Quality control is crucial in the food industry. Monitoring the nutritional properties of food products contributes to brand reputation and profit.
Consumers monitor fat content carefully when buying meat, and producers have to document it precisely. Monitoring the fat content also has a significant cost-benefit effect. New automation technologies are therefore required to improve food production and processing.
A Finnish food industry company Atria provided five minced meat samples for this study. We obtained five additional samples by mixing the five original ones to include ten samples in the analysis. To know the precise fat content of the samples, Specim ordered measurements from a 3rd party laboratory, Seilab. According to the Gerber method, they are certified in fat analysis, using a butyrometer (Seilab in Seinäjoki, Finland; method NMKL 181, 2005; see Table 1 below).
| Measured value by Seilab | Measured value by FX17 | |
|---|---|---|
| Sample 1 | 0.6% | 0.9% |
| Sample 2 | 16% | 15.2% |
| Sample 3 * | 10% | 10.4% |
| Sample 4 * | 18% | 20.8% |
| Sample 5 | 75% | 75.1% |
| Sample 6 (mix) | 3% | 2.7% |
| Sample 7 (mix) | 6% | 5.5.% |
| Sample 8 (mix) | 11% | 12.8% |
| Sample 9 (mix) | 19% | 19.0% |
| Sample 10 (mix) | 24% | 23.5% |
Table 1: fat content on each sample included in this study. Samples 3 and 4 were used for validation purposes.
We measured the samples with Specim FX17 hyperspectral camera (Fig.1). Hyperspectral imaging is a non-destructive method that combines spectroscopy and imaging. The Specim FX17 collects NIR spectra for each pixel of the acquired image (900 – 1700 nm). Those can be converted into fat content employing relevant processing algorithms. Here a regression model was built and calibrated on eight samples and applied on the two remaining ones (indicated with * in Table 1).
Figure 1: Specim FX17 on the 40×20 LabScanner (left) and a meat sample (right).
The regression model results are presented in Table 1 and Fig.2. It clearly shows that the Specim FX17 is a suitable tool to measure the fat content in minced meat precisely.
Figure 2: Regression plot of the quantitative model for fat content prediction. Red dots relate to calibration samples, whereas green ones relate to validation samples.
In addition to measuring the fat content, hyperspectral imaging is suitable for measuring its areal distribution in samples (Fig.3).
Figure 3: Example of fat distribution on a meat sample (here Sample 4).
Specim FX17 – a perfect tool for meat quality control
Specim FX17 hyperspectral camera integrated into machine vision systems provides the meat industry with accurate information on fat content. But that’s not all. It is also suitable to detect other meat properties such as moisture and freshness. Additionally, the Specim FX17 system excels at sorting out contaminants such as wood pieces and plastics, ensuring the quality control of the meat production processes.
One significant advantage of hyperspectral imaging in food quality control is its contactless and non-destructive inspection method. In food production, maintaining hygiene is of utmost importance to ensure the safety and quality of products. Hyperspectral imaging allows for the inspection of food products without any physical contact, making it a hygienic solution.
Hyperspectral imaging offers cost reduction and quick adaptation to new regulations by providing real-time information about the manufacturing process for decision-making and real-time quality control of meat processing.
