Submitted to: Transactions of the ASABE
Publication Type: Peer reviewed journal
Publication Acceptance Date: 6/2/2009
Publication Date: 6/2/2009
Publication URL: hdl.handle.net/10113/34396
Citation: Park, B., Yoon, S.C., Kise, M., Lawrence, K.C., Windham, W.R. 2009. Adaptive image processing methods for improving contaminant detection accuracy on poultry carcasses. Transactions of the ASABE. 52(3):999-1008. Interpretive Summary: Interpretive Summary Previously, ARS scientists at Russell Research Center have developed and demonstrated a real-time multispectral imaging system for fecal and ingesta contaminant detection during poultry processing. The imaging system, with a three-band common aperture camera, was able to detect contaminants with a high detection accuracy. However, due to time constraints for real-time, on-line applications and limited applicable image processing algorithms, moderate false positives were detected. In order to implement this imaging system in the commercial poultry processing industry, most false positives must be eliminated. To improve system performance, several image processing methods were examined. In this paper, noise analyses, optimizing system hardware including trigger, gain, and software binning to maximize detection accuracy and minimize false positives were reported. In addition, the optimum parameter values and the effects of binning and other filtering methods relevant to false positives were demonstrated. The outcomes from this study could be used for analyzing overall performance of real-time multispectral imaging system for contaminant detection of agricultural commodities.
Technical Abstract: Technical Abstract A real-time multispectral imaging system has demonstrated a science-based tool for fecal and ingesta contaminant detection during poultry processing. In order to implement this imaging system at commercial poultry processing industry, the false positives must be removed. For doing this, we tested and implemented additional image processing algorithms including binning, cuticle removal filter, median filter, and morphological analysis in real-time mode to maximize detection accuracy and minimize false positives (FPs). The median filtering and binning process were able to reduce FPs up to 98.7% and 95.2%, respectively by eliminating most salt and pepper noise from the raw images. The detection accuracy varied with parameter values of image processing algorithms including binning, threshold, median filter, and morphological filter. Overall contaminant detection accuracy on moving birds varied from 84.3% to 97.8%. In this case, the FPs errors were 1.9% and 41.8%, respectively. Although neither the overall detection accuracy nor FPs errors were affected by camera gains, the results of detection accuracy were slightly changed from 87.4% to 95.1%. In this case, the FPs errors were 1.8% and 15.9%, respectively. Thus, the ARS multispectral imaging system was able to detect contaminants with 91.6% accuracy and 3.3% FPs errors by selecting optimum image processing methods at the processing speed of 140 birds per minute.