Submitted to: ASAE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: August 1, 2002
Publication Date: August 1, 2002
Interpretive Summary: U.S. consumption of poultry and poultry products has steadily increased. Currently, individual poultry carcasses are subjected to visual inspection by Food Safety Inspection Service (FSIS) inspectors. There are needs for improvement of the existing inspection methods. Development of rapid and reliable inspection systems to ensure safe production of poultry during post-harvest processing has become an important issue. The Instrumentation and Sensing Laboratory has been involved in development of noninvasive optical sensing methods, as a rapid means to inspect chicken carcasses in the processing plants. This paper reports the use of hyperspectral fluorescence imaging techniques for detection of skin tumors on the chicken carcass. Algorithms using several spectral regions were devised to automatically detect chicken carcasses with skin tumors. This information is useful to the FSIS and poultry processing plants.
Technical Abstract: This paper describes a method for detecting skin tumors on chicken carcasses. It utilizes both spectral and spatial information in hyperspectral fluorescence images to increase detection rate in a synergistic manner. Since real-time processing is a key issue in implementation, the proposed method uses a limited number of features to reduce the computational complexity. Nevertheless, it shows favorable results and, in addition, reveals meaningful spectral bands for detecting tumors. The method and finding can be employed in implementing customized chicken tumor-detecting systems.