Main Article Content


In this paper an automated technique for leaf disease identification that is robust to uncontrolled environments and applicable to different leaf disease species. In existing method relies on an end-to- end residual convolutional neural network (CNN) that represents the state-of-the-art in semantic segmentation. To enhance its sensitivity to leaf diseases, we fine-tune this network using a single dataset of apple leaf disease images. In proposed method refinement method to better distinguish between individual leaf disease instances. Without any preprocessing or dataset-specific training, experimental results on images of apple, peach and pear leaf diseases, acquired under different conditions demonstrate the robustness and broad applicability of our method. In this project analysis a digital image processing and analysis techniques for automation of agricultural products and prediction of yields. The proposed analysis image processing techniques include color, size and shape features. This paper analysis new approach leaf disease image segmentation is applying non linear algorithm. The color and texture features have been used in order to work with the sample images of leaf disease diseases.

Article Details

How to Cite
.P.Jeevitha, & R.Navin Kumar. (2019). Image processing based leaf rot disease detection of betel vine . International Journal of Intellectual Advancements and Research in Engineering Computations, 7(1), 789–794. Retrieved from