Tools
Tools
Vad, Rohit (2020) Weed Detection in Soybean Crops using Regression Analysis and Deep Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (626kB) | Preview |
Preview |
PDF (Configuration manual)
Download (465kB) | Preview |
Abstract
The troublesome and unwanted effects of weeds are often are a cause for an injury or degradation to the health of the yield. Weeds constantly consume nutrients, water, and sunlight, thereby decreasing the quality and the quantity of the crop that is cultivated. Using deep learning and regression analysis, this paper focuses on the principle of image classification and extends it to detecting weeds in soybean crops and classifying the images into broadleaf weeds, soil, grass or soybean. This application provides great help to the agricultural sector by aiding the farmers select the specific herbicide for spraying depending on the type of weeds and thereby stunting it. Deep learning techniques such as Convolution Neural Network (CNN), Artificial Neural Network (ANN) and traditional machine learning algorithm Logistic Regression were implemented for the purpose of detecting and classifying weeds in images. The performances of these models were compared and evaluated based on accuracy of each model. The Convolutional Neural Network model significantly outperforms the other two with an accuracy of 97%.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software S Agriculture > S Agriculture (General) |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 21 Jan 2021 11:43 |
| Last Modified: | 21 Jan 2021 11:43 |
| URI: | https://norma.ncirl.ie/id/eprint/4426 |
Actions (login required)
 |
View Item |