IMAGING SYSTEM FOR FECAL AND INGESTA DETECTION ON POULTRY CARCASSES

Authors: Lawrence, Kurt; PARK, BOSOON - UNIVERSITY OF GEORGIA; Windham, William; Buhr, Richard - Jeff; Smith, Douglas

Submitted to: Poultry Science Association Meeting Abstract
Publication Type: Abstract Only
Publication Acceptance Date: 6/14/2001
Publication Date: 6/14/2001
Citation: Lawrence, K.C., Park, B., Windham, W.R., Buhr, R.J., Smith, D.P. 2001. Imaging system for fecal and ingesta detection on poultry carcasses. [abstract] Poultry Science Association Meeting.

Interpretive Summary: When poultry are processed, potential sources of harmful bacteria are feces and ingesta (f&i), which is undigested food. These bacteria commonly reside in the feces of the bird and the carcass can become contaminated when the f&i come in contact with the surface of a carcass during processing. Processing plants use large quantities of water to remove the f&i and insure a clean safe food product. If a system were available to detect f&i on a carcass, then only contaminated birds would need washing, which could result in significant water savings and safer food. An imaging system was developed to quickly identify f&i on the surface of poultry carcasses. The system uses an imaging camera to take two-dimensional digital picture at many discrete wavelengths ranging from 430 nm to 900 nm. These images can then be combined to distinguish between contaminates and everything else. Sixteen chickens were slaughtered, picked, hard scalded, and eviscerated. Images of the birds before and after contamination with feces from the duodenum, ceca, and colon, and ingesta were taken. The ratio of a 565-nm image divided by a 517-nm image proved to be one of the best and simplest methods for detecting f&i. Further image processing known as thresholding and histogram stretching resulted in the detection of 97 to 100 percent of contaminates. The research demonstrates the feasibility of a real-time system for f&i detection.

Technical Abstract: The imaging system is capable of collecting spectral reflectance information from 430 to 900 nm with 1-nm resolution for every pixel of a carcass image. The resulting three-dimensional image cube is typically reduced to 320x340 pixels of spatial information with 512 pixels of spectral information for each spatial pixel. This paper reports the results of this system for the detection of ingesta from the crop or gizzard and feces from the duodenum, ceca, and colon on the surface of a poultry carcass. Sixteen six-week old male birds on a corn/soybean diet were meal-fed, subjected to an 8-hour feed withdrawal, cooped, slaughtered, hard scalded (57.5 C for 2 min.), picked, eviscerated, and feces and ingesta was collected. Uncontaminated carcasses were then immediately imaged. Next, feces and ingesta were applied to varying locations on the breast, wings, and legs of the carcass, typically three spots per contaminant, for a total of 190 contaminant spots, and second images were taken. Results are presented for several data analysis techniques including principal component analysis, which includes all measured wavelengths, and the wavelength ratio of the 565-nm image divided by the 517-nm image. The wavelength-ratio images were further processed with background masking, thresholding, and histogram stretching. The threshold and histogram stretching values were fixed for all birds. Linear and square root histogram stretches were performed. Results indicated that 97.3 and 100 percent of the contaminates were detected with the linear and square-root histogram stretches, respectively. The research shows the feasibility of a real-time system for fecal and ingesta detection from two wavelength images at typical