Plant Identification Using New Architecture Convolutional Neural Networks Combine with Replacing the Red of Color Channel Image by Vein Morphology Leaf

Abstract

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

Keywords

• deep learning
• convolutional neural networks
• leaf classification