Kurt C. Lawrence

A hyperspectral imaging system for identification of faecal and ingesta contamination on poultry carcasses

A method and system for detecting faecal and ingesta contaminants on poultry carcasses were demonstrated. A visible/near infrared monochromator, which measured reflectance and principal component analysis were first used to identify key wavelengths from faecal and uncontaminated skin samples. Measurements at 434, 517, 565 and 628 nm were identified and used for evaluation with a hyperspectral imaging system. The hyperspectral imaging system, which was a line-scan (pushbroom) imaging system, consisted of a hyperspectral camera, fibre-optic line lights, a computer and frame grabber. The hyperspectral imaging camera consisted of a high-resolution charge coupled device (CCD) camera, a prism-grating-prism spectrograph, focusing lens, associated optical hardware and a motorised controller. The imaging system operated from about 400 to 900 nm. The hyperspectral imaging system was calibrated for wavelength, distance and percent reflectance and analysis of calibrated images at the key wavelengths indicated that single-wavelength images were inadequate for detecting contaminants. However, a ratio of images at two of the key wavelengths was able to identify faecal and ingesta contaminants. Specifically, the ratio of the 565-nm image divided by the 517-nm image produced good results. The ratio image was then further processed by masking the background and either enhancing the image contrast with a non-linear histogram stretch, or applying a faecal threshold. The results indicated that, for the limited sample population, more than 96% of the contaminants were detected. Thus, the hyperspectral imaging system was able to detect contaminants and showed feasibility, but was too slow for real-time on-line processing. Therefore, a multivariate system operating at 565 and 517 nm, which should be capable of operating at real-time on-line processing speed, should be used. Further research with such a system needs to be conducted.

Simple Algorithms for the Classification of Visible/Near-Infrared and Hyperspectral Imaging Spectra of Chicken Skins, Feces, and Fecal Contaminated Skins

is shown in Fig. 5. It can be seen from the curve that Abs(r) increases with an increase in the smoothing width. When the width is less than 20 cm21, Abs(r) increases markedly, from 0.27 to 0.86 as shown in the x8e gure. It is interesting to note that 20 cm21 happens to be the average half width of the two absorption peaks. When the smoothing width is greater than 20 cm21, Abs(r) increases only slightly to a value of 0.93 with a smoothing width of 50 cm21.

Surface enhanced Raman scattering (SERS) with biopolymer encapsulated silver nanosubstrates for rapid detection of foodborne pathogens

A biopolymer encapsulated with silver nanoparticles was prepared using silver nitrate, polyvinyl alcohol (PVA) solution, and trisodium citrate. It was deposited on a mica sheet to use as SERS substrate. Fresh cultures of Salmonella Typhimurium, Escherichia coli, Staphylococcus aureus and Listeria innocua were washed from chicken rinse and suspended in 10 ml of sterile deionized water. Approximately 5 μl of the bacterial suspensions was placed on the substrate individually and exposed to 785 nm HeNe laser excitation. SERS spectral data were recorded over the Raman shift between 400 and 1800 cm(-1) from 15 different spots on the substrate for each sample; and three replicates were done on each bacteria type. Principal component analysis (PCA) model was developed to classify foodborne bacteria types. PC1 identified 96% of the variation among the given bacteria specimen, and PC2 identified 3%, resulted in a total of 99% classification accuracy. Soft Independent Modeling of Class Analogies (SIMCA) of validation set gave an overall correct classification of 97%. Comparison of the SERS spectra of different types of gram-negative and gram-positive bacteria indicated that all of them have similar cell walls and cell membrane structures. Conversely, major differences were noted around the nucleic acid and amino acid structure information between 1200 cm(-1) and 1700 cm(-1) and at the finger print region between 400 cm(-1) and 700 cm(-1). Silver biopolymer nanoparticle substrate could be a promising SERS tool for pathogen detection. Also this study indicates that SERS technology could be used for reliable and rapid detection and classification of food borne pathogens.

Discriminant analysis of dual-wavelength spectral images for classifying poultry carcasses

An analysis of texture features, based on co-occurrence matrices (COMs), was conducted to determine the performance of dual-wavelength imaging for discriminating unwholesome poultry carcasses from wholesome carcasses. The variance, sum average, sum variance, and sum entropy of COMs were the most significant texture features (P 0.005) for identifying unwholesome poultry carcasses. However, the feature values of angular second moment, variance, sum average, sum variance, and sum entropy did not vary with the COM parameters, distance and direction. The characteristics of variance and sum variance texture features varied with the wavelength of spectral images and with condemnation of poultry carcasses, as well. The sum variance of wholesome carcasses was higher (P 0.005) than unwholesome carcasses for spectral images at 542 nm. For 542 and 700 nm images, linear discriminant models were able to identify unwholesome carcasses with a classification accuracy of 91.4%. However, a single linear discriminant model was not acceptable for identifying three different types of carcasses (wholesome, septicemic and cadaver), because of extreme inaccuracy for septicemic carcasses. In this case, the classifier that demonstrated the highest accuracy was 89.6% accurate at 542 nm. Thus, a dual-wavelength imaging system with optical filters of 542 and 700 nm wavelengths appears promising for detecting unwholesome poultry carcasses. Published by Elsevier Science B.V.

