Analysis　sparse　model　has　been　successfully　used　for　a　variety　of　tasks　such　as　image　denoising,　deblurring,　and　most　recently　compressed　sensing,　so　it　arouses　much　attention.　K-SVD　is　a　mature　dictionary　learning　approach　for　the　analysis　sparse　model.　However,　it　represents　images　as　one　dimension　signals,　which　results　in　mistakes　of　spatial　correlations.　In　this　paper,　we　propose　a　novel　analysis　sparse　model,　where　analysis　dictionary　derived　from　two　analysis　operators　which　act　on　an　image,　leading　to　a　sparse　outcome.　And　a　two　dimensional　K-SVD　(2D-KSVD)　is　proposed　to　train　the　analysis　sparse　dictionaries.　Experiments　on　image　denoising　validate　that　the　proposed　analysis　dictionary　can　express　more　image　spatial　and　frequency　characteristics　and　by　using　the　dictionary,　the　two　dimension　analysis　sparse　model　outperforms　the　traditional　analysis　model　in　terms　of　PSNR.　©　2012　Springer-Verlag.