Mean Squared Error: Love It or Leave It? A new look at signal fidelity measures

In the field of signal processing, the mean-squared error (MSE) has been the dominant quantitative performance metric, remaining as the standard criterion for the assessment of signal quality and fidelity. It is also the method of choice for comparing competing signal processing methods and systems and it is the preference of design engineers seeking to optimize signal processing signals. However, MSE has limitations in other applications, like in the field of image processing. Nevertheless, it is being used as much as other areas of signal processing. As such, there are situations where it is ideal that other quantitative performance metric must be used, where a new signal processing algorithm might be compared to other algorithms using several fidelity criteria.