Feature　extraction　and　representation　is　a　key　step　in　scene　classification.　In　this　paper,　a　contour　detection-based　mid-level　features　learning　method　is　proposed　for　scene　classification.　First,　a　sketch　tokens-based　contour　detection　scheme　is　proposed　to　initialize　seed　blocks　for　learning　mid-level　patches　and　the　patches　with　more　contour　pixels　are　selected　as　seed　blocks.　The　procedure　is　demonstrated　to　be　helpful　for　scene　classification.　Next,　the　seed　blocks　are　employed　to　train　an　exemplar　SVM　to　discover　other　similar　occurrences　and　an　entropy-rank　criterion　is　utilized　to　mine　the　discriminative　patches.　Finally,　scene　categories　are　identified　by　matching　the　discriminative　patches　and　testing　images.　Extensive　experiments　on　the　MIT　Indoor-67　dataset,　the　15-scene　dataset　and　the　UIUC-sports　dataset　show　that　the　proposed　approach　yields　better　performance　than　other　state-of-the-art　counterparts.