Diane E. Chan

MULTISPECTRAL DETECTION OF FECAL CONTAMINATION ON APPLES BASED ON HYPERSPECTRAL IMAGERY: PART I. APPLICATION OF VISIBLE AND NEAR–INFRARED REFLECTANCE IMAGING

Fecal contamination of apples is an important food safety issue. To develop automated methods to detect such contamination, a recently developed hyperspectral imaging system with a range of 450 to 851 nm was used to examine reflectance images of experimentally contaminated apples. Fresh feces from dairy cows were applied simultaneously as a thick patch and as a thin, transparent (not readily visible to the human eye), smear to four cultivars of apples (Red Delicious, Gala, Fuji, and Golden Delicious). To address differences in coloration due to environmental growth conditions, apples were selected to represent the range of green to red colorations. Hyperspectral images of the apples and fecal contamination sites were evaluated using principal component analysis with the goal of identifying two to four wavelengths that could potentially be used in an on-line multispectral imaging system. Results indicate that contamination could be identified using either three wavelengths in the green, red, and NIR regions, or using two wavelengths at the extremes of the NIR region under investigation. The three wavelengths in the visible and near-infrared regions offer the advantage that the acquired images could also be used commercially for color sorting. However, detection using the two NIR wavelengths was found to be less sensitive to variations in apple coloration. For both sets of wavelengths, thick contamination could easily be detected using a simple threshold unique to each cultivar. In contrast, results suggest that more computationally complex analyses, such as combining threshold detection with morphological filtering, would be necessary to detect thin contamination spots using reflectance imaging techniques.

MULTISPECTRAL DETECTION OF FECAL CONTAMINATION ON APPLES BASED ON HYPERSPECTRAL IMAGERY: PART II. APPLICATION OF HYPERSPECTRAL FLUORESCENCE IMAGING

Pathogenic E. coli contamination in unpasteurized apple juice or cider is thought to originate from animal feces, and fecal contamination of apples has been recognized by the FDA as an important health issue. In a companion article, reflectance imaging techniques were shown inadequate for the detection of thin smears of feces applied to apples. The objective of this study was to evaluate the use of fluorescence imaging techniques to detect fecal contamination on apple surfaces. A hyperspectral imaging system based on a spectrograph, camera, and UV light source was used to obtain hyperspectral images of Red Delicious, Fuji, Golden Delicious, and Gala apples. Fresh dairy feces were applied to each apple as both a thick patch and as a thin smear. Results indicate that multispectral fluorescence techniques can be used to effectively detect fecal contamination on apple surfaces. Both principal component analysis and examination of emission maxima identified the same four multispectral bands (450, 530, 685, and 735 nm) as being the optimal bands to allow discrimination of contaminated apple surfaces. Furthermore, the simple two-band ratio (e.g., 685 to 450 nm) reduced the variation in normal apple surfaces while accentuating differences between contaminated and uncontaminated areas. Because of the limited sample size, delineation of an optimal detection scheme is beyond the scope of the current study. However, the results suggest that use of multispectral fluorescence techniques for detection of fecal contamination on apples in a commercial setting may be feasible.

Development of a simple algorithm for the detection of chilling injury in cucumbers from visible/near-infrared hyperspectral imaging

Hyperspectral images of cucumbers under a variety of conditions were acquired to explore the potential for the detection of chilling-induced damage in whole cucumbers. Region of interest (ROI) spectral features of chilling injured areas, resulting from chilling treatment at 0 °C, showed the reduction of reflectance intensity over the period at post-chilling room temperature (RT) storage. A large spectral difference between good, smooth skins and chilling-injured skins occurred in the 700–850 nm visible/near-infrared (NIR) region. Both simple band ratio algorithms and principal component analysis (PCA) were attempted to discriminate the ROI spectra of good cucumber skins from those of chilling injured ones. Results revealed that both the dual-band ratio algorithm (R811nm/R756nm) and a PCA model from a narrow spectral region of 733–848 nm can detect chilling-injured skins with a success rate of over 90%. The results also suggested that chilling injury is relatively difficult to detect at the initial post-chilling RT stage, especially during the first 0–2 days in storage, due to insignificant manifestation of chilling induced symptoms.

