In　this　paper,　an　algorithm　for　super-resolution　restoration　of　multispectral　images　based　on　principal　component　analysis　(PCA　transform)　is　proposed.　By　employing　PCA　transform,　the　valid　information　contained　in　the　multispectral　images　is　concentrated　in　the　first　principal　component.　Then　the　super-resolution　restoration　of　the　first　principal　component　images　was　carried　out　on　the　basis　of　high-resolution　reference　images.　Next,　the　reconstructed　high-frequency　information　is　restored　to　all　bands　of　multispectral　images　by　inverse　PCA　transform.　This　algorithm　utilizes　the　correlation　between　the　first　principal　component　after　PCA　transform　and　the　panchromatic　image.　By　constructing　the　grey-level　mapping　model,　the　high-frequency　information　contained　in　the　panchromatic　image　is　mapped　onto　the　first　principal　component　image.　The　Maximum-a-Posteriori　based　constrained　optimization　is　performed　to　further　improve　the　quality　of　the　reconstructed　high-frequency　information.　The　algorithm　not　only　makes　full　use　of　the　high-frequency　information　contained　in　the　panchromatic　image,　but　also　avoids　the　introduction　of　error　information.　The　quality　of　the　reconstructed　high-resolution　image　is　ensured,　and　the　problem　of　spectral　distortion　caused　by　the　separation　of　bands　is　prevented.