contributions of this paper are summarized as follows: 1) We propose to use the intra-block structure and inter-block texture to measure the image quality. 2) We devise a novel visual feature based on the image diffusion speed to characterize the inter-block texture.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have