A chicken carcass inspection system using visible/near-infrared reflectance: In-plant trials

On-line trials of an industrial prototype visible/near-infrared spectrophot ometer system developed by the Instrumentation and Sensing Laboratory for i nspecting poultry for diseased and defective carcasses were conducted durin g an 8-day period in a slaughter plant in New Holland, Pennsylvania. Spectr a (470-960 nm) of 1174 normal and 576 abnormal (diseased and/or defective) chicken carcasses were measured. The instrument measured the spectra of vet erinarian-selected carcasses as they passed on a processing line at a speed of 70 birds per minute. Classification models using principal component an alysis as a data pretreatment for input into neural networks were able to c lassify the carcasses from the spectral data with a success rate of 95%. Da ta from 3 days can predict the subsequent two days' chickens with high accu racy. This accuracy was consistent with the results obtained previously in off-line studies. Thus, the method shows promise for separation of diseased and defective carcasses from wholesome carcasses in a partially automated inspection system. Details of the models using various training regimens ar e discussed.