Sparse　coding　theory　is　a　method　for　finding　a　reduced　representation　of　multidimensional　data.　When　applied　to　images,　this　theory　can　adopt　efficient　codes　for　images　that　captures　the　statistically　significant　structure　intrinsic　in　the　images.　In　this　paper,　we　mainly　discuss　about　its　application　in　the　area　of　texture　images　analysis　by　means　of　Independent　Component　Analysis.　Texture　model　construction,　feature　extraction　and　further　segmentation　approaches　are　proposed　respectively.　The　experimental　results　demonstrate　that　the　segmentation　based　on　sparse　coding　theory　gets　promising　performance.