Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.
Dynamic Thresholding Method for Improving Contaminant Detection Accuracy with Hyperspectral Images
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.orgCitation: Paper number 053071, 2005 ASAE Annual Meeting . (doi: 10.13031/2013.19077) @2005
Authors: Bosoon Park, Seung Chul Yoon, Kurt C. Lawrence, William R. Windham
Keywords: Hyperspectral, Multispectral Imaging, Machine Vision, Image Processing, Food Safety, Poultry Inspection, Fecal Contamination, Fisher’s Linear Discriminant Analysis
Detection of fecal contamination in the visceral cavity of broiler carcasses is important for food safety to protect consumers from food pathogens. The simple ratio of reflectance values of 565-nm image to 517-nm image was effective for identifying cecal contaminants in the visceral cavity. Since the accuracy of detection algorithms for identifying cecal contaminants varied with fecal threshold values, determination of optimum threshold was crucial for detecting fecal contaminants during poultry processing. The dynamic threshold method using Fishers linear discriminant analysis (FLDA), along with simple multispectral image ratio with Gaussian window averaging (10-nm FWHM bandwidth), performed better (98.9% detecting accuracy with 1.06% omission error) than static threshold method to identify cecal contaminants. The mean and standard deviation of dynamic threshold were 1.0247 and 0.0274, respectively. Since the accuracy of fecal threshold was a trade off and sacrificed with missed contaminants and false positives, the dynamic thresholding method using FLDA was useful for cecal contaminant detection. Also, FLDA can be implemented to determine and update fecal threshold values for on-line inspection at poultry processing plants.(Download PDF) (Export to EndNotes)