The main idea of adaptive loop filter (ALF) is to apply a classification to obtain multiple classes, which gives a partition of a set of all pixel locations. After that, a Wiener filter is applied for each of those classes. Therefore, the performance of ALF essentially relies on how its classification behaves. Multiple-feature based (classifications) adaptive loop filter (MCALF) extends a classification in ALF by applying more than one classifier at the encoder to group all reconstructed samples and then to select a classifier with the best RD-performance to carry out the classification process. Overall, MCALF gives about 5.61%, bitrate reduction for luma over VTM-1.0 and about 5.34% over BMS-1.0 (without ALF) for random access keeping nearly the same complexity of ALF.