Matrox vision system enables fruit sorting

The system allows packers to accurately grade fruit according to pre-established quality and colour criteria to meet market requirements.

Processing and packaging costs are reduced as substandard fruit is immediately removed from production batches.

The vision system includes proprietary double-sensor CMOS high-resolution cameras - one colour and one infrared camera per lane, acquisition boards and LED lighting.

20 colour pictures and 20 infrared pictures are taken of each piece of fruit as it moves and rotates forward - covering 100 per cent of its surface.

The vision system can perform optical sizing (equatorial or maximum diameter, volume integration), colour sorting (eight different criteria) and detection of external defects on the fruit.

The images are then processed using the Matrox Imaging Library (MIL) toolkit.

Binarisation and blob analysis are used to separate the fruit from its background and to obtain dimensions such as Feret diameters and elongation, for example.

The HLS (Hue, Luminosity, Saturation) colour space conversion and statistical functions are used for colour processing.

Convolutions and custom-designed algorithms recognise stems and cores, and reject fruit with defects on the skin, such as black spots or russet.

The system's user interface, which includes a 3D display, lets operators adjust quality and sorting parameters in real time and store them for future use.

Globalscan gives production managers the ability to analyse the data gathered from the vision system and generate statistics by producer, orchard or field, species or variety of fruit.

Reports provide metrics on the batch of fruit that is being processed including size, weight, diameter, colour and quality.