Wafer　dicing　is　a　basic　step　in　building　electronic　devices　such　as　CPU　or　GPU.　It　is　automatically　accomplished　in　the　wafer　Dicing　Machine　in　which　a　little　misalignment　of　wafers　may　lead　to　damaged　chips.　The　information　of　misalignment　may　be　obtained　by　detecting　the　paddle　vat　to　calculate　the　misalignment　between　the　blade　and　the　part　of　the　wafer　which　has　been　diced　in　real-time.　In　this　paper,　methods　for　detecting　the　paddle　vat　are　studied.　For　most　of　simple　wafer　images　where　the　intensities　of　paddle　vats　are　quite　different　from　that　of　the　background,　a　binary　segmentation　approach　is　used　to　detect　the　paddle　vat　of　the　wafer　image.　The　threshold　for　binarization　is　calculated　by　the　grey-scale　histogram　of　the　wafer　image　which　is　smoothed　by　using　exponentially　smoothed　method.　For　wafer　images　with　complex　backgrounds,　the　improved　Canny　detection　algorithm　with　anisotropic　diffusion　is　used　to　detect　the　edges　of　paddle　vats.　Experimental　results　show　the　validity　of　the　methods.