Ensuring a tart is cut into equal slices is a challenge — let alone at the rate of 200 tarts per minute on the production line. Add to that the task of making sure fragile toppings, such as the meringue on lemon meringue pies, are not damaged — and that each tarte au framboise has enough raspberries on the top — and it is clear that the latest generation of inspection technology can play a key role on the factory floor.
The stakes are high as many bakery products are luxury items, often in transparent packaging which allows the purchaser to see the item — so damaged and non-uniform products will be left on the supermarket shelf. This not only adds to food waste – dealing with such issues results in additional costs and disruption for manufacturers.
The use of low-energy X-ray imaging to detect foreign objects in food products is an established technique on the production line. It is based on being able to detect material that is substantially denser (higher in atomic number) than the food matrix. But guarding against cosmetic issues in luxury food products involves more than just looking for contrasting densities. It also requires looking at levels of contrast – the difference between soft fruit and the background filling, for example, as well as the crevices in the surface of a dessert created by a cutting tool. This requires enhanced detection capabilities and higher resolution.
This kind of inspection calls for the detection of differential greyscales in the inspection image, which are considerably smaller than the variation in the normal range of greyscales in a standard product. For example, a pie which comprises semi-glutinous material, when cut with a narrow blade, will show a channel where the blade has passed through the product. However, after withdrawing the blade, the crevice will tend to close due to the fluid nature of the pie filling. A similar situation exists with the coverage of raspberries on a pie. The variability in the image is within the normal range for the pie filling.
A standard approach would involve trying to adjust conventional density settings to pick out characteristic features of faulty products. This involves many iterative testing cycles to be able to achieve an acceptably high probability of detection, while maintaining an acceptably low false reject rate. But, in the examples highlighted above, the variability of the product relative to the image artifacts indicating non-conformant items would be too great to have a realistic chance of success.
In addition, conventional rule-based algorithms could not be applied because of the irregularity of the parts. So, the latest generation of inspection technology uses specially developed tools that allow large image sets to be acquired, with defects in differing positions and orientations. The image sets can be processed automatically, and associated diagnostic data collected and statistically analyzed, to allow a fast and efficient means of analyzing the effectiveness of the algorithms being deployed.
The result is that the technology can detect when a multi-bladed cutting tool on the production line is offset – resulting in uneven slices – by measuring the center of the slices relative to the outside diameter of the tart. Tarts which fail to meet the quality criterion will be rejected and – if there is a series of rejects – the inspection system will shut down the production line until the tooling is adjusted.
The latest technology can also detect the presence of the small plastic tripod designed to protect the fragile top of items such as lemon meringue pies so that they do not get crushed. It is important to ensure that a tripod is present on each pie – but only one, as a second one could be the result of a foreign body. This can be confirmed using the latest X-ray inspection technology. For a tarte au framboise, meanwhile, the emphasis is on a consistent covering of raspberries to look good. This can be achieved by taking an X-ray image of the product – either within or outside its carton – and applying an image processing algorithm to determine the coverage.
Quality control of these kinds of luxury items is crucial for brand reputation, as well as keeping costs down by reducing waste and production line disruption. The latest generation of X-ray inspection technology is hitting the sweet spot for manufacturers in more ways than one.
Dr Richard Parmee is founder and CEO of X-ray inspection technology specialist Sapphire Inspection Systems. As well as designing bespoke solutions, Richard and his team provide a wide range of standard X-ray inspection systems to cater for hundreds of different products in the food, pharmaceutical and cosmetics industries.