Automated illness detection: Potato illness detection applying Artificial Intelligence

Scientists from the Indian Institute of Technology (IIT) Mandi have created a computational model for automated illness detection in potato crops applying photographs of the leaves. The study led by Srikant Srinivasan, associate professor, School of Computing and Electrical Engineering, IIT Mandi, in collaboration with the Central Potato Research Institute, Shimla, makes use of Artificial Intelligence (AI) procedures to highlight the diseased portions of the leaf.

Potatoes, in the history of the world, have been the result in of the world’s wonderful famine of the mid-nineteenth century that killed more than a million people today in Ireland and rang the death knell for the Irish language. The cause? Potato Blight, a frequent illness of the potato plant, that begins as uneven light green lesions close to the tip and the margins of the leaf and then spreads into substantial brown to purplish-black necrotic patches that ultimately leads to rotting of the plant. If left undetected and unchecked, blight could destroy the complete crop inside a week.

“In India, as with most developing countries, the detection and identification of blight are performed manually by trained personnel who scout the field and visually inspect potato foliage,” explained Srinivasan. This procedure, as anticipated, is tedious and normally impractical, particularly for remote places, simply because it demands the presence of a horticulture specialist.

“Automated disease detection can help in this regard and given the extensive proliferation of the mobile phones across the country, the smartphone could be a useful tool in this regard,” mentioned Joe Johnson, study scholar, IIT Mandi, though highlighting the sensible usage of his study. The sophisticated HD cameras, improved computing energy and communication avenues supplied by smartphones present a promising platform for automated illness detection in crops, which can save time and assistance in the timely management of ailments, in situations of outbreaks.

The computational tool created by the IIT Mandi scientists can detect blight in potato leaf pictures. The model is constructed applying an AI tool referred to as mask area-based convolutional neural network architecture and can accurately highlight the diseased portions of the leaf amid a complicated background of plant and soil matter.

In order to create a robust model, wholesome and diseased leaf information had been collected from fields across Punjab, UP and Himachal Pradesh. It was vital that the model created had portability across the nation. “The model is being refined as more states are covered,” added Srinivasan and highlighted that it would be deployed as aspect of the FarmerZone app that will be readily available to potato farmers for free of charge.


Originally appeared on: TheSpuzz

Scoophot
Logo
Reset Password