**6. Conclusions**

In this paper, we propose a new feature for plant recognition based on leaf image using DPCNN and BOF and propose a method combining BOF\_SC and BOF\_DP. In the proposed method, features of leaf are adopted, and SVM is taken as the classifier. Firstly, the proposed features BOF\_DP were compared with the existing features on the Flavia dataset. After that, four famous leaf datasets were used to validate the performance of the proposed system. Experimental results show that BOF\_DP has a better effect than other features, and our method is superior to other methods in recognition accuracy. However, to the DPCNN model, the parameters may not be optimal. In future work, we will try to find the best way to set the parameters automatically and improve the recognition accuracy.

**Author Contributions:** Writing—original draft preparation, Z.W. and J.C.; writing—review and editing, Z.W. and J.C.; project administration, Y.Z.; resources, J.K. and Y.M. All authors have read and agreed to the published version of the manuscript.

**Funding:** This study was jointly funded by China Postdoctoral Science Foundation (Grant No. 2013M532097), National Natural Science Foundation of China (Grant No. 61201421), the Foundation of National Glaciology Geocryology Desert Data Center (Grant No. Y929830201), and the 13th Five-year Informatization Plan of the Chinese Academy of Sciences(Grant No. XXH13506).

**Conflicts of Interest:** All Authors declare that they have no conflict of interest.
