Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: March 23, 2011
Publication Date: May 12, 2011
Citation: Park, B., Yoon, S.C., Windham, W.R., Lawrence, K.C., Heitschmidt, G.W., Kim, M.S., Chao, K. 2011. Line-scan hyperspectral imaging for real-time on-line poultry fecal detection. Sensing and Instrumentation for Food Quality and Safety. 5:25-32. Interpretive Summary: The ARS multispectral imaging system with three-band common aperture camera was able to inspect fecal contaminants in real-time during poultry processing. Recent study has demonstrated several image processing methods including binning, cuticle removal filter, median filter, and morphological analysis could remove false positive errors in real-time mode. The ARS research groups and their industry partner are now merging the fecal detection and systemically disease detection systems onto a common platform using a line-scan hyperspectral imaging system. This system will aid in commercialization by creating one hyperspectral imaging system with user-defined wavelengths that can be installed at different locations of the processing line to solve significant food safety problems. The objective of this paper is to demonstrate the feasibility of a line-scan hyperspectral imaging system in terms of processing speed and detection accuracy for real-time, on-line fecal detection at current processing speed of commercial poultry plant. The newly developed line-scan hyperspectral imaging system could improve Food Safety Inspection Service (FSIS)’s science-based poultry safety inspection program significantly.
Technical Abstract: The preliminary results demonstrated that high speed line-scan hyperspectral imaging system has a potential for real-time online fecal detection during poultry processing. To improve detection accuracy, fully calibrated images both spatially and spectrally were acquired for further processing. In addition, triggering capability, either external or internal mode, needs to be implemented for real-time image processing. Currently, internal triggering method based on the shape of a carcass is being developed. In doing this, entire processing speed from line-scan image acquisition to analysis for identifying fecal contaminants was 150 birds per minutes, which met the industry requirement. For quality image acquisition, a lighting system both tungsten halogen and light-emitting device was tested. From the preliminary studies, we found high speed line-scan hyperspectral imaging system can be used for fecal contaminant detection as a common platform with wholesomeness inspection that has been tested by ARS Beltsville researchers. However, more research needs to be done to fully validate performance of the system to detect fecal contaminants in terms of ground truths for acceptable detection accuracy (97% and higher) with minimum false positive errors (3% and lower). For this task, we have tested several markers as a ground truths based on confirmation by human inspector and are developing automatic link with ground truths using a charge-coupled device color camera.