In the past few years, considerable attention has been paid to the development of better video quality metrics that correlate well with the human perception of quality. Although many metrics have been proposed, most of them are very complex and require the original video for estimating the quality -- Full Reference (FR) metrics. As a result, their use in real-time transmission applications is very difficult. For these applications, the solution is to use no-reference (NR) quality metrics, i.e., metrics that do not require the original (reference) to estimate quality. In this project, we propose to develop a library to develop no-reference metrics for estimating the strength of video impairments.