American Society of Agricultural and Biological Engineers

Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Crop verses Weed Recognition with Artificial Neural Networks

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Paper number  013104,  2001 ASAE Annual Meeting. (doi: 10.13031/2013.7425) @2001
Keywords:   Machine Vision, Artificial Neural Networks, Plant Recognition, Robotic Weed Control

A weed detection algorithm using a neural network-based computational engine for a robotic weed control system was evaluated. A software-based neural network-based vision system successfully classified weeds; cotton plants and soil on images collected in commercial cotton fields. Ninety-three percent of the weeds were correctly mapped for herbicide application and 91% of the cotton plants were correctly mapped for no herbicide treatment.

(Download PDF)    (Export to EndNotes)