Image　super-resolution　(SR)　techniques　have　been　applied　to　a　wide　range　of　applications,　including　high-definition　television,　face　recognition,　security　surveillance,　and　medical　image　processing.　High-resolution　images　with　rich　detailed　information　can　be　acquired　by　interpolating　low-resolution　images　using　SR　techniques.　However,　artifacts　and　blur　distortion　are　inevitably　introduced　while　increasing　the　resolution　of　images,　which　affect　the　SR　image　perceptual　quality　and　the　accuracy　of　subsequent　image　processing.　For　the　QA　of　SR　images,　this　chapter　first　shows　the　SR　image　databases　on　account　of　interpolation　and　image　enhancement.　Second,　it　introduces　the　full-reference　QA　approaches　based　on　the　quality　loss　function　and　L　2　Norm.　Third,　it　presents　the　QA　methods　based　on　a　two-stage　regression　model,　pixel　similarity　between　image　blocks,　and　natural　scene　statistical　model.　In　the　end,　the　authors　have　discussed　the　future　research　trends　of　SR　image　QA　and　pointed　out　it　is　necessary　to　establish　accurate　and　efficient　objective　QA　approaches　to　SR　images.　©　2022,　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.