A hypersphere method for plant leaves classification

The recognition of the tens of thousands of kinds of plants on Earth is an important and difficult task. If we use a nearest neighbour classifier to solve it, millions of training data are needed to obtain a high correct recognition rate. However, the corresponding classification process is quite time-consuming. We propose a new approach using a moving median centers hypersphere technique to recognize different plant leaves. With this new method, we can successfully decrease the classification time, and reduce the storage size without sacrificing the classification accuracy. Experimental results using real data show that this method is really efficient and effective in classifying different plant leaves.