Abscess detection on bovine livers with a commercial smart imaging system

Meat processors are responsible for ensuring that animal carcasses are fit for human consumption [1]. Trained meat <br/>inspectors play a crucial role in quality control, identifying and condemning unhealthy tissue, with this process occurring <br/>at line speed. Whilst optimized for reporting of disease conditions for quality assurance processes, the time and tools <br/>currently available to inspectors, or other on-floor staff, restricts the depth of information able to be recorded due to rapid <br/>chain speeds. Impacts to the supply chain due to downgraded product can be significant. For example, abscessed <br/>condemned at around 3% of beef cattle slaughtered [2]. Line speed automated disease assessment therefore offers a <br/>promising layer of objective data for defect capture and producer feedback.Currently, Smart Imaging Systems (SIS) are <br/>used in processing plants for foreign object detection, quality assurance and quality control of meat products. One imaging <br/>modality, hyperspectral cameras, capture light reflected from the meat product, across multiple wavelengths in near <br/>infrared to visible ranges with this data being utilized via Machine learning models to identify multiple visual and <br/>biochemical tissue characteristics [3]. Current in-plant hyperspectral imaging systems include the composition analysis of <br/>meat cuts and control of foreign materials [4]. Automated assessment for abscesses and other offal health conditions, <br/>using imaging systems such as hyperspectral analysis, could therefore expand offal inspection with objective data. To <br/>investigate this, the development of hyperspectral disease detection models using commercially available smart imaging <br/>system was investigated.