We　propose　an　iterative　semi-blind　carrier　frequency　offset　(CFO)　estimation,　self-interference　(SI)　cancelation　and　signal　detection　scheme　for　full-duplex　(FD)　orthogonal　frequency　division　multiplexing　(OFDM)　systems.　To　the　best　of　our　knowledge,　this　is　the　first　work　to　consider　signal　detection　of　FD　systems　in　the　presence　of　both　CFO　and　SI.　The　CFO　estimation,　SI　cancelation　and　signal　detection　are　performed　initially　by　a　subspace　based　semi-blind　method,　which　are　then　enhanced　significantly　by　performing　iterations　among　them.　Its　CFO　compensation　is　performed　on　the　desired　signal　estimate,　avoiding　the　introduction　of　CFO　to　the　SI.　The　pilots　for　the　desired　signal　and　SI　are　carefully　designed　to　enable　simultaneous　transmission　of　them　to　achieve　FD　training　mode.　Simulation　results　show　that,　the　proposed　iterative　scheme,　with　much　lower　training　overhead,　demonstrates　a　significant　performance　enhancement　over　the　existing　methods.　By　utilizing　the　second　order　statistics　of　the　received　signal,　a　much　superior　bit　error　rate　(BER)　performance　can　be　achieved　compared　to　the　case　with　perfect　SI　cancelation　and　CFO　compensation.　Its　output　signal-to-　interference-and-noise-ratio　(SINR)　is　close　to　that　with　perfect　SI　cancelation,　and　robust　against　the　input　signal-to-interference　ratio　(SIR).　©　2018　IEEE.