@misc{13721,
  abstract     = {{In this study, we examined the possibility of detecting different types of materials that contaminate carcasses during industrial pig slaughter using video image analysis and artificial intelligence (AI). A camera system was installed between evisceration and postmortem meat inspection on an industrial pig slaughter line with a capacity of 12,000 pigs per day. The pigs were photographed using five 2D cameras, and the images were analysed for contamination using an AI-based algorithm. The setup, which was developed and installed by CLK GmbH, performed under industrial conditions. In order to train the system, specifications were created for the most frequently occurring types of contamination, namely, intestinal contents, bile, stomach contents, and tubular rail fat. Afterward, the system was trained using annotated images. In principle, the system was able to recognize all types of contamination on the camera images; even pinhead-sized contaminations were visible. The agreement between the algorithm and the results of an expert assessor who assessed the images online agreed in 60% of the judgements. The agreement between experts using onsite assessment and those using online assessment by images was 73%. Thus, the kappa measure of agreement was κ = 0.1215 (p = 0.0199). Significantly higher recognition rates appear to be possible by adjusting the algorithm and increasing the number of training images. Thus, the system is a useful tool to preselect contaminated carcasses and to support postmortem inspection.}},
  author       = {{Tholen, Janna and Kirse, Alina and Voß, Alexander and Schulze Althoff, Gereon and Strotkötter, Lea and Kreienbrock, Lothar and Upmann, Matthias}},
  booktitle    = {{Frontiers in Food Science and Technology}},
  issn         = {{2674-1121}},
  keywords     = {{artificial intelligence (AI), bile contamination, contamination detection, faecal contamination, slaughter hygiene, tubular rail fat}},
  publisher    = {{Frontiers Media SA}},
  title        = {{{Detection of carcass contamination using video image analysis during industrial pig slaughter}}},
  doi          = {{10.3389/frfst.2026.1698416}},
  volume       = {{6}},
  year         = {{2026}},
}

@misc{13723,
  abstract     = {{The introduction of error feedback systems can lead to a reduction in the occurrence of errors. Therefore, it was investigated whether the proportion of contaminated carcasses can be reduced by installing a feedback system (preInspector) indicating an accumulation of contamination on a pig slaughter line. The technical equipment for the workplace of a „preInspector“ was installed on the slaughter line between the evisceration and official meat inspection. The person working there operated various hand buttons („buzzers“) depending on the type of carcass defects that occurred. In this case, contamination with tubular rail fat and faecal contamination, on the belly and/or on the back, were registered. Other defects were related to the plucks (tongue, trachea, oesophagus, lungs, heart, diaphragm, liver), intestinal package, hair and claw removal. After inspecting the carcass halves and activating the buzzer, the signals were collected. The detection was automatically assigned to the corresponding pig.
The average slaughter rate was 1200 pigs per hour. As soon as the number of contaminations rose above a threshold of 50 contaminations per 60-minute time interval, a light signal was triggered at the corresponding workstations on the slaughter line. On average, 981 positive buzzer activities related to contaminations per day were detected, with large fluctuations of the frequency between 323 and 1,752. An influence on the frequency of contamination occurrence through the feedback to the corresponding workstations was not observed.}},
  author       = {{Tholen, Janna and Upmann, Matthias}},
  booktitle    = {{Journal of food safety and food quality : JFSFQ : Archiv für Lebensmittelhygiene}},
  issn         = {{0003-925X}},
  keywords     = {{Contamination, industrial pig slaughter, faecal contamination, hygiene feedback system}},
  number       = {{6}},
  pages        = {{156--160}},
  publisher    = {{Schaper}},
  title        = {{{Influence of a hygiene feedback system during pig slaughter on the frequency of carcass contamination}}},
  doi          = {{10.53194/0003-925X-75-156}},
  volume       = {{75}},
  year         = {{2024}},
}