X-ray detection with the least false positives

Given the current great emphasis on food safety, SensorX’ strive for ultimate, bone-free product quality is perfectly placed. The latest improvement implies the virtual elimination of false positives – normally a disruptive influence in bone detection.

Marel’s x-ray bone detection system is a success story for many years now. In the course of time, the role of integrated software has become increasingly important to drive the machine to maximum accuracy and reliability.

Less rework

For poultry processors, the ideal x-ray detection machine should detect bone remnants and other contaminants with the very highest degree of accuracy. What processors don’t want is a machine which gives too many false positives. A false positive is material which is actually bone-free but which the machine handles and records as though it contained residual bone. In this situation, bone performance detection statistics, whilst looking impressive, will not reflect the true situation and could be misleading for departmental management.

Marel’s latest Sensor X software not only reduces the incidence of false positives to an absolute industry minimum but also detects those difficult to see bone fragments more accurately. This means less rework and fewer inspectors, enhancing still further the machine’s already excellent performance.

Perfect balance

The new software creates a perfect balance between an increased detection rate and a reduced false positive rate. But this equilibrium is a thin line. It’s no use to try and detect the very smallest, almost harmless bone particles if the percentage of bigger bone detection isn’t high enough. The first aim of Marel was therefore to achieve the highest percentage of “big” bone particle detection in the market. Elaborate testing of the new SensorX software shows that this objective has become a reality.

When performing bone detection tests, false positives should always be included. If detection results are excellent, but the false positive rate is 30%, the machine is useless, because there’s way too much rework to be done.

Photo: Marel Poultry

Saving labour

A dual lane SensorX, working on full capacity, handles 240 pieces of meat per minute. Let’s assume the bone detection rate is 5% and the false positive rate is 6%. That would mean that 26 pieces of meat are rejected per minute. As an average operator can inspect 10 pieces per minute for bones, three of them would be needed to keep the production running.

When you succeed in bringing down the false positive rate to 3%, this would result in 19 pieces per minute, needing only 2 inspectors. In this way the labour saving effects of the new SensorX software are immediately visible.

Food safety

Food safety and consistency is vital in the poultry processing industry. The SensorX bone detection system is an efficient and cost effective way to detect and remove bones and bone fragments from poultry products.

Marel’s Innova software is capable of collecting reliable data to achieve full traceability throughout the production process. It provides real-time monitoring of key performance indicators such as yield, throughput, quality, capacity and labour efficiency. These valuable insights ensure that the production conforms to quality and food safety standards.

Market leader

By now hundreds of SensorX systems have been delivered to high-end poultry processors in 40 countries around the world; Marel has become the market leader in bone detection for poultry. Continuous improvements will keep strengthening this position.