Skip to main content
ARS Home » Research » Publications at this Location » Publication #186274
Title: DEVELOPMENT OF FAST LINE SCANNING IMAGING ALGORITHM FOR DISEASED CHICKEN DETECTION

Author
item YANG, CHUN-CHIEH - VISITING SY-ISL, ANRI
item Chao, Kuanglin - Kevin Chao
item Chen, Yud
item Kim, Moon

Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 10/23/2005
Publication Date: 11/20/2005
Citation: Yang, C.C., Chao, K., Chen, Y.R., Kim, M.S. 2005. Development of fast line scanning imaging algorithm for diseased chicken detection. SPIE Conference, 10/23-26, 2005, Boston, Massachusetts. 5996OC-1-5996OC-12.

Interpretive Summary: The U.S. poultry industry is facing a need to improve existing inspection procedures while maintaining, and even increasing, production output to meet growing consumer demand for safe and wholesome poultry and poultry products that satisfy higher food safety and quality standards. For this problem, much attention has become focused on the development of reliable automated high-speed inspection systems for use on poultry processing lines. In this study, a hyperspectral line-scanning imaging system is being developed at the Instrumentation and Sensing Laboratory for inspection of wholesome and systemically diseased chickens. The chicken carcasses were hung on shackles moving at a speed of 70 carcasses per minute. Four wavelengths, 413 nm, 472 nm, 515 nm, and 546 nm, were selected for differentiating between wholesome and systemically diseased chickens. A fuzzy logic-based algorithm was developed to classify between images of wholesome and systemically diseased chickens. For each scanned line, four image features from single pixels were used as inputs to run the fuzzy logic algorithm to obtain a discrete decision output, indicating the existence of systemic disease. The average decision output over all pixels from all line scans in the region of interest on the chicken surface was analyzed. The average decision output for each line scan in the region of interest was also analyzed, and the lines for which the average output was higher than 0.50 were counted. Both methods obtained 100% accuracy for 137 sample 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. 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, and a reference waveband, 622 nm. 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 and each was able to successfully differentiate 100% of the 137-bird sample set (72 systemically diseased chickens and 65 wholesome chickens).