Detection and Categorization of Sorghum Crop using MCRNN Architecture

Sorghum crop detection is highly favored in the field of agricultural information. Deep learning has been responsible for remarkable improvements in the accuracy of image categorization and detection systems over the last decade. These improvements have been made possible by recent technological adv...

Full description

Saved in:
Bibliographic Details
Published in2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 1505 - 1509
Main Authors Murugan, M.Senthil, Sungeetha, D., Vijaya, K., Soundari, A. Gnana, Dhanalakshmi, R., Gomathi, S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.09.2023
Subjects
Cancer
Computational modeling
Computer architecture
Crop detection
Crops
Deep learning
long short-term memory
Performance evaluation
Plant diseases
Sorghum
Standardization
Online AccessGet full text

Cover

More Information
Summary:Sorghum crop detection is highly favored in the field of agricultural information. Deep learning has been responsible for remarkable improvements in the accuracy of image categorization and detection systems over the last decade. These improvements have been made possible by recent technological advancements. In the agricultural industry, the most significant barrier to entry is classification and identification. As a result, it is of the utmost importance to create effective methods for the automatic detection, identification, and prediction of crops as a result of the fact that some crops are utilized for therapeutic purposes. Deep learning strategies can be utilized to extract knowledge and relationships from the data that is currently being processed in order to facilitate the automation of such processes. This article discusses the application of DL in the agricultural sector, with a particular emphasis on the tasks of crop classification and detection, particularly with regard to the sorghum crop, which possesses the capacity to inhibit the development of cancer. Therefore, for the purpose of accurate crop detection and categorization, has been applied a well-known model K-fold cross-validation technique with the proposed architecture in this study. The sorghum test dataset, which contains around 50,000 image samples of sorghum plant leaf, was utilized in the studies that were conducted. The performance was judged based on the identification and detection accuracy.
DOI:10.1109/ICOSEC58147.2023.10275812