webvic-c

TOMRA Neon: Adding value and ease to machine-harvested blueberries

By employing artificial intelligence modelling, TOMRA Neon detects clusters with unrivalled accuracy. (Image source: TOMRA)

The new TOMRA Neon, a blueberry pre-grader with state-of-the-art AI technology enables blueberry growers to automatically process machine harvested blueberries for the fresh market, bringing overall value to the blueberry business model

Machine harvesters are undoubtedly faster and cost-effective than manual picking. However, they do also tend to harvest debris and fruit clusters which cause disruption on packhouse production lines. Moreover, they also harvest unwanted green and red berries which unnecessarily reduce pack-out from grading lines. 

The new TOMRA Neon works by pre-grading machine-harvested blueberries before transferring the fruit directly onto TOMRA’s KATO260 optical sorter and sizer. By employing artificial intelligence (AI) modelling, TOMRA Neon detects clusters with unrivalled accuracy. Being compact, durable, and easy to clean, it fits perfectly into any processing and packing line. 

Recognising the challenge

Being labour-intensive and physically tiring, manual blueberry harvesting is no longer preferred by harvesters, making it increasingly difficult for growers to recruit and retain seasonal harvesting staff. This has accelerated the adoption of automated harvesting. By working closely with blueberry growers and packhouses, TOMRA Food recognised the need to help customers move to machine harvesting, adding value by reducing labour requirements, while still delivering the highest quality product to the consumer. 

Detailed conversations with customers led to TOMRA setting itself the task of designing and developing a blueberry pre-grader that is technically sophisticated, robust, easy to maintain, easy to clean, and yet also price sensitive.

To achieve the necessary technical sophistication, TOMRA’s engineers drew extensively on their experience developing the company’s LUCAi AI technology, an optional add-on for the KATO260 which classifies and grades fruit with unrivalled accuracy. LUCAi employs deep learning, which uses pre-trained models to teach computers how to process data, such as complex patterns in photos – a principal which TOMRA will extend to other applications. 

Impressive results

After being tested and validated over two-and-a-half years in varied machine-harvested conditions in North America and New Zealand, it has been found that TOMRA Neon optimises optical grader efficiency by removing more than 95% of clusters and more than 90% of green and red berries. Moreover, TOMRA Neon runs with a throughput capacity of up to 500 berries per second, thanks to its unique ejection manifold. Even when fruit removal is as high as 40%, an output speed of up to 280 berries per second can be maintained to keep the KATO260 running at full capacity.

For more information, visit: www.tomra.com