This　paper　presents　a　study　on　a　car　model　recognition　method　based　on　deep　learning.　The　study　involves　designing　and　building　a　deep　learning　network　comprising　four　convolutional　layers,　two　pooling　layers,　and　two　fully　connected　layers.　The　network　has　a　simple　structure　and　can　be　deployed　at　the　edge　for　real-time　identification　and　processing,　without　requiring　high　hardware　requirements.　The　researchers　collected　and　organized　their　own　data,　and　after　training　and　optimization,　the　final　accuracy　of　the　model　was　found　to　be　more　than　83%　-　validating　the　effectiveness　of　the　model.　Overall,　the　study　presents　a　promising　approach　to　car　model　recognition　using　deep　learning,　with　potential　applications　in　various　fields.　©　2024　The　Authors.