Subject: Weed Control, Image Processing, Machine Learning, Precision Agriculture
Year: 2016
Type: Proceeding article
Title: Weed segmentation from grayscale tobacco seedling images
Author: Lameski, Petre
Author: Zdravevski, Eftim
Author: Kulakov, Andrea
Abstract: Manual weed extraction from young seedlings is a hard manual labour process. It has to be continuously performed to increase the yield per land unit of any agricultural product. Precise segmentation of plant images is an important step towards creating a camera sensor for weed detection. In this paper we present a machine learning approach for segmenting weed parts from images. A dataset has been generated using bumblebee camera under various light conditions and subsequently training and test patches were extracted. We have generated various texture-based descriptors and used different classification algorithms aiming to correctly recognize weed patches. The results show that in a case when the images are gray-scale, the light conditions are varying, and the distance of the camera to the weeds is not constant machine learning algorithms perform poorly
Publisher: Springer, Cham
Relation: International Conference on Robotics in Alpe-Adria Danube Region
Identifier: oai:repository.ukim.mk:20.500.12188/21231
Identifier: http://hdl.handle.net/20.500.12188/21231
