Full reference image quality metrics for JPEG compressed images

As high-resolution digital images that are used in remote sensing technologies and medical imaging, tend to be of large sizes and thereby consuming large storage space, large transmission bandwidth, and long transmission times. Therefore, image compression is required before storage and transmission. JPEG2000 and JPEG is the widely used compression standard offering best compression performance. However, compression leads to loss of data and may lead to erroneous results. Thus, there is a need for image quality assessment (IQA) of compressed images at various compression stages. In this paper, we address the full-reference (FR) image quality metric (IQM) for JPEG compressed images and we present a new effective and efficient IQA model, called LSDBIQ (local standard deviation based image quality). The approach is based on the comparison of the local standard deviation of two images. The proposed metrics is tested on four well-known databases available in the literature (TID2013, TID2008, LIVE and CSIQ). Experimental results show that the proposed metrics outperforms other models for the assessment of image quality and have very low computational complexity.