CLASSIFICATION OF ONLINE POULTRY CARCASSES WITH BACKPROPAGATION NEURAL NETWORKS

A transportable system equipped with an overhead shackle conveying lin e and a visible/near-infrared (Vis/NIR) spectrophotometer system was a ssembled and used at a poultry slaughter plant. The reflectance spectr a of each poultry carcass hung on the moving shackle was measured with a stationary fiber optic probe, which was set 2 to 5 cm away from the carcass, depending on the size. Reflectance spectra of wholesome and unwholesome poultry carcasses on the moving shackle, set at 60 or 90 b irds/min, were measured, either under room light or in a dark environm ent. The scanning time for each carcass was 0.32 s. Most of the unwhol esome poultry carcasses for this study were septicemic and air-sacculi tic. The average accuracy in classifying wholesome and unwholesome car casses was above 94%. All the misclassified carcasses were air-sacculi tic. With a shackle speed of 90 birds/min, the highest average accurac y was obtained when the reflectance was measured in the dark (97.5%). The results showed that the accuracy of classification could be improv ed with the maintenance of a consistent lighting environment. All resu lts indicated; the Vis/NIR spectrophotometer system would be a highly accurate, robust tool for on-line, real-time classification of wholeso me and unwholesome carcasses.