HYPERSPECTRAL IMAGING FOR FOOD PROCESSING AUTOMATION

Authors: Park, Bosoon; Lawrence, Kurt; Windham, William; Smith, Douglas; Feldner, Peggy

Submitted to: International Society for Optical Engineering
Publication Type: Proceedings
Publication Acceptance Date: 7/8/2002
Publication Date: 11/12/2002
Citation: Park, B., Lawrence, K.C., Windham, W.R., Smith, D.P., Feldner, P.W. 2002. Hyperspectral imaging for food processing automation. International Society for Optical Engineering. 4816:308-316.

Interpretive Summary: Food processing automation improves productivity with high quality control capability and benefits both producers and consumers. The poultry industry is one of the food industries that require automatic processing controls considering safety as well as quality. Current safety inspection is being done organoleptically, so automatic inspection systems need to be developed to meet federal mandates or company quality control guidelines. Recently, hyperspectral imaging (or imaging spectroscopy) has emerged as a powerful technique for utilization in food safety research areas. With the implementation of a Hazard Analysis Critical Control Point (HACCP) System, the poultry industry was mandated to establish science-based process controls. Development of image sensor technology that retains individual carcass inspection for on-line detection of fecal and ingesta contamination would provide a science-based process control and decrease water usage. Hyperspectral imaging can be an effective technique for identifying surface contaminants on poultry carcasses. This paper presents the development of a hyperspectral imaging system for the identification of surface fecal and ingesta contaminants on poultry carcasses.

Technical Abstract: A hyperspectral imaging system could be used effectively for detecting feces (from duodenum, ceca, and colon) and ingesta on the surface of poultry carcasses, and potential application for real-time, on-line processing of poultry for automatic safety inspection. The hyperspectral imaging system included a line scan camera with prism-grating-prism spectrograph, fiber optic line lighting, motorized lens control, and hyperspectral image processing software. Hyperspectral image processing algorithms, specifically band ratio of two wavelength (565/517) images and thresholding were effective on the identification of fecal and ingesta contamination of poultry carcasses. A multispectral imaging system including a common aperture camera with three optical trim filters (515.4 nm with 8.6-nm FWHM, 566.4 nm with 8.8-nm FWHM, and 631 nm with 10.2-nm FWHM), which were selected and validated by a hyperspectral imaging system, was developed for a real-time, on-line application. A total image processing time required to perform the current multispectral images captured by a common aperture camera was approximately 251 msec or 3.99 frames/sec. A preliminary test shows that the accuracy of real-time multispectral imaging system to detect feces and ingesta on corn/soybean fed poultry carcasses was 96%. However, many false positive spots that cause system errors were also detected.