|Heitschmidt, Gerald - Jerry|
Submitted to: Journal of Electronic Imaging
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/2/2015
Publication Date: 8/10/2015
Citation: Yoon, S.C., Shin, T., Lawrence, K.C., Heitschmidt, G.W., Park, B., Gamble, G.R. 2015. Hyperspectral imaging using RGB color for foodborne pathogen detection. Journal of Electronic Imaging. 24(4):043008.
Interpretive Summary: Hyperspectral imaging, using hundreds of spectral channels, is a powerful tool to study properties of food products and detect defects and harmful materials by analyzing spatial and spectral information simultaneously. However, compared to digital cameras for conventional color imaging, hyperspectral imaging instruments are very expensive and difficult to operate. A study was conducted to investigate statistical regression methods for recovering hyperspectral images only from RGB color images so that any existing hyperspectral image processing models can be used with a digital color camera. This research may have many practical applications such as a digital color imaging system using a hyperspectral image classification algorithm to differentiate the big six non-O157 Shiga-toxin producing Escherichia coli (STEC) serogroups. The R-squared value, a statistical measure for goodness-of-fit of a regression model, was 0.98 (1 means a perfect fit.) in the visible spectral region. The overall classification accuracy of the hyperspectral image classification model in identifying the types of the six non-O157 STEC serogroups was up to 92% (99% with the original hyperspectral images). Thus, the results of the study suggested the potential of color imaging in reconstructing hyperspectral images and applying them for hyperspectral imaging applications such as pathogen detection and classification.
Technical Abstract: This paper reports the latest development of a color vision technique for detecting colonies of foodborne pathogens grown on agar plates with a hyperspectral image classification model that was developed using full hyperspectral data. The hyperspectral classification model depended on reflectance spectra measured in the visible and near-infrared spectral range from 400 and 1,000 nm (473 narrow spectral bands). Multivariate regression methods were used to estimate and predict hyperspectral data from RGB color values. The six representative non-O157 Shiga-toxin producing Escherichia coli (STEC) serogroups (O26, O45, O103, O111, O121, and O145) were grown on Rainbow agar plates. A line-scan pushbroom hyperspectral image sensor was used to scan 36 agar plates grown with pure STEC colonies at each plate. The 36 hyperspectral images of the agar plates were divided in half to create training and test sets. The mean R-squared value for hyperspectral image estimation was about 0.98 in the spectral range between 400 and 700 nm for linear, quadratic and cubic polynomial regression models and the detection accuracy of the hyperspectral image classification model with the principal component analysis and k-nearest neighbors for the test set was up to 92% (99% with the original hyperspectral images). Thus, the results of the study suggested that color-based detection may be viable as a multispectral imaging solution without much loss of prediction accuracy compared to hyperspectral imaging.