Published Paper Details:

The Areca nut, otherwise called the betel nut, holds huge significance as a tropical yield, with India remaining as the second-biggest maker and purchaser universally. All through its development organizes, the areca nut faces various sicknesses influencing different parts from the roots to the natural products. Customarily, distinguishing these sicknesses has depended on manual visual reviews by ranchers, which isn't just work serious yet additionally inclined to errors.To alleviate these difficulties, we propose an inventive strategy utilizing AI procedures to robotize the quality recognition of areca nuts. Our methodology uses the K-Closest Neighbor (KNN) and Backing Vector Machine (SVM) calculations to characterize the nuts into classifications of positive or negative quality. For this reason, we fostered a custom dataset containing 208 pictures of areca nuts, including both great and terrible quality examples, to prepare and test our models.The KNN calculation accomplished a high precision of 95.12%, fundamentally beating the SVM calculation, which recorded an exactness of 65.68%. These outcomes feature KNN's prevalent presentation in distinctive the nature of areca nuts in light of picture separated features.Our study underscores the capability of AI in rural applications, giving a more effective, exact, and versatile answer for surveying areca nut quality. This innovative headway can fundamentally help ranchers by diminishing the time and work expected for crop examination and improving in general yield the executives. Future examination will zero in on augmenting the dataset, refining the calculations, and creating pragmatic apparatuses for certifiable application.