Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: March 20, 2008
Publication Date: April 15, 2008
Citation: Yoon, S.C., Lawrence, K.C., Smith, D.P., Park, B., Windham, W.R. 2008. Embedded bone fragment detection in poultry using transmittance image enhancement and hyperspectral reflectance imaging. Sensing and Instrumentation for Food Quality and Safety, 10.1007/s11694-008-9044-1 (online version). Interpretive Summary: Bone fragments embedded in poultry products pose a physical hazard to consumers, especially, to children, may cause injury, and thus, need to be detected. The predominant technology for bone detection is X-ray imaging which is based on the projection of ionizing radiation through a meat sample onto an image detector. Optical imaging, which is based on non-ionizing light at the visible and near-infrared spectral range, has not been fully explored to measure the internal and functional information of uncooked or cooked poultry products. The overall objective of this research was to study how reflectance spectra can be exploited for detection of bone fragments in compressed chicken fillets. The study found that the use of both hyperspectral transmittance and reflectance images were necessary to make the bone detection task via optical imaging feasible. This finding may contribute to the development of an online and real-time bone detection system in industry.
Technical Abstract: This paper is concerned with the detection of bone fragments embedded in compressed de-boned skinless chicken breast fillets by enhancing single-band transmittance images generated by back-lighting and exploiting spectral information from hyperspectral reflectance images. Optical imaging of chicken fillets is often dominated by multiple scattering properties of the fillets. Thus, resulting images from multiple scattering are diffused, scattered and low contrast. In this study, a fusion of hyperspectral transmittance and reflectance imaging, which is a non-ionized and non-destructive imaging modality, was investigated as an alternative method to the conventional transmittance X-ray imaging technique which is an ionizing imaging modality. An image formation model, called an illumination-transmittance model, was applied for correcting non-uniform illumination effects so that embedded bones are more easily detected by a simple segmentation method using a single threshold value. Predicted bones from the segmentation were classified by the nearest neighbor classifier that was trained by the spectral library of mean reflectance of some chicken tissues like fat, meat and embedded bones. Experimental results with chicken breast fillets and bone fragments are provided.