Mango Leaf Diseases Detection using Deep Learning

Abstract

Click Here:Access Full Text

Diseases and pests cause great economic loss to the mango industry every year. The detection of various mango diseases is challenging for the farmers as the symptoms produced by different diseases may be very similar, and may be present simultaneously. This research paper is an attempt to provide the timely and accurate detection and identification of mango leaf diseases. Convolutional Neural Networks are end-to-end learning algorithms which perform automatic feature extraction and learn complex features directly from raw images, making them suitable for a wide variety of tasks like image classification, object detection, segmentation etc. In the proposed study, we develop a Convolutional Neural Networks based model for detection and classification of mango leaf diseases at the initial stages. Data augmentation is performed on a collected dataset. We applied data augmentation techniques like rotation, translation, reflection and scaling. Convolutional Neural Networks model has been trained on the augmented data for detection and classification of mango leaf diseases. The proposed CNN based model attains 90.36 percent of accuracy. The results validate that the proposed method is effective in detecting various types of mango leaf diseases and can be used as a practical tool by farmers and agriculture scientists.

Keywords: Convolution Neural Network (CNN), Crop, Deep learning, Image classification, Mango.

View PDF