Face　detection　is　a　branch　field　originated　from　face　recognition.　In　recent　years,　face　detection　has　shown　important　significance　and　value　in　daily　produce　and　application.　A　face　detection　method　based　on　BP　neural　network　and　improved　AdaBoost　algorithm　is　proposed　in　this　paper.　First,　Using　BP　neural　network　instead　of　YCbCr　gaussian　model　to　build　skin　color　model.　Meanwhile,　a　new　method　of　weight　updating　for　AdaBoost　algorithm　is　proposed.　The　distance　between　the　threshold　and　the　sample　is　introduced　into　the　update　of　weight.　Besides　the　weight　has　a　boundary　value.　Finally,　BP　neural　network　is　used　to　obtain　the　skin　color　candidate　areas　in　the　image,　and　the　improved　AdaBoost　algorithm　is　used　to　accurately　detect　the　face　in　the　image.　Based　on　our　experimental　result,　the　new　solution　using　our　BP　neural　network　and　improved　AdaBoost　algorithm　performs　higher　accuracy　than　the　existing　approach.