The　images　obtained　by　terahertz　continuous　wave　imaging　system　are　easily　interfered　by　background　factors,　and　there　are　also　defects　such　as　low　contrast　and　strong　interference　fringes,　which　become　obstacles　for　display　and　analysis.　In　order　to　solve　this　problem,　we　propose　a　clustering　algorithm　based　on　improved　fuzzy　C-means　for　target　detection　in　this　paper.　Aiming　at　the　characteristics　of　terahertz　images,　the　objective　function　is　improved,　and　the　quantum　particle　swarm　algorithm　is　introduced　to　optimize　it　to　improve　its　shortcomings　of　easyly　trapping　into　local　values.　The　research　results　show　that　the　new　clustering　segmentation　algorithm　is　suitable　for　terahertz　continuous　wave　images　with　irregular　fringe　interference.　It　can　better　extract　the　target　in　the　image　and　has　better　detection　accuracy　than　the　classic　image　clustering　algorithm.　©　2022,　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.