Plant Leaf Diseases Detection Using Fuzzy C-Mean and Gaussian Smoothing

  • Monika Mangla, Deepika Punj, Shilpa Sethi


Plants are very susceptible to the onslaught of diseases; diseases of plants can be distinguished from the buds on the leaves. The disease is visually recognizable as it has a unique color and texture features. But visual recognition has the disadvantage that it affects the inaccuracy of the identified disease. In this context, image processing using sophisticated algorithms has long been used. However, due to real world constraints such as noise, shadowing and fluctuations in cameras, they are often overkill image processing tasks. To detect plant leaf diseases, two alternative methodologies: A Fuzzy C-Mean approach that automatically learned for the number of clusters which intensify the detection accuracy and a concoction of Gaussian function with Convolution Neural Network (CNN) which smoothen images, remove higher frequencies and noise has been used. In this research, the test was conducted with 200 samples of various category of leaves imagery, 160 imagery as training data and 40 imagery as test data. A comparative analysis has been performed between Fuzzy C-Mean and Gaussian Function using CNN on various shape features like elongation, solidity and some texture features like smoothness, uniformity and entropy. Experimental results show that Gaussian function using CNN performs better with 97.50% accuracy as compared to Fuzzy C-Mean which provides 95% accuracy.

How to Cite
Monika Mangla, Deepika Punj, Shilpa Sethi. (2020). Plant Leaf Diseases Detection Using Fuzzy C-Mean and Gaussian Smoothing. International Journal of Advanced Science and Technology, 29(3), 10497 -. Retrieved from