Search

Our goal is to use multiple spectroscopy methods in a single system and develop novel multimode spectroscopic data fusion techniques for fish species identification in real-time. We collected spectral signatures of fish fillets from six fish species using four hyperspectral imaging systems: (1) Reflectance spectral imaging in the visible and NIR (VIS-NIR), (2) Reflectance spectral imaging in the short wave infrared (SWIR), (3) Fluorescence visible spectral imaging with UVA and violet excitation, (4) Raman imaging with a 785 nm laser excitation. All fish fillet samples were confirmed by DNA testing. We built multiple classification/ dimension reduction combination methods to calculate the average sensitivity and associated variance for each class and each spectroscopy mode. In our prototype, the derived statistics are used to form policies for Monte Carlo prediction reinforcement learning. We compared the results of our weighted fusion decisions against individual spectroscopy mode decisions to show an overall sensitivity improvement. We believe this is the first reported use of reinforcement learning applied to multimode spectroscopy data classification in food fraud applications.

This study developed multimode hyperspectral imaging techniques to detect substitution and mislabeling of fish fillets. Line-scan hyperspectral images were collected from fish fillets in four modes, including reflectance in visible and nearinfrared (VNIR) region, fluorescence by 365 nm UV excitation, reflectance in short-wave infrared (SWIR) region, and Raman by 785 nm laser excitation. Fish fillets of six species (i.e., red snapper, vermilion snapper, Malabar snapper, summer flounder, white bass, and tilapia) were used for species differentiation and frozen-thawed red snapper fillets were used for freshness evaluation. A total of 24 machine learning classifiers were used for fish species and freshness classifications using four types of spectral data in three different subsets (i.e., full spectra, first ten components of principal component analysis, and bands selected by a sequential feature selection method). The highest accuracies were achieved at 100% using full VNIR reflectance spectra for the species classification and 99.9% using full SWIR reflectance spectra for the freshness classification. The VNIR reflectance mode gave an overall best performance for both species and freshness inspection.

Commercial Raman systems generally conduct imaging and spectroscopy measurements at subcentimeter scales. Such small spatial ranges cannot be used to inspect food samples with large surface areas (e.g., tomato fruit and beef steak), which is not convenient for food experiments. A line-scan macro-scale Raman system has been developed using a 785 nm line laser to implement high-throughput Raman chemical imaging (RCI) for food safety and quality research. A one-axis positioning table is used to move the samples to accumulate hyperspectral data using a pushbroom method. A dispersive Raman spectrograph is used in the system, which can be configured to backscattering RCI mode for surface inspection and spatially offset Raman spectroscopy (SORS) mode for subsurface inspection. In-house developed LabVIEW software is used to fulfill functions for system control, hardware parameterization, and data transfer. The systems is flexible and versatile for food test, and it has been used to evaluate safety and quality of various food and agricultural products, such as detecting chemical adulterants mixed in food powders, mapping carotenoid content on carrot cross section, imaging whole surface of pork shoulder, and authenticating foods and ingredients through packages.

Despite the complexity of the factors that lead to loss of seed viability, conventional methods like germination tests, tetrazolium tests are commonly employed to determine it. However, these methods have downsides like being destructive, time consuming and non-representative. Therefore, there is a need to develop a fast, non-destructive and real-time measurement and sorting system of seeds based on viability for industrial purpose. In this study, we seek to utilize HSI and multivariate data analysis techniques to classify viable seeds from non-viable ones and later use it basis to develop an online real-time detection system for sorting these seeds based on viability. For this cause, Data from melon and watermelon seeds were collected using a SWIR HSI system. The performance of the classification models achieved both during calibration and real-time tests were quite impressive and a proof that HSI can be effectively applied to an industrial real-time sorting system.

Applications of machine vision techniques are prevalent for quality inspection of foods. For safety inspection of fruits such as apples to detect biological contaminants, a method to capture and reconstruct a whole-surface of apple is needed. In this paper, we present a reconstruction method for whole-surface imaging of apples with the use of a line-scan hyperspectral imaging technique. In addition, the development of online whole-surface inspection technology for round-fruits is presented.

The objective of this study was to predict the moisture content, soluble solids content, and titratable acidity content in bell peppers during storage, based on hyperspectral imaging (HSI) in the 1000–1500 nm wavelength range. The mean spectra of 148 mature bell peppers were extracted from the hyperspectral images, and multivariate calibration models were built using partial least squares regression to predict MC, SSC, and TA content in bell peppers with different preprocessing techniques. The selected optimum wavelengths were used to create distribution maps for MC, SSC, and TA content of bell peppers. The results revealed that HSI coupled with multivariate analysis can be used successfully to predict the MC, SSC, and TA content in bell peppers.

Bacterial biofilm formed by pathogens on fresh produce surfaces is a food safety concern because the complex extracellular matrix in the biofilm structure reduces the reduction and removal efficacies of washing and sanitizing processes such as chemical or irradiation treatments. Therefore, a rapid and nondestructive method to identify pathogenic biofilm on produce surfaces is needed to ensure safe consumption of fresh, raw produce. This research aimed to evaluate the feasibility of hyperspectral fluorescence imaging for detecting Escherichia.coli (ATCC 25922) biofilms on baby spinach leaf surfaces. Samples of baby spinach leaves were immersed and inoculated with five different levels (from 2.6x104 to 2.6x108 CFU/mL) of E.coli and stored at 4°C for 24 h and 48 h to induce biofilm formation. Following the two treatment days, individual leaves were gently washed to remove excess liquid inoculums from the leaf surfaces and imaged with a hyperspectral fluorescence imaging system equipped with UV-A (365 nm) and violet (405 nm) excitation sources to evaluate a spectral-image-based method for biofilm detection. The imaging results with the UV-A excitation showed that leaves even at early stages of biofilm formations could be differentiated from the control leaf surfaces. This preliminary investigation demonstrated the potential of fluorescence imaging techniques for detection of biofilms on leafy green surfaces.

Hyperspectral imaging has been shown to be a powerful tool for nondestructive evaluation of biological samples. We recently developed a new line-scan-based shortwave infrared (SWIR) hyperspectral imaging system. Critical sensing components of the system include a SWIR spectrograph, an MCT (HgCdTe) array detector, and a custom-designed illumination source. The system has an effective imaging range from 900 nm to 2500 nm. In this paper, we present SWIR hyperspectral images of plant leaves and fruits, and preliminary SWIR image analysis results.

Fluorescence imaging technique has been widely used for quality and safety measurements of agro-food materials. Fluorescence emission intensities of target materials are influenced by wavelengths of excitation sources. Hence, selection of a proper excitation wavelength is an important factor in differentiating target materials effectively. In this study, optimal fluorescence excitation wavelength was determined on the basis of fluorescence emission intensity of defect and sound areas of cherry tomatoes. The result showed that fluorescence responses of defect and sound surfaces of cherry tomatoes were most significantly separated with the excitation light wavelength range between 400 and 410 nm. Fluorescence images of defect cherry tomatoes were acquired with the LEDs with the central wavelength of 410 nm as the excitation source to verify the detection efficiency of cherry tomato defects. The resultant fluorescence images showed that the defects were discriminated from sound areas on cherry tomatoes with above 98% accuracy. This study shows that high power LEDs as the excitation source for fluorescence imaging are suitable for defect detection of cherry tomatoes.