Scopus Indexed Publications

Paper Details

Automatic Recognition of Plant Leaf Diseases Using Deep Learning (Multilayer CNN) and Image Processing
Abdur Nur Tusher, Narayan Ranjan Chakraborty , Mst. Sakira Rezowana Sammy, Shornaly Akter Hasna,

Bangladesh is highly dependent on Agricultural production on it’s economic strength, however different types of diseases have made an enormous damage on the growth of agricultural crops. Bacterial Blight and leaf brown spot (common rust) are the most common diseases affecting the guava, mango, rice, corn and peach plant. Thus, it is become very essential to detect leaf diseases early to protect from damaging the entire crop. The farmers have no enough knowledge about the leaf disease and they used manual process in order to identify disorder. So, the detection accuracy is not good enough and time consuming. An automated and accurate identification system has become essential to overcome this problem. In this paper, a novel technique to diagnose and classify guava, mango, rice, corn and peach diseases has been proposed. One of the effective and modern method for finding the disorder and providing appropriate treatment is deep learning. We have mainly focused on CNN algorithm for training the dataset and found 95.26% accuracy rate. Identification of the diseases would help Bangladesh to grow its economy as it will increase the production rate of guava, mango, rice, corn and peach plants.

CNN Computer vision Plant leaf disease Machine learning Image processing Deep learning Bacterial blight Brown spot Common rust
Journal or Conference Name
Lecture Notes in Networks and Systems
Publication Year