Real-time image processing for rapid contaminant detection on broiler carcasses

摘要

Recently, the imaging research group at Russell Research Center, ARS in Athens, Georgia has developed a real-time multispectral imaging system for fecal and ingesta contaminant detection on broiler carcasses. The prototype system includes a common aperture camera with three optical trim filters (515.4, 566.4 and 631-nm wavelength), which were selected by visible/NIR spectroscopy and validated by a hyperspectral imaging system. The preliminary results showed that the multispectral imaging technique can be used effectively for detecting feces (from duodenum, ceca, and colon) and ingesta on the surface of poultry carcasses with a processing speed of 140 birds per minute. The accuracy for the detection of fecal and ingesta contaminates was 96%. However, the system contains many false positives including scabs, feathers, and boundaries. This paper demonstrates calibration of common aperture multispectral imaging hardware and real-time multispectral image processing software. The software design, especially the Unified Modeling Language (UML) design approach was used to develop real-time image processing software for on-line application. The UML models including class, object, activity, sequence, and collaboration diagram were discussed. Both hardware and software for a real-time fecal and ingesta contaminant detection were tested at the pilot-scale poultry processing line.