Visualization of Plant Leaf Classification Process Based on Multi-Layer Network Model

Abstract

Tree recognition is a ubiquitous topic in the field of artificial intelligence, and the identification of leaf types is one of the important ways in analyzing tree species. Based on the focalized attention mechanism and feature fusion strategy, we in this paper establish a multi-layer network model classifier: Leaf-AMNet to classify the Liriodendron leaves and Ginkgo leaves. In order to explore the "black box" problem of deep learning, we visualize the classification process of Leaf-AMNet. Experimental results show that Leaf-AMNet achieves high accuracy on Leaf Dataset and shows potential information via visual effects.