DETECTION OF SPLENOMEGALY IN POULTRY CARCASSES BY UV AND COLOR IMAGING

Splenomegaly (spleen enlargement) is one indication that processed poultry is not acceptable for human consumption because of diseases such as tumors or septicemia. This study explored the possibility of detecting splenomegaly with a computer imaging system that will assist human inspectors in food safety inspections. Images of internal viscera from 45-day-old commercial turkeys were taken with fluorescent and UV lighting systems. Image processing algorithms using the linear transformation, morphological filtering, and statistical classification were developed to distinguish the spleen from its background surroundings and then to detect abnormalities. Experimental results demonstrated that the imaging method could effectively distinguish the spleen from other organs and intestines. Based on a total of 57 turkey sample images, correct classification rates of 92% and 95% in detection of spleen abnormality were obtained using a self test set and an independent test set, respectively. The methods indicated the feasibility of using automated machine vision systems in the future to inspect internal organs and check the wholesomeness of poultry carcasses.