Disease Detection in Fruits using Convolutional Neural Networks

Plant and fruit diseases are a main intimidation to food protection, but their quick identification remains not easy in many parts of the world due to the lack of the necessary infrastructure. Plant and fruit disease of images using segmentation and classification plays an important role in the disease detection through symptoms. A novel segmentation and classification method of disease leaf and fruit image is proposed based on a Super pixel Segmentation. The whole color leaf and fruit image is firstly divided into a number of compact and nearly uniform super pixels by super pixel clustering, which can provide useful clustering cues to guide image segmentation to accelerate the convergence speed of the existing algorithm, and then, the lesion pixels are quickly and accurately segmented from each super pixel by SLIC algorithm. And also disease can be detection based on deep learning algorithm which includes cconvolution neural network algorithm. The experimental results and the comparison results with related approaches reveal to the proposed method is effective and has high realistic value for disease detection.