Identification of weed by using Convolutional Neural Network algorithm in Deep Learning

Diksha Suresh Girigosavi; Sneha Deshmukh; Aarti Dandvate

Identification of weed by using Convolutional Neural Network algorithm in Deep Learning

Authors: Diksha Suresh Girigosavi, Sneha Deshmukh, Aarti Dandvate

Unique Paper ID: 160769
Volume: 10
Issue: 1
PageNo: 1181-1184

Keywords: CNN Classification Convolutional Neural Network Image processing Weed Classification

Abstract:
Weeds present in the crops are one of the major factors that lead to a decrease in crop production. Weed control is essential in agricultural productivity as weeds act as a pest to crops. The weeds take up nutrients, and water which leads to weight reduction in plants and decreases the grains per ear and grain yield. So a method needs to be developed which would detect these weeds in the field and then herbicide is sprayed on them to completely destroy them through the use of convolutional neural networks. The weed removal process is a vital part of the agricultural fields. The usual way to remove the weed is time-consuming and also requires more manual labor work. The aim is to remove the weeds in agricultural fields automatically. The proposed work is used to detect the weed which is grown between crops using a deep learning technique and remove the weeds with an automatic cutter. Deep learning is used to analyze the relevant features from the agricultural images. The dataset is trained for the classification of weeds and crops. In deep learning, Convolutional Neural Network(CNN) uses the convolutional layer with a ReLU function for extracting the features of an image and uses a max-pooling and fully connected layer with ReLU to classify the weed from the crop. Here, The pre-processed image is applied to the CNN network. From the resultant image, the Region Of Interest(ROI) is extracted, and also extract some features for training. After training, the classification is done. Thus the weed is detected using a deep-learning network. In this,100 images are trained to improve accuracy.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 10
Issue: 1
PageNo: 1181-1184

Identification of weed by using Convolutional Neural Network algorithm in Deep Learning

Available:https://ijirt.org/Article?manuscript=160769

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now