With　the　rapid　development　of　image　retrieval　technology,　personalized　image　retrieval　has　attracted　widespread　attention.　On　the　Internet,　a　great　deal　of　images　are　stored　and　transmitted　in　a　compressed　format.　In　order　to　improve　the　accuracy　and　reduce　the　decoding　time　in　the　process　of　image　retrieval,　personalized　image　retrieval　in　compressed　domain　based　on　user　interest　model　is　proposed　in　this　paper.　First,　according　to　the　JPEG　compressed　format,　the　low　resolution　image　is　constructed　to　extract　its　visual　features.　Second,　the　user　interest　model　is　utilized　to　realize　personalized　image　retrieval.　At　last,　the　user　interest　model　is　updated　with　user　relevant　feedback　of　short-term　interest　and　long-term　interest.　Experimental　results　show　that　the　proposed　method　can　significantly　reduce　the　time　of　image　retrieval,　as　well　as　improving　recall　and　precision.　©　2013　ACM.