In　this　paper,　we　investigate　the　wavelet-based　estimators　of　a　kind　of　censored　mixture　density　and　discuss　their　pointwise　asymptotic　convergence　rates　over　Holder　spaces.　We　first　consider　the　linear　wavelet　estimator　and　give　its　upper　bound.　However,　the　linear　one　is　nonadaptive　and　not　applicable　since　it　is　related　to　the　unknown　space　parameter.　Finally,　we　use　the　hard　threshold　method　to　explore　adaptive　nonlinear　wavelet　estimator　and　obtain　the　same　convergence　order　as　the　linear　one　up　to　a　logarithmic　penalty.