Published Paper Details:

The project's primary objective is to find coconut palm disease and coconut maturity, with the objective of improving the quality of the product yield. It is difficult for a farmer to manually monitor coconut palm disease and maturity, which can take an extended period of time. Coconut palm diseases include seeding disease, white fungal disease, and spotting disease. The proposed system aids in the identification of coconut palm disease and coconut maturity, as well as to provide remedies for the disease and determining coconut maturity, which is the project's primary objective. Currently, solutions are found through image-processing techniques involving the identification of coconut maturity stages. As a matter of fact, an improved convolutional neural network model for order to detect two important coconut maturity stages, mature and immature, is proposed. Because of the complexity of the environment and the similarity between coconuts and their backgrounds, ability to detect the maturation stages of coconuts for harvesting without human intervention presents a challenge. To solve the problem, CNN model with Densenet architecture was employed for Coconut palm disease prediction and Resnet architecture was put to use for coconut maturity analysis. The final output will be easily obtained by using these architectures.