In　an　Image　Quality　Assessment　(IQA)　scenario,　the　Human　Vision　System　(HVS)　always　acts　as　the　ultimate　receiver　and　valuator　of　generated　images.　As　an　important　feature　of　HVS,　the　visual　attention　data　has　been　demonstrated　to　be　able　to　effectively　improve　the　performance　of　existing　objective　quality　metrics.　However,　this　feature　has　not　yet　been　well　explored　in　the　IQA　of　image　interpolation.　In　this　paper,　we　conduct　an　eye-tracking　test　on　an　interpolated　image　database　and　investigate　the　impact　of　visual　attention　on　IQA　of　image　interpolation.　Two　visual　attention　models,　saliency　map　and　Region　Of　Interest　(ROI),　are　then　obtained　from　the　eye-tracking　data.　We　further　incorporate　these　models　into　non-integer　interpolated　IQA　metric　and　examine　their　performances.　Experiments　show　that　the　introduction　of　eye-tracking　features　obviously　improves　the　conventional　IQA　metric　for　non-integer　image　interpolation.　©　2018　IEEE.