2 Years Impact Factor:
2.85
5 Years Impact Factor: 1.53
Author: B. Pavansai, L. Saiteja , V. Ganesh , Mr. Ch. Durga Mallikarjun Rao
Abstract:
The classification of plant seedlings plays a crucial role in sustainableagriculture, with the global market for smart farming projected to reach $22 billion by 2025. Approximately 40% of agricultural produce is lost due to weeds and misidentification of plant species, highlighting the need for effective classification systems. Furthermore, inefficient manual identification methods can lead to reduced crop yields and increased costs for farmers. Existing systems predominantly rely on manual labor for seedling identification, which is time-consuming and prone to human error. This research proposes a novel deep learning framework that incorporates image data preprocessing techniques to enhance the accuracy of plant seedling classification. By leveraging convolutional neural networks (CNNs) and employing an ensemble classification approach, the proposed system aims to accurately classify various seedlings, including Black-grass, Charlock, Cleavers, and others. This advancement in c
Download PDF