The purpose of this study is to develop a bee mite detection model using hyperspectral images of bee combs and deep learning-based recognition algorithms. The hyperspectral image has a resolution of 510 × 270 and consist of 15 wavebands in the ranging from 611 nm to 850 nm. Image processing was applied to preprocess data and used for data augmentation. Convolutional Neural Network (CNN) was used to develop the bee and bee mite detection models. The developed bee mite detection model was combined with an algorithm for localization to detect honey bees in hyperspectral bee comb images. Consequently, the bee mite detection model using snapshot hyperspectral image was developed to recognize the bee mite.
In this study, the optimal distance between the light source and the sensor by each apple size was investigated for soluble solid content (SSC) measurement, and 1D-Convolutional Neural Network (CNN) SSC models were developed at that distance. The visible/near-infrared transmittance spectra of apple in the range of 400 to 1100 nm were measured using a 100W halogen light source. The distance between the light source and the sensor was set at three levels, which had less impact on the size of the apple investigated in the previous study. The transmission spectra of the fruit were measured at the distance of each level by size, and the SSC was also measured. 1D- CNN was used to develop SSC estimation models. The results of this study showed that 1D-CNN technology could improve the SSC measurement performance of apples. In the future, these deep learning results can be applied to a high-performance online non-destructive fruit sorter.
A rapid and reliable inspection technique for determining sanitation status of produce processing equipment surfaces in processing facilities is needed to help reduce potential food safety risks. In this study, fluorescence imaging methods were evaluated to detect produce residues on the surfaces of food processing equipment such as stainless steel (STS). Contamination spots on the STS were created using droplets of a range of dilutions of carrot juice. Hyperspectral fluorescence images of the sample surfaces were obtained using excitation light sources based on ultraviolet LEDs (365 nm) and on violet LEDs (405 nm) for comparison. Image and spectral data were analyzed to determine optimal single bands and two-band ratios to detect the juice residue spots of the STS, and a support vector machine (SVM) algorithm was applied to the ratio images to determine classification accuracies. These results suggest that the simple multispectral fluorescence imaging methods can potentially be incorporated into portable imaging devices for spot-checking food contact surfaces for contaminants in processing facilities.
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.
The consumption of fresh-cut agricultural produce in Korea has been growing. The browning of fresh-cut vegetables
that occurs during storage and foreign substances such as worms and slugs are some of the main causes of consumers’
concerns with respect to safety and hygiene. The purpose of this study is to develop an on-line system for evaluating
quality of agricultural products using hyperspectral imaging technology. The online evaluation system with single
visible-near infrared hyperspectral camera in the range of 400 nm to 1000 nm that can assess quality of both surfaces of
agricultural products such as fresh-cut lettuce was designed. Algorithms to detect browning surface were developed for
this system. The optimal wavebands for discriminating between browning and sound lettuce as well as between
browning lettuce and the conveyor belt were investigated using the correlation analysis and the one-way analysis of
variance method. The imaging algorithms to discriminate the browning lettuces were developed using the optimal
wavebands. The ratio image (RI) algorithm of the 533 nm and 697 nm images (RI533/697) for abaxial surface lettuce and
the ratio image algorithm (RI533/697) and subtraction image (SI) algorithm (SI538-697) for adaxial surface lettuce had the
highest classification accuracies. The classification accuracy of browning and sound lettuce was 100.0% and above
96.0%, respectively, for the both surfaces. The overall results show that the online hyperspectral imaging system could
potentially be used to assess quality of agricultural products.
A nondestructive, real-time pungency measuring system with visible and near-infrared spectroscopy has been recently
developed to measure capsaicinoids content in Korean red-pepper powder. One hundred twenty-five red-pepper powder
samples produced from 11 regions in Republic of Korea were used for this investigation. The visible and near-infrared
absorption spectra in the range from 450 to 950 nm were acquired and used for the development of prediction models of
capsaicinoids contents in red-pepper powders without any chemical pretreatment to the samples. Partial Least Squares
Regression (PLSR) models were developed to predict the regional capsaicinoids contents using the acquired absorption
spectra. The chemical analysis of the total capsaicinoids (capsaicin and dihydrocapsaicin) was performed by a high
performance liquid chromatographic (HPLC) method. The determination coefficient of validation (RV2) and the standard
error of prediction (SEP) for the capsaicinoids content prediction model, for a representative region in this study, were
0.9585 and ±10.147 mg/100g, respectively.
