Plant Classification Based On Stacked Autoencoder

With the development of rapid technology, the similarity between plants is increasing, which will enhance the classified workload of botanists. Therefore, it is urge to find a quick automatic classification method. In recent years, the performance of autoencoder has become more and more prominent. Consequently, in this paper, we employ stacked autoencoder to classify three plants, including 630 images in total. The result of this experience shows that the accuracy of classification is 93.3%.