A major part of the Indian economy relies on agriculture, thus, identification of any diseased crop in the initial phase is very important as these diseases cause a significant drop in agricultural production and also affect the economy of the country. Tomato crops are susceptible to various diseases, which may be caused due to transmission of diseases through Air or Soil.
The researchers have tried to automate the procedure of detection of diseases in the Tomato Plant by studying several attributes related to the leaf of the plant. Using various machine learning algorithms such as Support Vector Machine (SVM), Convolutional Neural Network (CNN), ResNet, and InceptionV3, the researchers have trained the model and based on the results obtained, they have evaluated and compared the performance of these algorithms on different features set.
The dataset resulted in 10 classes (healthy and other unhealthy classes) having a total of 18,450 images for the training of the models. After implementing all of the algorithms and comparing their results, the researchers found that the ResNet was most appropriate for extracting distinct attributes from images. The trained models can be used to detect diseases in Tomato Plant timely and automatically.
Read the complete research at www.researchgate.net.
Sharma, Anshul & Chandak, A. & Khandelwal, Aryan & Gandhi, Raunak. (2022). Detection of Diseases in Tomato Plant using Machine Learning. International Journal of Next-Generation Computing. 10.47164/ijngc.v13i5.941.