A　fabric　defect　detection　system　based　on　single-point　photoelectric　sensing,　was　proposed　and　developed.　The　performance　of　the　system　was　enhanced　by　using　wavelet　denoising　algorithm　to　reduce　the　negative　effect　of　noise　and　the　environment　disturb,　such　as　fluorescent　light　in　the　factory.　Instead　of　detection　of　light　reflection　from　fabric,　a　light　transmission　technique　with　higher　signal-to-noise　rate　was　employed　in　the　system　for　evaluating　the　fabric　defect.　A　Si　photodiode　was　used　to　record　the　defect　signal　of　fabric.　The　signal　was　enhanced　by　stationary　wavelet　transform.　The　signal　was　quantitatively　evaluated　and　finally　a　defect　alarm　was　triggered.　From　the　experimental　results,　the　timeliness,　robustness　and　detection　precision　of　the　system　were　demonstrated,　therefore,　it　could　be　recommended　for　the　applications　in　fabric　industries.