Line-Scan Hyperspectral Imaging Platform for Agro-Food Safety and Quality Evaluation: System Enhancement and Characterization

Line-scan-based hyperspectral imaging techniques have often served as a research tool to develop rapid multispectral methods based on only a few spectral bands for rapid online applications. With continuing technological advances and greater accessibility to and availability of optoelectronic imaging sensors and spectral imaging spectrographs, the range of implementation for hyperspectral imaging has been broadening across quality and safety inspection needs in the food and agricultural industries. We have developed a series of food inspection imaging systems based on hyperspectral line-scan imaging with the use of a low-light sensitive, electron-multiplying charge-coupled device (EMCCD). In this methodology article, the spectral and spatial system performance of the latest generation of the ARS hyperspectral imaging system, which is capable of reflectance and fluorescence measurements in the visible and near-infrared (NIR) spectral regions from 400 to 1000 nm, is evaluated. Results show that the spectral resolution of the system is 4.4 nm at full-width at half-maximum (FWHM) and 6 nm FWHM at our typical operation mode (6-pixel spectral binning). We enhanced the system throughput responses by using spectral weighting filters to better utilize the dynamic range of the analog-to-digital converter. With this system throughput adjustment, noise-equivalent reflectance measurements were significantly reduced by approximately 50% in the NIR region for a range of standard diffuse reflectance targets. The responsivity of the system from 450 to 950 nm was determined to be linear.

Development of hyperspectral imaging technique for the detection of chilling injury in cucumbers

Hyperspectral images of cucumbers were acquired before and during cold storage treatments as well as during subsequent room temperature (RT) storage to explore the potential for the detection of chilling induced damage in whole cucumbers. Region of interest (ROI) spectral features of chilling injured areas, resulting from cold storage treatments at 0°C or 5°C, showed a reduction in reflectance intensity during multi-day post chilling periods of RT storage. Large spectral differences between good-smooth skins and chilling injured skins occurred in the 700-850 nm visible/NIR region. A number of data processing methods, including simple spectral band algorithms, second difference, and principal component analysis (PCA), were attempted to discriminate the ROI spectra of good cucumber skins from those of chilling injured skins. Results revealed that using either a dual-band ratio algorithm (Q811/756) or a PCA model from a narrow spectral region of 733-848 nm could detect chilling injured skins with a success rate of over 90%. Furthermore, the dual-band algorithm was applied to the analysis of images of cucumbers at different conditions, and the resultant images showed more correct identification of chilling injured spots than other processing methods.

SEPARATING SEPTICEMIC AND NORMAL CHICKEN LIVERS BY VISIBLE/NEAR–INFRARED SPECTROSCOPY AND BACK–PROPAGATION NEURAL NETWORKS

The visible/near–infrared spectra of 300 chicken livers were analyzed to explore the feasibility of using spectroscopy to separate septicemic livers from normal livers. Three strategies involving offset, second difference, and functional link methods were applied to preprocess the spectra, while principal component analysis (PCA) was utilized to reduce the input data dimensions. PCA scores were fed into a feed–forward back–propagation neural network for classification. The results showed no obvious difference in classification accuracy between offset and non–offset data when no other preprocessing method was applied. The full 400–2498 nm wavelength region produced better results than the 400–700 nm, 400–1098 nm, and 1102–2498 nm sub–regions when more than 30 PCA scores were used. In general, the classification accuracy was improved by increasing the number of scores of input data, but too many scores diminished performance. The functional link test showed that using functional–link spectra selected at every third point with 60 scores achieved the same classification accuracy as that obtained when using all the data points with 90 scores. The best classification model used offset correction followed by second difference (g = 31) and 60 scores. It achieved a classification accuracy of 98% for normal and 94% for septicemic livers.

