Identification Of Blight Disease In Cashew Leaf Using Deep Convolution Neural Networks


  • T. Mahendran Assistant professor of Computer Applications Arignar Anna Government Arts College, Villupuram – 605 602. Tamilnadu, India


cashew leaf, blight disease, DCNN, pattern recognition, machine learning, accuracy.


This cashew plant in India, one of the world's top cashew-producing nations, is severely afflicted by the blight disease. The plant leaves affected by the blight illness are completely dried out and perished. When crop diseases are first identified, saving the cashew plant can help farmers take prompt precautions and countermeasures to get rid of them. At the moment, deep learning is a hot field for research in pattern recognition and machine learning; it is effective at finding these issues in cashew plants. In this study, we suggest a deep convolution neural network (DCNN)-based method for identifying blight diseases. Utilizing a dataset of 200 unedited images of unhealthy and healthy cashew leaves taken in a cashew experimental field. DCNNs are trained to recognize the blight disease 80% of the time and use images of cashew leaves for testing 20% of the time. The accuracy of the suggested DCNNs-based representation
is 96.48%. Compared to traditional machine learning models, this accuracy is far higher. The farmers can get a sense of the viability and efficacy of the suggested strategy from the simulation results for the early detection of cashew blight disease.




How to Cite

T. Mahendran. (2023). Identification Of Blight Disease In Cashew Leaf Using Deep Convolution Neural Networks. Chinese Journal of Computational Mechanics, (5), 257–263. Retrieved from