Leaf Disease Detection of Multiple Plants Using Deep Learning
Shital Pawar, Sakshi Shedge, Nibedita Panigrahi, Aparna Jyoti, Pradnya Thorave, Samina Sayyad
Abstract
The great advancement in deep learning has increased the interest in technologies of image recognition. Different deep learning techniques help big data analysis with large potential and finding the disease of plant in agriculture sector. The deep learning model extract the features from an input and uses its features for classification. In consideration of climate change, plants are affected, which impacts agricultural yield. When the condition worsens, the plants become more susceptible to many diseases caused by fungi, bacteria, viruses, etc. Diseases can affect the plant growth. In the proposed system, CNN algorithm is used to detect the disease from leaf images and pesticides are suggested based on the disease found. The proposed method uses 15-layer CNN. The proposed system will provide pesticide supplier name according to area as well as it provides additional information about the leaf disease of the affected plant in the area, disease name, complete accuracy, time, and weather forecasting information also. The dataset contains 10 plants - apple, potato, corn, tomato, grape, rice, sugarcane, cucumber, pepper, soyabean.