DefinePK hosts the largest index of Pakistani journals, research articles, news headlines, and videos. It also offers chapter-level book search.
Title: A leaf disease image classifier using deep residual networks and YOLOv3 object detection algorithm
Authors: Jessica S. Velasco, Gilbert B. Hollman, Nilo Arago, Roel Mendoza, Nikka Marie D. Manuel, Ernel Angelo D. Zulueta, Lean Karlo S. Tolentino
Journal: ARPN Journal of Engineering and Applied Sciences
Publisher: Khyber Medical College, Peshawar
Country: Pakistan
Year: 2022
Volume: 17
Issue: 15
Language: English
Nowadays, technology has been part of everyone’s life. Technology advancements are now making a new phase in the medical field. Emerging machine learning technologies are beginning to transform agricultural sciences and improve them in making such many ways. To aid in the detection and classification of plant diseases, the study presents a Deep Learning approach by examining the leaf of the given plan. Furthermore, the categorization is performed in steps to eliminate possibilities at each level, resulting in increased prediction accuracy. To identify a leaf in the supplied image, a YOLOv3 object detector is utilized. ResNet18 is used to analyze the leaf. ResNet18 model is were trained to subject the transfer learning. Once that each layer is identified, the type of leaf will check and the models of Convolutional Neural Network will classify what diseases that occur in a plant. A disease identification system with an accuracy of 96% was developed. Research shows that management of crop diseases can help improve.
Loading PDF...
Loading Statistics...