Image　classifications　the　basis　to　solve　visual　tracking,　image　segmentation,　scenes　understanding　and　other　complex　visual　tasks.　Bag　of　words　(Bow)　model　is　initially　applied　in　text　classification　area,　introduced　in　image　proceeding　and　recognition　on　account　of　its　simple　and　effective.　This　paper　follows　the　standard　bag-of-words　pipeline,　but　substitutes　original　SIFT　descriptor　with　DSP-SIFT(domain-size　pooling　sift).　Then,　taking　account　of　the　truth　that　an　DSP-SIFT　was　developed　for　gray　images　which　limits　its　performance　with　regard　to　some　colored　objects,　we　present　to　add　CN(color-name)　descriptor　to　collect　the　color　information　to　form　visual　words　of　image.　The　experimental　results　over　fifteen　scene　categories　and　Caltech　101　datasets　indicate　that　our　method　can　achieve　very　promising　performance.