In　the　process　of　Chinese　license　plate　recognition,　the　main　problems　are　as　follows,　such　as　the　feature　extraction　method　is　cumbersome　and　inefficient,　the　Chinese　character　recognition　rate　is　low.　This　paper　studies　the　license　plate　technology　in　depth　based　on　convolution　neural　network.　In　order　to　solve　the　problem　of　low　recognition　rate　of　Chinese　characters,　we　use　continuous　convolution　layers　to　convolve　the　image　and　extract　more　characters.　Experiments　show　that　the　proposed　method　can　more　effectively　extract　the　license　plate　characteristics,　improve　the　license　plate　recognition　rate.　©　2017　IEEE.