WEED DETECTION IN CROPS USING AI/ML

This project presents an intelligent AI and Machine Learning–based weed detection system that effectively addresses key challenges in modern agriculture. By using image-based analysis, the system accurately distinguishes weeds from crops without relying on specialized hardware orIoT devices. The proposed approach reduces manual effort, minimizes unnecessary herbicide usage, and supports precision farming practices. Its scalable design allows deployment across different crop types and field conditions. The system operates efficiently on standard hardware, making it accessible to farmers with limited resources. Reliable detection and clear result visualization enhance usability and decision-making. Overall, the system contributes to sustainable agriculture by improving crop productivity and promoting environmentally responsible weed management.

[1]   Sharma, R., Patel, K., & Mehta, S. (2025). Vision transformer-based weed detection for precision agriculture under real field conditions. Computers and Electronics in Agriculture, 219, 108921.   [2]  Wang, L., Zhou, Y., & Li, H. (2025). Intelligent crop–weed segmentation using hybrid deep learning models. IEEE Transactions on Artificial Intelligence, 6(1), 55–68.   [3]  Liu, Y., Zhang, H., & Wang, J. (2024). Deep learning-based crop and weed classification in complex agricultural environments. Precision Agriculture, 25(2), 410–428. [4]  Ahmed, S., Khan, M. A., & Ullah, A. (2024). Lightweight convolutional neural networks for real-time weed detection on edge devices. IEEE Access, 12, 55630–55642.   [5]   Verma, P., Singh, R., & Yadav, A. (2024). AI-driven image analysis for selective weed control in smart farming systems. Journal of Agricultural Informatics, 15(3), 21–34.   [6]   Rahman, M. M., Islam, T., & Hossain, M. (2023). Transfer learning-based weed detection using crop field images. Sensors, 23(7), 3451.   [7]  Boursianis, A. D., Papadopoulou, M. S., & Goudos, S. K. (2023). Artificial intelligence and computer vision for weed management in smart agriculture. Journal of Agricultural Informatics, 14(1), 1–15.   [8]    Zhang, X., Li, D., & Chen, Y. (2023). Automated weed identification using deep convolutional neural networks in precision farming. Biosystems Engineering, 226, 75–88.   [9]    Li, X., Chen, Z., & Yang, Y. (2022). Deep convolutional neural networks for weed recognition in crop fields. Biosystems Engineering, 215, 41–55.   [10]    Sudars, K., Jasko, J., & Namatevs, I. (2022). Deep learning-based plant and weed classification for precision agriculture applications. Agronomy, 12(4), 876.