Design and evaluation of a deep CNN algorithm for detecting farm weeds. (3rd February 2023)

• Record Type: Journal Article
• Authors: Pattanaik, Balachandra; Malibari, Areej; Kumarasamy, M.; Nagaraj, V.; Gopikrishnan, M.
• Is Part Of: International journal of engineering systems modelling and simulation. Volume 14:Number 2(2023)
• Page Start: 71
• Page End: 79
• Publication Date: 2023-02-03
• Subjects: image processing -- deep learning -- convolutional neural networks -- CNN -- rectified linear units -- ReLU -- weed detection -- automation; Engineering systems -- Computer simulation -- Periodicals; Engineering systems -- Mathematical models -- Periodicals; 620.0042
• Languages: English
• ISSNs: 1755-9758

Abstract

Weeds are unwanted plants that grow with crops and usually removed by spraying herbicides or by manual labour. Herbicides being sprayed mostly do not reach their target because of the focus on a very wide area. This also tends to harm the environment, and other living organisms. Manual labour is time-consuming and expensive and it is continuously managed and monitored. The autonomous robotics and image processing tasks can be completed with precision and ease in agriculture. With image processing, plants and weeds can be classified. Methods like scale invariant feature transforms (SIFT), speeded-up robust features (SURF), and ensemble learning, neural networks can be incorporated into identifying the difference. We can easily classify weeds and crops from images of plantations leveraging machine learning algorithms, artificial vision analysis systems, among others. Deep learning methods like convolutional neural network (CNN), rectified linear units (ReLU) and SoftMax (for classification) are focused in this paper.