A novel image quality assessment metric using singular value decomposition

Image quality assessment (IQA) plays an important role in many applications such as image compression and transmission. In this paper a full referenced IQA (FR-IQA) model has been proposed which is based upon transformation based technique. Singular value decomposition (SVD) has been used to determine the basis vectors that best describe the input image signal. In contrast to other transformation based techniques such as discrete cosine transformation (DCT) and wavelet transform (WT), SVD does not use predefined basis vectors. In this paper a new methodology has been adopted in which both reference and distorted images are first combined together and then SVD is applied to compute the basis vectors. Projection coefficients of both reference and distorted images when projected onto these basis vectors have been used to calculate the final score. The proposed methodology has been tested on three publicly available image databases. The results of proposed methodology are better than most of the state of the art IQA metrics.