Amazon India 2

Amazon India has revealed plans to build grading and packing solutions for fruits and vegetables harnessing the power of machine learning (ML).

At Amazon India’s Amazon Smbhav event, Rajeev Rastogi, Amazon India vice president (machine learning), said the company planned to develop a conveyor belt-based automatic grading and packing machine.

“We are building a computer vision-based grading solution for products such as onions and tomatoes,” said Rastogi.

“The ML based approach analyses produce images to detect defects such as cuts, cracks, pressure damage etc. and can carry out millions of assessments per day at a cost that is far below that of any other method.”

Rastogi said the machine will reduce grading costs by 78 per cent compared to manual grading, leveraging hardware and ML to pack produce into pre-determined quality grades.

“Quality is one of the key drivers of fruit and vegetable purchasing decisions, and a critical factor in achieving customer satisfaction,” explained Rastogi.

“Having humans grade the quality of fruits and vegetables by manually examining each individual piece of produce - each tomato or each onion is not scalable to millions of quality assessments per day.”

Amazon’s solution is also set to use near infrared sensors and to detect attributes such as sweetness and ripeness, according to Rastogi.