In　recent　decades,　image　segmentation　based　on　PDE　is　used　widely　in　industry.　Geodesic　active　contour　(GAC)　model　is　a　common　used　method.　But　one　drawback　of　this　model　is　that　it＇s　difficult　to　control　the　number　of　iterations　and　sometimes　may　produce　an　over-segmentation　result.　In　this　paper,　a　convergence-to-boundary　method　is　proposed.　In　this　method,　the　model　combining　gradient　vector　flow　(GVF)　with　GAC　is　used　when　the　distance　between　the　evolution　curves　produced　by　successive　iterations　is　smaller　than　some　given　threshold.　It　can　extend　the　capture　range　and　stop　at　the　boundary　stably　avoiding　over-segmentation.　The　experimental　results　show　the　curve　can　converge　to　boundary　well.　©　2011　IEEE.