Open AccessAUTOMATED WEED REMOVAL SYSTEM USING CONVOLUTIONAL NEURAL NETWORK
Author(s) -
J P Mounashree,
Nithesh Singh Sanjay,
B S Sushmitha,
B G Usha,
Anupama Shivamurthy
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i02.033
Subject(s) - weed control , weed , convolutional neural network , computer science , agricultural engineering , agriculture , artificial intelligence , machine vision , precision agriculture , process (computing) , workload , agronomy , engineering , geography , archaeology , biology , operating system
Weeds are very annoying for farmers and alsonot very good for the crops. Its existence might damage thegrowth of the crops. Therefore, weed control is veryimportant for farmers. Farmers need to ensure theiragricultural fields are free from weeds for at least once aweek, whether they need to spray weed herbicides to theirplantation or remove it using tools or manually. The aim ofthis research is to build an automated weed control system.The system consists of motors, Raspberry pi and a camerawhich we use to capture the image of the crops and weeds.An automated image classification system has beendesigned to differentiate between weeds and crops. For theimage classification method, we employ the convolutionalneural network algorithm to process the image of theobject. Deep learning is used to analyze the relevantfeatures from the agricultural images. The dataset istrained for the classification of weed and crop. Therefore,by the use of technology, farmers can reduce the amount ofworkload and workforce they need to monitor theirplantation. In addition, this technology also can improvethe quality of the crops.