Research on weeds identification based on K-means feature learning

摘要

This paper aims to overcome the unstable identification results and weak generalization ability in feature extraction based on manual design to realize the automatic weeds identification. On the basis of unsupervised feature learning identification model, K -means clustering algorithm after data preprocessing is used to realize feature learning and construct feature dictionary. Then this feature dictionary is used to extract features from labeled data and train the classification model to realize the automatic weeds identification. In this process, this paper focuses on the effect of parameters such as the clustering number to identification accuracy under single-layer network structure, and the identification accuracy between the single-layer and the two-layer network structure was compared and analyzed. Experimental results show that identification rate can be improved by increasing the network levels, as well as fine-tuning the parameters under the premise of selecting reasonable parameters.