This study presented a preliminary investigation into the use of macro-scale Raman chemical imaging for the screening
of dry milk powder for the presence of chemical contaminants. Melamine was mixed into dry milk at concentrations
(w/w) of 0.2%, 0.5%, 1.0%, 2.0%, 5.0%, and 10.0% and images of the mixtures were analyzed by a spectral information
divergence algorithm. Ammonium sulfate, dicyandiamide, and urea were each separately mixed into dry milk at
concentrations of (w/w) of 0.5%, 1.0%, and 5.0%, and an algorithm based on self-modeling mixture analysis was applied
to these sample images. The contaminants were successfully detected and the spatial distribution of the contaminants
within the sample mixtures was visualized using these algorithms. Although further studies are necessary, macro-scale
Raman chemical imaging shows promise for use in detecting contaminants in food ingredients and may also be useful
for authentication of food ingredients.
Many researchers have been tried to find a rapid pungency measuring method for the capsaicinoids, the main component of spicy to
overcome the disadvantages of the conventional HPLC measurement which is labor-intensive, time-consuming, and expensive. In
this research, an on-line based pungency measuring system for red-pepper powder was developed using a UV/Visible/Near-Infrared
spectrometer with the wavelength range of 400 ~ 1050 nm. The system was constructed with a charge-couple device(CCD)
spectrometer, a reference measuring unit, and a sample transfer unit. Predetermined non-spicy red-pepper powder were
mixed with spicy one (var. Chungyang) to produce samples with a wide range of spicy levels. Total 33 different samples with
11 spicy levels and three particle size(below 0.425 mm, 0.425 ~ 0.71 mm, 0.71 ~ 1.4 mm) were prepared for
measurements. The Partial Least Square Regression Model (PLSR model) was developed to predict the capsaicinoids content with
the obtained spectra using the developed pungency measuring system and compared with the results measured by HPLC. The best
result of PLSR model (R2 = 0.979, SEP = ± 6.56 mg%) was achieved for the spectra of red-pepper powders of the
particle size below 1.4 mm with a pretreatment of smoothing with a 6.5 nm wavelength gap. The results show the
potential of NIRS technique for non-destructive and on-line measurement of capsaicinoids content in red-pepper powder.
The physical and mechanical properties of baby spinach were investigated, including density, Young's modulus, fracture
strength, and friction coefficient. The average apparent density of baby spinach leaves was 0.5666 g/mm3. The tensile
tests were performed using parallel, perpendicular, and diagonal directions with respect to the midrib of each leaf. The
test results showed that the mechanical properties of spinach are anisotropic. For the parallel, diagonal, and
perpendicular test directions, the average values for the Young's modulus values were found to be 2.137MPa, 1.0841
MPa, and 0.3914 MPa, respectively, and the average fracture strength values were 0.2429 MPa, 0.1396 MPa, and 0.1113
MPa, respectively. The static and kinetic friction coefficient between the baby spinach and conveyor belt were
researched, whose test results showed that the average coefficients of kinetic and maximum static friction between the
adaxial (front side) spinach leaf surface and conveyor belt were 1.2737 and 1.3635, respectively, and between the
abaxial (back side) spinach leaf surface and conveyor belt were 1.1780 and 1.2451 respectively. These works provide the
basis for future development of a whole-surface online imaging inspection system that can be used by the commercial
vegetable processing industry to reduce food safety risks.
The identification of pesticide and 6-benzylaminopurine (6-BAP) plant growth regulator was carried out using a label-free
opto-fluidic ring resonator (OFRR) biosensor. The OFRR sensing platform is a recent advancement in opto-fluidic
technology that integrates photonic sensing technology with microfluidics. It features quick detection time, small sample
volume, accurate quantitative and kinetic results. The most predominant advantage of the OFRR integrated with
microfluidics is that we can potentially realize the multi-channel and portable biosensor that detects numerous analytes
simultaneously. Antisera for immunoassay were raised in rabbits against the 6-BAP-BSA conjugate. Using the
immunization protocol and unknown cytokinin reacting with same antibody, comparable sensitivity and specificity were
obtained. 6-BAP antibody was routinely used for cytokinin analysis. A sensitive and simple OFRR method with a good
linear relationship was developed for the determination of 6-BAP. The detection limit was also examined. The biosensor
demonstrated excellent reproducibility when periodically exposed to 6-BAP.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.