Author
 |
YANG, CHUN-CHIEH - VISITING SCI., UNIV OF KY |
|
Chao, Kuanglin - Kevin Chao |
|
Chen, Yud |
|
Kim, Moon |
|
Chan, Diane |
|
Submitted to: Biosystems Engineering
Publication Type: Peer Reviewed Journal Publication Acceptance Date: 8/22/2006 Publication Date: 10/13/2006 Citation: Yang, C., Chao, K., Chen, Y.R., Kim, M.S., Chan, D.E. 2006. Development of fuzzy logic-based differentiation algorithm and fast line-scan imaging system for chicken inspection. Biosystems Engineering. 95(4):483-496. Interpretive Summary: To ensure food safety and prevent food safety hazards in the inspection process for poultry, egg, and meat products, the Food Safety and Inspection Service (FSIS) of the United States Department of Agriculture (USDA) has implemented the Hazard Analysis and Critical Control Point (HACCP) program throughout the country and has also been testing the HACCP-based Inspection Models Project (HIMP). This project includes a zero tolerance standard for chickens with infectious conditions such as septicemia and toxemia, which must be removed from the processing line. For poultry plants to meet government food safety regulations while maintaining their competitiveness to satisfy consumer demand, FSIS has required the development of new inspection technologies, such as automated computer imaging inspection systems. In this study, an online hyperspectral line-scan imaging system was developed at the Instrumentation and Sensing Laboratory for differentiation of wholesome and systemically diseased chickens. The key and reference wavelengths were selected based on the spectra of chicken images, and then used to generate image features for differentiation. An appropriate light source was selected to suit the optimal key wavelength selection. An image processing algorithm was developed to determine whether or not the region of interest for a carcass has entered or passed beyond the field of view, in order to trigger the beginning and end of the image differentiation process. A set of fuzzy logic membership functions was derived from sample pixels of chicken images. Two fuzzy logic-based algorithms were developed that nearly perfectly differentiated 116 systemically diseased chickens from 113 wholesome chickens. The line-scan hyperspectral system, built to extract useful image features for online chicken carcass inspection, can function as a high-speed multispectral imaging system using the same features and detection algorithm without the need for cross-system calibration. This information is useful to the Food Safety and Inspection Service (FSIS), and poultry processing plants. Technical Abstract: A hyperspectral line-scan imaging system for automated inspection of wholesome and diseased chickens was developed and demonstrated. The hyperspectral imaging system consisted of an electron-multiplying charge-coupled-device (EMCCD) camera and an imaging spectrograph. The system used a spectrograph to collect spectral measurements across a pixel-wide vertical linear field of view through which moving chicken carcasses passed. After a series of image calibration procedures, the hyperspectral line-scan images were collected for chickens on a laboratory simulated processing line. Light-emitting-diode (LED) line lights and quartz-tungsten-halogen (QTH) line lights were evaluated and LED lights were selected as the appropriate light source. From spectral analysis, four key wavebands for differentiating between wholesome and systemically diseased chickens were selected: 413 nm, 472 nm, 515 nm, and 546 nm; a reference waveband at 626 nm was also selected. The ratio of relative reflectance between each key wavelength and the reference wavelength was calculated as an image feature. A fuzzy logic-based algorithm utilizing the key wavebands was developed to identify individual pixels on the chicken surface exhibiting symptoms of systemic disease. Two differentiation methods were developed that nearly perfectly differentiated 116 systemically diseased chickens from 113 wholesome chickens. |
