Smart Agriculture: Utilizing Image Processing for Real-Time Crop Disease Monitoring

Smart Agriculture: Utilizing Image Processing for Real-Time Crop Disease Monitoring

Ms. Priyanka Lalasaheb Naikal1  , Ms. Sujata Gaikwad 2 , Mr. Parmeshwar Suresh Deshmukh3

2 TPCT’s College of Engineering , Osmanabad (Dharashiv), India.

priyankanaikal12@gmail.com , sujatagaikwad414@gmail.com,psdeshmukh111995@gmail.com

Abstract: The K-Means clustering technique is a widely recognized method for low-level image segmentation challenges, converging iteratively to refine partitioning decisions based on an initial user-specified cluster set that updates with each iteration. Initially, our approach identifies predominantly green-colored pixels in the image, which are then masked based on threshold values computed using Otsu's method. Subsequent masking eliminates any remaining predominantly green pixels. Additionally, pixels with zero values for red, green, and blue channels, as well as those along the boundaries of the infected cluster, are systematically removed. Experimental findings highlight the robustness of this technique in detecting plant leaf diseases, demonstrating its efficacy in real-world scenarios.

Keywords: Image Segmentation, K-Means clustering, Crop disease detection, Image processing, Agriculture, Machine learning,