The match filter (MF) is always superior to constrained energy minimization (CEM)

Abstract

The constrained energy minimization (CEM) and matched filter (MF) are two most frequently used target detection algorithms in the remotely sensed community. In this paper, we first introduce an augmented CEM (ACEM) by adding a N-dimensional band consisting of 1’s. According to a recently published conclusion that CEM can always achieve a better performance by adding any linearly independent bands, ACEM is better than CEM. Further, we prove that ACEM is mathematically equivalent to MF. As a result, we can conclude that the classical matched filter (MF) is always superior to the CEM operator.