Leaf Detection by Extracting Leaf Features with Convolutional Neural Network
9 Pages Posted: 15 Jul 2019 Last revised: 30 Sep 2019
Date Written: May 18, 2019
Plants are backbone of human’s life and plays vital role by providing us food and oxygen. In order to improve the drug industry, balance the ecosystem as well as the agricultural productivity and sustainability there is need of good understanding of plants to help in identifying new or rare plant species. In proposed system, learning of leaf features extracts from pre-processed image instead of raw image. Extraction of leaf features under series of convolution layers reduces time complexity than hand crafted features. In this System also decides raw image are gone through image pre-processing stage like background removal, edge detection and gray scale conversion. Evaluate the hierarchical transformation of leave features from low level to higher level abstraction. First of all train a pre-process leaf data under CNN layer and find that the network exhibits layer-by-layer transition from general to specific types of leaf features.
Keywords: Leaf Features, Convolutional Neural Network (CNN), Pooling, Venation
JEL Classification: Y60
Suggested Citation: Suggested Citation