Coronavirus　disease　(COVID-19),　caused　by　the　SARS-CoV-2　virus,　is　a　potentially　fatal　disease　of　global　public　health　concern.　Fever　has　been　reported　to　be　a　common　clinical　symptom　in　COVID-19　and　current　CDC　recommendations　for　mitigation　of　community　COVID-19　transmission　include　temperature　screening,　so　prompting　widespread　temperature　screening　across　multiple　sectors,　including　hospitals,　office　buildings　and　airports.　The　need　for　no-contact　and　rapid　measurement　of　body　temperature　during　the　COVID-19　pandemic　emergency　has　led　to　the　widespread　use　of　thermal　imaging　cameras.　However,　the　body　temperature　measurement　is　also　disturbed　by　the　environment　factors,　including　ambient　temperature,　background　light　etc.　When　the　ambient　temperature　is　low,　the　temperature　of　the　patient　will　also　be　low.　It　was　difficult　to　screen　the　fever　patients　by　using　the　absolute　temperature　criteria,　and　it　often　result　in　missing　detection.　In　order　to　solve　this　problem,　this　paper　proposed　a　method　of　screening　COVID-19　symptom　fever　patients　by　the　body　temperature　difference　detection.　The　temperature　difference　detection　method　combined　the　temperature　measurement　of　the　infrared　imaging　camera　and　the　visible　camera　face　recognition.　This　method　will　eliminate　environmental　interference　and　equipment　errors,　to　reduce　the　probability　of　the　fever　missed　detection.　©　Published　under　licence　by　IOP　Publishing　Ltd.