Partial least squares regression of hyperspectral images for contaminant detection on poultry carcasses

The US Department of Agriculture has developed multispectral and hyperspectral imaging systems to detect faecal contaminants. Until recently, the hyperspectral imaging system has been used as a research tool to detect a few optimum wavelengths for use in a multispectral imaging system. However, with the development of complementary metal oxide semiconductor cameras, discrete wavelengths or subsets of the full-detector range can be used to greatly increase the speed of hyperspectral imaging systems. This paper reports on the use of a broad-spectrum multivariate statistical analysis technique for detecting contaminants with hyperspectral imaging. Partial least squares regression was used for model development. Calibration models from spatially averaged region of interest data were developed with and without smoothing, with and without scatter correction and with and without first derivative (difference) pre-processing. Results indicate that using the full spectral range with scatter correction was needed for good model development. Furthermore, validation of the various calibration models indicated that pre-processing with scatter correction, nine-point boxcar smoothing and first derivative pre-processing resulted in the best validation with about 95% of the over 400 contaminants detected with only 26 false positives (errors of commission). About one-third of the false positives were from bruised wingtips which would not be visible during in-plant commercial processing.

Hyperspectral Imaging for Differentiating Colonies of Non-0157 Shiga-Toxin Producing Escherichia Coli (STEC) Serogroups on Spread Plates of Pure Cultures

Direct plating on solid agar media has been widely used in microbiology laboratories for presumptive-positive pathogen detection, although it is often subjective and labour-intensive. Rainbow agar is a selective and differential chromogenic medium used to isolate pathogenic Escherichia coli (E. coli) strains. However, it is challenging to differentiate colonies of the six representative pathogenic non-0157 Shiga-toxin producing E. coli (STEC) serogroups (026, 045, 0103, 0111, 0121 and 0145) on Rainbow agar due to the phenotypic differences and the presence of background microflora. Therefore, there is a need for a method or technology to objectively, rapidly and accurately perform high-throughput screening of non-0157 STEC colonies on agar plates. In this paper, we report the development of a visible-near infrared hyperspectral imaging technique and prediction model for differentiating colony types of the six non-0157 STEC serogroups in spread plates of pure cultures inoculated on Rainbow agar. The prediction model was based on supervised linear classification of factor scores obtained by principal component analysis (PCA). Both PCA-MD (Mahalanobis distance) and PCA-kNN (k-nearest neighbour) classifiers were used for model development. From the 24 hyperspectral images measured from two replicates, 51,173 spectral samples were collected from 1421 colonies. Chemometric preprocessing methods and other operating parameters, such as scatter correction, first derivative, moving average, sample size and number of principal components (PCs), were compared with a classification and regression tree (CART) method, configured as a classification tree and followed by brute-force searching from candidates selected by the CART. The number of PCs, scatter correction and moving average were selected as the most important elements to consider before selecting a set of candidate models. Cross-validation (CV), such as hold out and k-fold CV, was used to validate the prediction performance of candidate models. Serogroups 0111 and 0121 consistently showed over 99% classification accuracy regardless of the classification algorithms. However, the classification accuracies of serogroups 026, 045, 0103 and 0145 showed varying results from 84% up to 100%, depending on which preprocessing treatment and prediction model were adopted. The best overall mean classification accuracy of 95.06% was achieved with PCA-kNN (k=3), six PCs, five-pixel sample size defined around each colony centre, standard normal variate and detrending, first derivative with 11-point gaps and moving average with 11-point gaps. Future studies will focus on automating colony segmentation, further improving detection accuracy of the developed models, expanding the spectral library to include background microflora from ground beef and developing prediction models to detect the target bacteria in the presence of background microflora.

Detection and differentiation of Salmonella serotypes using surface enhanced Raman scattering (SERS) technique

This research was conducted to prove that developed silver biopolymer nanoparticle substrate for surface enhanced Raman scattering (SERS) technique could detect and differentiate three different serotypes of Salmonella. Nanoparticle was prepared by adding 100xa0mg of silver nitrate to a 2xa0% polyvinyl alcohol solution, then adding 1xa0% trisodium citrate to reduce silver nitrate and produce silver encapsulated biopolymer nanoparticles. Then, nanoparticle was deposited on a stainless steel plate and used as SERS substrate. Fresh cultures of Salmonellatyphimurium, Salmonellaenteritidis and Salmonella infantis were washed and suspended in 10xa0mL of sterile deionized water. Approximately 5xa0μl of the bacterial suspensions were placed on the substrate individually and exposed to 785xa0nm laser excitation. SERS spectral data were recorded between 400 and 1,800xa0cm−1. SERS signals were collected from 15 different spots on the substrate for each sample. PCA model was developed to classify Salmonella serotypes. PC1 identified 92xa0% of the variation between the Salmonella serotypes, and PC2 identified 6xa0% and in total 98xa0% between the serotypes. Soft independent modeling of class analogies of validation set gave an average correct classification of 92xa0%. Comparison of the SERS spectra of Salmonella serotypes indicated that both isolates have similar cell walls and cell membrane structures which were identified by spectral regions between 520 and 1,050xa0cm−1. However, major differences were detected in cellular genetic material and proteins between 1,200 and 1,700xa0cm−1. SERS with silver biopolymer nanoparticle substrate could be a promising tool in pathogen detection and it would potentially be used to classify them.

