The computer application developed by the researchers using a complex computational model can detect blight in potato leaf images

Scientists from the Indian Institute of Technology (IIT) Mandi, have developed a computational model for automated disease detection in potato crops using photographs of its leaves. The research led by Dr Srikant Srinivasan, Associate Professor, School of Computing and Electrical Engineering, IIT Mandi, in collaboration with the Central Potato Research Institute, Shimla, uses Artificial Intelligence (AI) techniques to highlight the diseased portions of the leaf.

Funded by the Department of Biotechnology, Government of India, the results of this research have recently been published in the journal Plant Phenomics, in a paper co-authored by Dr Srikant Srinivasan and Dr Shyam K Masakapalli along with research scholars, Joe Johnson, and Geetanjali Sharma, from IIT Mandi, and Dr Vijay Kumar Dua, Dr Sanjeev Sharma, and Dr Jagdev Sharma, from Central Potato Research Institute, Shimla.

The Blight is a common disease of the potato plant, that starts as uneven light green lesions near the tip and the margins of the leaf and then spreads into large brown to purplish-black necrotic patches that eventually lead to rotting of the plant. 

The advanced HD cameras, better computing power and communication avenues offered by smartphones offer a promising platform for automated disease detection in crops, which can save time and help in the timely management of diseases, in cases of outbreaks.

The computational tool developed by the IIT Mandi scientists can detect blight in potato leaf images. The model is built using an AI tool called mask region-based convolutional neural network architecture and can accurately highlight the diseased portions of the leaf amid a complex background of plant and soil matter.

In order to develop a robust model, healthy and diseased leaf data were collected from fields across Punjab, UP and Himachal Pradesh. It was important that the model developed should have portability across the nation.

“Analysis of the detection performance indicates an overall precision of 98 per cent on leaf images in field environments,” said Dr Srinivasan.

Following this success, the team is sizing down the model to a few tens of megabytes so that it can be hosted on a smartphone as an application. With this, when the farmer will photograph the leaf which appears unhealthy, the application will confirm in real-time if the leaf is infected or not. With this timely knowledge, the farmer would know exactly when to spray the field, saving his produce and minimising costs associated with unnecessary use of fungicides.

“The model is being refined as more states are covered,” added Dr Srinivasan and highlighted that it would be deployed as part of the FarmerZone app that will be available to potato farmers for free.