The determination of plant species from ̄eld observation requires substantial botanical expertise, which puts it beyond the reach of most nature enthusiasts. Traditional plant species identi ̄cation is almost impossible for the general public and challenging even for professionals who deal with botanical problems daily such as conservationists, farmers, foresters, and land- scape architects. Even for botanists themselves, species identi ̄cation is often a di±cult task. This paper proposes a model deep learning with a new architecture Convolutional Neural Network (CNN) for leaves classi ̄er based on leaf pre-processing extract vein shape data replaced for the red channel of colors. This replacement improves the accuracy of the model signi ̄cantly. This model experimented on collector leaves data set Flavia leaf data set and the Swedish leaf data set. The classi ̄cation results indicate that the proposed CNN model is e®ective for leaf recognition with the best accuracy greater than 98.22%.