Modified pressure imaging for egg crack detection and resulting egg quality

Cracks in the shell surface compromise the primary barrier for external microbial contamination of the egg. Microcracks are very small cracks in the shell surface that are difficult to detect by human graders. New technology has been developed that uses modified pressure and imaging to detect microcracks in eggs. Research has shown the system to have an accuracy of 99.6% in detecting both cracked and intact eggs. A study was undertaken to determine if quality differences existed between modified pressure imaged and control eggs during extended cold storage. Three replicates were conducted with eggs stored at 4 degrees C for 5 wk with weekly quality testing. The physical quality factors monitored were Haugh units, albumen height, egg weight, shell strength, vitelline membrane strength and elasticity, and whole egg total solids. All measurements were conducted on individual eggs (12/treatments per replicate) each week with the exception of whole egg solids, which were determined from 3 pools (4 eggs each)/treatment per replicate each week. Percentage of whole egg total solids was the only significant difference (P < 0.05) between treatments (23.65% modified pressure imaged and 23.47% control). There was a significant difference (P < 0.05) for egg weight between replicates (60.82, 58.02, and 60.58 g for replicates 1, 2, and 3, respectively). Therefore, imaging eggs in the modified pressure system for microcrack detection did not alter egg quality during extended cold storage. Utilizing the modified pressure crack detection technology would result in fewer cracked eggs reaching the consumer, consequently enhancing food safety without affecting product quality.

Hyperspectral imaging for poultry contaminant detection

A hyperspectral imaging system was designed and constructed to collect spectral and spatial images of poultry carcasses.t- Briefly, the imaging system consists of an imaging spectrograph with 25 urn slit width-Grating Type I (ImSpector V9, Spectral Vision, Ltd); a high-resolution CCD camera (SensiCam, Cooke Corp.); 1.4/17 mm compact C-mount lens, (Xenoplan, Schneider) and associated optical hardware; motor for lens motion control (Newport); frame-grabber (12-bit PCI interface board, Cooke Corp.); and computer (Pentium III, 500 MHz). The prism-grating-prism spectrograph has a nominal spectral range of 400 to 900 nm with a 6.6-mm axis and attaches to the camera for generating linescan images. The spectrograph has a nominal spectral resolution of 2.5 nm. It is connected to a 2/3 silicon based CCD sensor with a 1280 x 1024 pixel resolution. The lighting system consists of two 150-watt quartz halogen DC stabilised fibre optic illuminators (Fiber-Lite A240, Dolan-Jenner, Inc.), lamp assem-

Development of real-time line-scan hyperspectral imaging system for online agricultural and food product inspection

This paper reports a recent development of a line-scan hyperspectral imaging system for real-time multispectral imaging applications in agricultural and food industries. The hyperspectral imaging system consisted of a spectrograph, an EMCCD camera, and application software. The real-time multispectral imaging with the developed system was possible due to (1) data binning, especially a unique feature of the EMCCD sensor allowing the access to non-contiguous multispectral bands, (2) an image processing algorithm designed for real-time multispectral imaging, and (3) the design and implementation of the real-time application software. The imaging system was developed as a poultry inspection instrument determining the presence of surface feces on poultry carcasses moving at commercial poultry processing line speeds up to 180 birds per minute. The imaging system can be easily modifiable to solve other real-time inspection/sorting problems. Three wavelengths at 517 nm, 565 nm and 802 nm were selected for real-time fecal detection imaging. The fecal detection algorithm was based on dual band ratios of 565nm/517nm and 802nm/517nm followed by thresholding. The software architecture was based on a ping pong memory and a circular buffer for the multitasking of image grabbing and processing. The software was written in Microsoft Visual C++. An image-based internal triggering (i.e. polling) algorithm was developed to determine the start and end positions of birds. Twelve chickens were used for testing the imaging system at two different speeds (140 birds per minute and 180 bird per minute) in a pilot-scale processing line. Four types of fecal materials (duodenum, ceca, colon and ingesta) were used for the evaluation of the detection algorithm. The software grabbed and processed multispectral images of the dimension 118 (line scans) x 512 (height) x 3 (bands) pixels obtained from chicken carcasses moving at the speed up to 180 birds per minute (a frame rate 286 Hz). Intensity calibration, detection algorithm, displaying and saving were performed within the real-time deadlines.