Detecting fecal contaminants in the visceral cavity of the broiler is difficult but extremely important for poultrysafety inspection. A hyperspectral imaging system was used for detecting internal cecal contaminants on broiler carcasshalves. Two 565- and 517-nm wavelength images were selected from 512 calibrated hypercube image data. Image processingalgorithms including band ratio, threshold, and median filtering were used to identify fecal contaminants from the internalcavity. The accuracy of detection algorithms to identify cecal contaminants varied with fecal threshold values and medianfilter as well. The imaging system identified cecal contaminants with 92.5% detection accuracy but also incorrectly identified123 carcass features that were not considered as contaminants (false positives) and missed 15 actual contaminants when afecal threshold value of 1.05 was employed. The higher accuracy (96.9%) and lower missed contaminants were obtained whena different fecal threshold value was used. However, in this case, false positives markedly increased.
No takes yet. Share an insight, caveat, or question.
Park et al. (2005) studied this question.