Leaf recognition plays an important role in plant classification. Its main problem is whether the selected features are stable and have a good ability to distinguish between different leaf types. In this paper, we propose a new method for plant classification from a set of leaf images based on artificial immune system (AIS) and wavelet transforms. AIS are a type of intelligent algorithm they imitate the human defense mechanism and they use its principles, to give them the power to be applied as a classifier. Moreover, the wavelet transform offers fascinating features for texture classification. The experimental results show that it is possible to use the artificial immune system and the wavelet transform to recognize the image of the leafy plant, and the recognition accuracy is encouraging.