A Spatially Offset Raman Spectroscopy Method for Non-Destructive Detection of Gelatin-Encapsulated Powders

Non-destructive subsurface detection of encapsulated, coated, or seal-packaged foods and pharmaceuticals can help prevent distribution and consumption of counterfeit or hazardous products. This study used a Spatially Offset Raman Spectroscopy (SORS) method to detect and identify urea, ibuprofen, and acetaminophen powders contained within one or more (up to eight) layers of gelatin capsules to demonstrate subsurface chemical detection and identification. A 785-nm point-scan Raman spectroscopy system was used to acquire spatially offset Raman spectra for an offset range of 0 to 10 mm from the surfaces of 24 encapsulated samples, using a step size of 0.1 mm to obtain 101 spectral measurements per sample. As the offset distance was increased, the spectral contribution from the subsurface powder gradually outweighed that of the surface capsule layers, allowing for detection of the encapsulated powders. Containing mixed contributions from the powder and capsule, the SORS spectra for each sample were resolved into pure component spectra using self-modeling mixture analysis (SMA) and the corresponding components were identified using spectral information divergence values. As demonstrated here for detecting chemicals contained inside thick capsule layers, this SORS measurement technique coupled with SMA has the potential to be a reliable non-destructive method for subsurface inspection and authentication of foods, health supplements, and pharmaceutical products that are prepared or packaged with semi-transparent materials.

Inspection of Fecal Contamination on Strawberries Using Line-Scan LED-Induced Fluorescence Imaging Techniques

In the United States, fecal contamination of produce is a food safety issue associated with pathogens such as Escherichia coli and Salmonella that can easily pollute agricultural products via animal and human fecal matters. Outbreaks of foodborne illnesses associated with consuming raw fruits and vegetables in the US have occurred more frequently in recent years. This problem not only threatens public health, but also results in a huge amount of unnecessary economic losses every year. Therefore, developing optical sensing technologies for the detection of contaminants on fresh produce is urgent and essential. Among fruits, strawberry is one high-potential vector of fecal contamination and foodborne illnesses since the fruit is often consumed raw and with minimal processing. In the present study, line-scan LED-induced fluorescence imaging techniques were applied for inspection of fecal material on strawberries, and the spectral characteristics and specific wavebands of strawberries were determined by detection algorithms. The results indicated that the combination of two-waveband intensity ratios, such as 680 nm / 688 nm and 680 nm / 704 nm, can successfully distinguish fecal contamination, uncontaminated surfaces, and leaves. The binary images showed that the algorithm could successfully detect all of the fecal contamination spots that were applied to the strawberry surfaces. The results of this study would improve the safety and quality of produce consumed by the public.

Machine Vision System for Automatic Online Inspection of Freshly Slaughtered Chickens

A machine vision system was developed and evaluated for the automation of online inspection to differentiate freshly slaughtered wholesome chickens from systemically diseased chickens. The system consisted of an electron-multiplying charge-coupled-device (EMCCD) camera used with an imaging spectrograph and controlled by a computer to obtain line-scan images quickly on a chicken processing line of a commercial poultry plant. The system scanned chicken carcasses on an eviscerating line operating at a speed of 140 chickens per minute. An algorithm was implemented in the system to automatically recognize individual carcasses entering and exiting the field of view, to locate the region of interest (ROI) of each chicken, to extract useful spectra from the ROI as inputs to the differentiation method, and to determine the condition for each carcass as being wholesome or systemically diseased. The system can acquire either hyperspectral or multispectral images without any cross-system calibration. The essential spectral features were selected from hyperspectral images of chicken samples. The differentiation of chickens on the processing line was then carried out using multispectral imaging. The high accuracy obtained from the evaluation results showed that the machine vision system can be applied successfully to automatic online inspection for chicken processing.

Online Machine Vision System for Inspection of Poultry Carcasses

A machine vision system was developed and evaluated for automation of online inspection to differentiate freshly slaughtered wholesome chickens from systemically diseased ones. The system consisted of an electron-multiplying charge-coupled-device (EMCCD) camera and an imaging spectrograph to obtain line-scan images quickly in a processing line of a poultry plant. The system scanned the surfaces of freshly slaughtered chicken carcasses on an eviscerating line at a speed of 140 chickens per minute. An algorithm was implemented in the system to automatically recognize carcasses entering and exiting the field of view, to locate the region of interest (ROI) of the chicken surface, to extract useful spectra from the ROI as inputs to the differentiation method, and to determine the chicken condition for each carcass. The system can take either hyperspectral or multispectral images without any cross-system calibration. The essential spectral features were selected from hyperspectral images of chicken samples. The differentiation of chickens on the processing line was carried out using multispectral imaging. The high accuracy obtained from the evaluation results showed that the machine vision system can be applied successfully to automatic online inspection for chicken processing.