In　this　paper　we　present　a　feature　extraction　approach　by　using　ICA　filters　bank,　which　consists　of　the　ICA　basis　images　learned　from　the　training　images.　On　the　basis　of　its　ability　to　capture　the　inherent　properties　of　textured　image,　we　use　the　ICA　filters　bank　as　template　model　to　extract　the　texture　feature　for　segmentation.　Experiments　based　on　clustering　and　classifications　are　demonstrated　to　show　the　feasibility　of　this　method.　©　2009　IEEE.