Contamination of food with fragments of bone, metal, glass, or other foreign material is a major concern in the food industry. Current inspection technologies often miss very small fragments embedded in meat or other soft materials or lead to ambiguous results that require time-intensive verification.
Battelle has developed a Microfocus Dual-Energy Radiographic System that leverages advanced algorithms to improve contaminant detection and identification in meat and poultry. The same technique could one day be applied for high-resolution imaging in other industries from airline security to medicine.
The system combines three components to improve the accuracy and resolution of contaminant detection:
Microfocus: A microfocus camera allows smaller objects to be seen and gives better measurements for attenuation properties.
Dual-energy radiography: The system uses both high-energy (HE) and low-energy (LE) radiography to produce two simultaneous radiographic images. Materials with different densities respond differently to HE and LE energies.
An advanced computer algorithm: An intelligent algorithm analyzes both images to provide a high-resolution image of objects made of a different material than their surroundings. The HE image is scaled along the material #1 attenuation curve. The program then “subtracts” the LE image from the scaled HE image to reveal the foreign object.
Combining the three techniques provides better results than are possible with other dual-energy systems emerging in the market today. The microfocus technique improves the dual-energy process and allows for more accurate measurement of radiographic density.
Testing demonstrates that the system accurately detects and identifies glass, bone, and plastic fragments as small as 1 mm in diameter in meat and in poultry. Conventional screening systems have a probability of detection for 3 to 4 mm sized bone fragments of 50-70 percent. Using either microfocus or dual-energy alone provides measurable improvement; when both of these methods are combined with a smart algorithm, the probability of detection for bone fragments of this size nears 100 percent.
With additional training of the algorithm, the same method could be applied to detect foreign objects in other food products or pharmaceuticals. It could also be used to improve threat detection for airport security, mail and package screening, and other applications.
In addition to improved detection capabilities, the technology offers several advantages for both food safety and security applications:
Non-invasive and can be used with already packaged products.
Retrofits into existing inspection and security systems, so conveyor belts or other mechanical components of the system can still be used.
No decrease in throughput.
Minimal retraining for inspection or security staff.