The R 2 was 0.612 when the spectra between 1100 nm and 1350 nm were analyzed. When the second derivatives of the spectral data were used, the R 2 of the PCR model to predict WB shear force of the meat was 0.633 for the full spectral range of 1100 to 2498 nm and 0.616 for the spectral range of 1100 to 1350 nm.
The spectral range is from 430 to 930 nm with spectral resolution of approximately 10 nm (full width at half maximum) and spatial resolution better than 1 mm. Our system is capable of reflectance and fluorescence measurements with the use of dual illumination sources where fluorescence emissions are measured with ultraviolet (UV-A) excitation. We present the calibrations and image-correction procedures for the system artifacts and heterogeneous responses caused by the optics, sensor, and lighting conditions throughout the spectrum region for reflectance and fluorescence. The results of the fluorescence correction method showed that the system responses throughout the spectrum region were normalized to within 0.5% error. The versatility of the hyperspectral imaging system was demonstrated with sample fluorescence and reflectance images of a normal apple and an apple with fungal contamination and bruised spots. The primary use of the imaging system in our laboratory is to conduct food safety and quality research. However, we envision that this unique system can be used in a number of scientific applications.
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.
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.
The Instrumentation and Sensing Laboratory, ARS, USDA, has developed a Vis/NIR spectroscopic system for on-line poultry carcass inspection. This system was proven to be effective in distinguishing between wholesome and unwholesome carcasses. To better understand how the carcasses can be differentiated, a further in-depth study of Vis/NIR spectra of poultry samples was conducted. Results showed that Vis/NIR spectroscopy can be used to differentiate poultry samples more finely than merely between a wholesome category and a broadly inclusive unwholesome category. Using principal component analysis (PCA) and discriminant analysis, wholesome, septicemia, and cadaver chicken samples were differentiated from each other with high accuracy. The best Vis/NIR classification model, using nine principal components (PCs) and a linear discriminant function, correctly classified 100%, 90.0%, and 92.5% of the whole (skin and meat) samples for wholesome, septicemia, and cadaver categories, respectively. For skin only samples, similar models using nine PCs resulted in lower accuracies. Examination of the PCA loadings for the whole samples suggested that the better discrimination of whole samples was dependent on spectral variation related to different forms of myoglobin present in the chicken meat,
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.