Abstract: One of the major obstacles that an agriculturist may experience in their cultivation is plant stress, which can result in severe economic crop loss. Nitrogen deficiency is one of the most common causes of plant stress. Nitrogen deficiency causes stunted growth in plants, depending on the severity of the stress. To aid agriculturists, developers are investigating several approaches for measuring plant stress. To evaluate plant stress, the suggested system uses Deep Learning and convolutional neural networks, as described in this research. Deep learning-based methods are more efficient at measuring different plant traits for diverse genetic discoveries while searching for plant stress than traditional image-based phenotyping methodologies.This research takes a deep learning method to picture analysis. This suggested approach uses deep convolutional neural networks (CNNs) to detect as well as pixel-wise segment features to capture high-resolution photos without sacrificing pixel density, resulting in more accurate detection. In addition, the proposed model also outperforms traditional Machine Learning techniques like SVM, KNN, DT by achieving an average of 10% better accuracy.
Keywords: Deep learning; Convolutional neural network; Plant stress; Transfer learning;
|
DOI:
10.17148/IJARCCE.2022.11731
