Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
India is mainly an agro based country where good quality production of crops plays a very important role but frequent attack of pathogens leads to severe crop damage thus, decreasing their yield which poses a major threat to the food security. This, in turn affects the economy of our country very much and the farmers suffers great loss. Thus, proper monitoring of the crops on regular basis is very important to take proper actions on time and save the crops from further damage. Artificial Intelligence plays a crucial role in addressing several concerns in agriculture, thus it is important that the farmers should be provided with AI based technologies to boost up crop production. In this paper we propose a transfer learning based approach for classification of healthy and diseased bean leaf plants using ResNet152 pre-trained model. The performance metrics of the model was studied by evaluating the four important parameters: classification accuracy, precision, recall and f1-score. Experimental result proved that ResNet152 performs better with a higher accuracy (0.89) and f1-score (0.88) than the other pre-trained models. Further a training accuracy of 97% was achieved in just 30 epochs of the ResNet152 model. A comparison table of the performance parameters of the different pre-trained models is also summarized at the end of the paper.
Keywords:
Agriculture, Artificial Intelligence, Pre-trained Models, Residual Network, Transfer Learning.
Cite Article:
"A Deep Learning Approach for Classification of Healthy and Diseased Leaf Images using ResNet152", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.7, Issue 5, page no.411 - 415, May-2022, Available :http://www.ijrti.org/papers/IJRTI2205070.pdf
Downloads:
000205147
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator