Prediction of Soluble-Solid Content in Citrus Fruit Using Visible-Near-Infrared Hyperspectral Imaging Based on Effective-Wavelength Selection Algorithm.

Citrus fruits were sorted based on external qualities, such as size, weight, and color, and internal qualities, such as soluble solid content (SSC), acidity, and firmness. Visible and near-infrared (VNIR) hyperspectral imaging techniques were used as rapid and nondestructive techniques for determining the internal quality of fruits. The applicability of the VNIR hyperspectral imaging technique for predicting the SSC in citrus fruits was evaluated in this study. A VNIR hyperspectral imaging system with a wavelength range of 400-1000 nm and 100 W light source was used to acquire hyperspectral images from citrus fruits in two orientations (i.e., stem and calyx ends). The SSC prediction model was developed using partial least-squares regression (PLSR). Spectrum preprocessing, effective wavelength selection through competitive adaptive reweighted sampling (CARS), and outlier detection were used to improve the model performance. The performance of each model was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). In the present study, the PLSR model was developed using only a citrus cultivar. The SSC prediction CARS-PLSR model with outliers removed exhibited R2 and RMSE values of approximatively 0.75 and 0.56 °Brix, respectively. The results of this study are expected to be useful in similar fields such as agricultural and food post-harvest management, as well as in the development of an online system for determining the SSC of citrus fruits.

Multispectral Wavebands Selection for the Detection of Potential Foreign Materials in Fresh-Cut Vegetables.

Ensuring the quality of fresh-cut vegetables is the greatest challenge for the food industry and is equally as important to consumers (and their health). Several investigations have proven the necessity of advanced technology for detecting foreign materials (FMs) in fresh-cut vegetables. In this study, the possibility of using near infrared spectral analysis as a potential technique was investigated to identify various types of FMs in seven common fresh-cut vegetables by selecting important wavebands. Various waveband selection methods, such as the weighted regression coefficient (WRC), variable importance in projection (VIP), sequential feature selection (SFS), successive projection algorithm (SPA), and interval PLS (iPLS), were used to investigate the optimal multispectral wavebands to classify the FMs and vegetables. The application of selected wavebands was further tested using NIR imaging, and the results showed good potentiality by identifying 99 out of 107 FMs. The results indicate the high applicability of the multispectral NIR imaging technique to detect FMs in fresh-cut vegetables for industrial application.

Review: Application of Artificial Intelligence in Phenomics.

Plant phenomics has been rapidly advancing over the past few years. This advancement is attributed to the increased innovation and availability of new technologies which can enable the high-throughput phenotyping of complex plant traits. The application of artificial intelligence in various domains of science has also grown exponentially in recent years. Notably, the computer vision, machine learning, and deep learning aspects of artificial intelligence have been successfully integrated into non-invasive imaging techniques. This integration is gradually improving the efficiency of data collection and analysis through the application of machine and deep learning for robust image analysis. In addition, artificial intelligence has fostered the development of software and tools applied in field phenotyping for data collection and management. These include open-source devices and tools which are enabling community driven research and data-sharing, thereby availing the large amounts of data required for the accurate study of phenotypes. This paper reviews more than one hundred current state-of-the-art papers concerning AI-applied plant phenotyping published between 2010 and 2020. It provides an overview of current phenotyping technologies and the ongoing integration of artificial intelligence into plant phenotyping. Lastly, the limitations of the current approaches/methods and future directions are discussed.

High-Throughput Phenotyping Approach for the Evaluation of Heat Stress in Korean Ginseng (Panax ginseng Meyer) Using a Hyperspectral Reflectance Image.

Panax ginseng has been used as a traditional medicine to strengthen human health for centuries. Over the last decade, significant agronomical progress has been made in the development of elite ginseng cultivars, increasing their production and quality. However, as one of the significant environmental factors, heat stress remains a challenge and poses a significant threat to ginseng plants' growth and sustainable production. This study was conducted to investigate the phenotype of ginseng leaves under heat stress using hyperspectral imaging (HSI). A visible/near-infrared (Vis/NIR) and short-wave infrared (SWIR) HSI system were used to acquire hyperspectral images for normal and heat stress-exposed plants, showing their susceptibility (Chunpoong) and resistibility (Sunmyoung and Sunil). The acquired hyperspectral images were analyzed using the partial least squares-discriminant analysis (PLS-DA) technique, combining the variable importance in projection and successive projection algorithm methods. The correlation of each group was verified using linear discriminant analysis. The developed models showed 12 bands over 79.2% accuracy in Vis/NIR and 18 bands with over 98.9% accuracy at SWIR in validation data. The constructed beta-coefficient allowed the observation of the key wavebands and peaks linked to the chlorophyll, nitrogen, fatty acid, sugar and protein content regions, which differentiated normal and stressed plants. This result shows that the HSI with the PLS-DA technique significantly differentiated between the heat-stressed susceptibility and resistibility of ginseng plants with high accuracy.

Non-Destructive Detection Pilot Study of Vegetable Organic Residues Using VNIR Hyperspectral Imaging and Deep Learning Techniques.

Contamination is a critical issue that affects food consumption adversely. Therefore, efficient detection and classification of food contaminants are essential to ensure food safety. This study applied a visible and near-infrared (VNIR) hyperspectral imaging technique to detect and classify organic residues on the metallic surfaces of food processing machinery. The experimental analysis was performed by diluting both potato and spinach juices to six different concentration levels using distilled water. The 3D hypercube data were acquired in the range of 400-1000 nm using a line-scan VNIR hyperspectral imaging system. Each diluted residue in the spectral domain was detected and classified using six classification methods, including a 1D convolutional neural network (CNN-1D) and five pre-processing methods. Among them, CNN-1D exhibited the highest classification accuracy, with a 0.99 and 0.98 calibration result and a 0.94 validation result for both spinach and potato residues. Therefore, in comparison with the validation accuracy of the support vector machine classifier (0.9 and 0.92 for spinach and potato, respectively), the CNN-1D technique demonstrated improved performance. Hence, the VNIR hyperspectral imaging technique with deep learning can potentially afford rapid and non-destructive detection and classification of organic residues in food facilities.

Handheld Multispectral Fluorescence Imaging System to Detect and Disinfect Surface Contamination.

Contamination inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle food. Food contamination must be prevented, and zero tolerance legal requirements and damage to the reputation of institutions or restaurants can be very costly. This paper introduces a new handheld fluorescence-based imaging system that can rapidly detect, disinfect, and document invisible organic residues and biofilms which may host pathogens. The contamination, sanitization inspection, and disinfection (CSI-D) system uses light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm, for the detection of organic residues, including saliva and respiratory droplets. The 275 nm light is also utilized to disinfect pathogens commonly found within the contaminated residues. Efficacy testing of the neutralizing effects of the ultraviolet light was conducted for Aspergillus fumigatus, Streptococcus pneumoniae, and the influenza A virus (a fungus, a bacterium, and a virus, respectively, each commonly found in saliva and respiratory droplets). After the exposure to UVC light from the CSI-D, all three pathogens experienced deactivation (> 99.99%) in under ten seconds. Up to five-log reductions have also been shown within 10 s of UVC irradiation from the CSI-D system.

Detection of adulterated sugar with plastic packaging based on spatially offset Raman imaging.

BACKGROUND: The application of optical sensing technology in food adulteration detection has been extensively studied. However, due to the impact of packaging materials on the penetration depth of photons in foods and the interference from the optical properties of the packaging materials themselves, the use of optical sensing technology to detect packaged foods adulteration is still a well-known problem. RESULTS: The line-scan Raman imaging system was used to collect Raman hyperspectral images of adulterated sugars, made by mixing soft sugar and cheap glucose in seven different ratios. With the 0 and 3 mm (optimal offset distance) between line-laser source and scanning line, the Raman hyperspectral images of adulterated sugars covered by packaging plastic were acquired respectively. Using adulterated samples un-covered by packaging plastic as training samples, the Random Forest prediction model was developed, and excellent prediction performance was achieved for adulterated samples un-covered by packaging plastics. Compared with Raman data acquired with 0 mm offset distance, the performance of the prediction model was significantly improved, with 0.957 for coefficient of determination (R2 ), 0.413 for root mean square error of prediction (RMSEP), and 4.846 for residual predictive deviation (RPD), for adulterated samples with plastic packaging acquired with the 3 mm offset distance. CONCLUSIONS: The novel non-destructive method based on spatially offset Raman imaging technology, which can reduce the interference of packaging materials and enhance the signal of internal interesting materials, was proposed for detection of adulterated sugar with plastic packaging. The experiment results show that spatially offset imaging technology provides a candidate method for detecting adulteration of packaged foods. © 2021 Society of Chemical Industry.

Near-Infrared Transmittance Spectral Imaging for Nondestructive Measurement of Internal Disorder in Korean Ginseng.

The grading of ginseng (Panax ginseng) including the evaluation of internal quality attributes is essential in the ginseng industry for quality control. Assessment for inner whitening, a major internal disorder, must be conducted when identifying high quality ginseng. Conventional methods for detecting inner whitening in ginseng root samples use manual inspection, which is time-consuming and inaccurate. This study develops an internal quality measurement technique using near-infrared transmittance spectral imaging to evaluate inner whitening in ginseng samples. Principle component analysis (PCA) was used on ginseng hypercube data to evaluate the developed technique. The transmittance spectra and spectral images of ginseng samples exhibiting inner whitening showed weak intensity characteristics compared to normal ginseng in the region of 900-1050 nm and 1150-1400 nm respectively, owing to the presence of whitish internal tissues that have higher optical density. On the basis of the multivariate analysis method, even a simple waveband ratio image has the great potential to quickly detect inner whitening in ginseng samples, since these ratio images show a significant difference between whitened and non-whitened regions. Therefore, it is possible to develop an efficient and rapid spectral imaging system for the real-time detection of inner whitening in ginseng using minimal spectral wavebands. This novel strategy for the rapid, cost-effective, non-destructive detection of ginseng's inner quality can be a key component for the automation of ginseng grading.

Classification of Watermelon Seeds Using Morphological Patterns of X-ray Imaging: A Comparison of Conventional Machine Learning and Deep Learning.

In this study, conventional machine learning and deep leaning approaches were evaluated using X-ray imaging techniques for investigating the internal parameters (endosperm and air space) of three cultivars of watermelon seed. In the conventional machine learning, six types of image features were extracted after applying different types of image preprocessing, such as image intensity and contrast enhancement, and noise reduction. The sequential forward selection (SFS) method and Fisher objective function were used as the search strategy and feature optimization. Three classifiers were tested (linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and k-nearest neighbors algorithm (KNN)) to find the best performer. On the other hand, in the transfer learning (deep learning) approaches, simple ConvNet, AlexNet, VGG-19, ResNet-50, and ResNet-101 were used to train the dataset and class prediction of the seed. For the supervised model development (both conventional machine learning and deep learning), the germination test results of the samples were used where the seeds were divided into two classes: (1) normal viable seeds and (2) nonviable and abnormal viable seeds. In the conventional classification, 83.6% accuracy was obtained by LDA using 48 features. ResNet-50 performed better than other transfer learning architectures, with an 87.3% accuracy which was the highest accuracy in all classification models. The findings of this study manifested that transfer learning is a constructive strategy for classifying seeds by analyzing their morphology, where X-ray imaging can be adopted as a potential imaging technique.

Improving Sensitivity in Raman Imaging for Thin Layered and Powdered Food Analysis Utilizing a Reflection Mirror.

Raman imaging has been proven to be a powerful analytical technique for the characterization and visualization of chemical components in a range of products, particularly in the food and pharmaceutical industries. The conventional backscattering Raman imaging technique for the spatial analysis of a deep layer suffers from the presence of intense fluorescent and Raman signals originating from the surface layer which mask the weaker subsurface signals. Here, we demonstrated the application of a new reflection amplifying method using a background mirror as a sample holder to increase the Raman signals from a deep layer. The approach is conceptually demonstrated on enhancing the Raman signals from the subsurface layer. Results show that when bilayer samples are scanned on a reflection mirror, the average signals increase 1.62 times for the intense band at 476 cm-1 of starch powder, and average increases of 2.04 times (for the band at 672 cm-1) for a subsurface layer of high Raman sensitive melamine powder under a 1 mm thick teflon sheet. The method was then applied successfully to detect noninvasively the presence of small polystyrene pieces buried under a 2 mm thick layer of food powder (a case of powdered food adulteration) which otherwise are inaccessible to conventional backscattering Raman imaging. In addition, the increase in the Raman signal to noise ratio when measuring samples on a mirror is an important feature in many applications where high-throughput imaging is of interest. This concept is also applicable in an analogous manner to other disciplines, such as pharmaceutical where the Raman signals from deeper zones are typically, substantially diluted due to the interference from the surface layer.

Classification Method for Viability Screening of Naturally Aged Watermelon Seeds Using FT-NIR Spectroscopy.

Viability analysis of stored seeds before sowing has a great importance as plant seeds lose their viability when they exposed to long term storage. In this study, the potential of Fourier transform near infrared spectroscopy (FT-NIR) was investigated to discriminate between viable and non-viable triploid watermelon seeds of three different varieties stored for four years (natural aging) in controlled conditions. Because of the thick seed-coat of triploid watermelon seeds, penetration depth of FT-NIR light source was first confirmed to ensure seed embryo spectra can be collected effectively. The collected spectral data were divided into viable and nonviable groups after the viability being confirmed by conducting a standard germination test. The obtained results showed that the developed partial least discriminant analysis (PLS-DA) model had high classification accuracy where the dataset was made after mixing three different varieties of watermelon seeds. Finally, developed model was evaluated with an external data set (collected at different time) of hundred samples selected randomly from three varieties. The results yield a good classification accuracy for both viable (87.7%) and nonviable seeds (82%), thus the developed model can be considered as a "general model" since it can be applied to three different varieties of seeds and data collected at different time.

Multispectral Fluorescence Imaging Technique for On-Line Inspection of Fecal Residues on Poultry Carcasses.

Rapid and reliable inspection of food is essential to ensure food safety, particularly in mass production and processing environments. Many studies have focused on spectral imaging for poultry inspection; however, no research has explored the use of multispectral fluorescence imaging (MFI) for on-line poultry inspection. In this study, the feasibility of MFI for on-line detection of fecal matter from the ceca, colon, duodenum, and small intestine of poultry carcasses was investigated for the first time. A multispectral line-scan fluorescence imaging system was integrated with a commercial poultry conveying system, and the images of chicken carcasses with fecal contaminants were scanned at processing line speeds of one, three, and five birds per second. To develop an optimal detection and classification algorithm to distinguish upper and lower feces-contaminated parts from skin, the principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) were first performed using the spectral data of the selected regions, and then applied in spatial domain to visualize the feces-contaminated area based on binary images. Our results demonstrated that for the spectral data analysis, both the PCA and PLS-DA can distinguish the high and low feces-contaminated area from normal skin; however, the PCA analysis based on selected band ratio images (F630 nm/F600 nm) exhibited better visualization and discrimination of feces-contaminated area, compared with the PLS-DA-based developed chemical images. A color image analysis using histogram equalization, sharpening, median filter, and threshold value (1) demonstrated 78% accuracy. Thus, the MFI system can be developed utilizing the two band ratios for on-line implementation for the effective detection of fecal contamination on chicken carcasses.

Rapid Measurement of Soybean Seed Viability Using Kernel-Based Multispectral Image Analysis.

Viability is an important quality factor influencing seed germination and crop yield. Current seed-viability testing methods rely on conventional manual inspections, which use destructive, labor-intensive and time-consuming measurements. The aim of this study is to distinguish between viable and nonviable soybean seeds, using a near-infrared (NIR) hyperspectral imaging (HSI) technique in a rapid and nondestructive manner. The data extracted from the NIR⁻HSI of viable and nonviable soybean seeds were analyzed using a partial least-squares discrimination analysis (PLS-DA) technique for classifying the viable and nonviable soybean seeds. Variable importance in projection (VIP) was used as a waveband selection method to develop a multispectral imaging model. Initially, the spectral profile of each pixel in the soybean seed images was subjected to PLS-DA analysis, which yielded a reasonable classification accuracy; however, the pixel-based classification method was not successful for high accuracy detection for nonviable seeds. Another viability detection method was then investigated: a kernel image threshold method with an optimum-detection-rate strategy. The kernel-based classification of seeds showed over 95% accuracy even when using only seven optimal wavebands selected through VIP. The results show that the proposed multispectral NIR imaging method is an effective and accurate nondestructive technique for the discrimination of soybean seed viability.

Through-packaging analysis of butter adulteration using line-scan spatially offset Raman spectroscopy.

Spectroscopic techniques for food quality analysis are limited to surface inspections and are highly affected by the superficial layers (skin or packaging material) of the food samples. The ability of spatially offset Raman spectroscopy (SORS) to obtain chemical information from below the surface of a sample makes it a promising candidate for the non-destructive analysis of the quality of packaged food. In the present study, we developed a line-scan SORS technique for obtaining the Raman spectra of packaged-food samples. This technique was used to quantify butter adulteration with margarine through two different types of packaging. Further, the significant commercial potential of the developed technique was demonstrated by its being able to discriminate between ten commercial varieties of butter and margarine whilst still in their original, unopened packaging. The results revealed that, while conventional backscattering Raman spectroscopy cannot penetrate the packaging, thus preventing its application to the quality analysis of packaged food, SORS analysis yielded excellent qualitative and quantitative analyses of butter samples. The partial least-square regression analysis predictive values for the SORS data exhibit correlation coefficient values of 0.95 and 0.92, associated with the prediction error 3.2 % and 3.9 % for cover-1 & 2, respectively. The developed system utilizes a laser line (ca. 14-cm wide) that enables the simultaneous collection of a large number of spectra from a sample. Thus, by averaging the spectra collected for a given sample, the signal-to-noise ratio of the final spectrum can be enhanced, which will then have a significant effect on the multivariate data analysis methods used for qualitative and/or qualitative analyses. This recently presented line-scan SORS technique could be applied to the development of high-throughput and real-time analysis techniques for determining the quality and authenticity various packaged agricultural products.

Application of Near Infrared Reflectance Spectroscopy for Rapid and Non-Destructive Discrimination of Hulled Barley, Naked Barley, and Wheat Contaminated with Fusarium.

Fusarium is a common fungal disease in grains that reduces the yield of barley and wheat. In this study, a near infrared reflectance spectroscopic technique was used with a statistical prediction model to rapidly and non-destructively discriminate grain samples contaminated with Fusarium. Reflectance spectra were acquired from hulled barley, naked barley, and wheat samples contaminated with Fusarium using near infrared reflectance (NIR) spectroscopy with a wavelength range of 1175-2170 nm. After measurement, the samples were cultured in a medium to discriminate contaminated samples. A partial least square discrimination analysis (PLS-DA) prediction model was developed using the acquired reflectance spectra and the culture results. The correct classification rate (CCR) of Fusarium for the hulled barley, naked barley, and wheat samples developed using raw spectra was 98% or higher. The accuracy of discrimination prediction improved when second and third-order derivative pretreatments were applied. The grains contaminated with Fusarium could be rapidly discriminated using spectroscopy technology and a PLS-DA discrimination model, and the potential of the non-destructive discrimination method could be verified.

Continuous Gradient Temperature Raman Spectroscopy of Fish Oils Provides Detailed Vibrational Analysis and Rapid, Nondestructive Graphical Product Authentication.

Background: Gradient temperature Raman spectroscopy (GTRS) applies the continuous temperature gradients utilized in differential scanning calorimetry (DSC) to Raman spectroscopy, providing a new means for rapid high throughput material identification and quality control. Methods: Using 20 Mb three-dimensional data arrays with 0.2 °C increments and first/second derivatives allows complete assignment of solid, liquid and transition state vibrational modes. The entire set or any subset of the any of the contour plots, first derivatives or second derivatives can be utilized to create a graphical standard to quickly authenticate a given source. In addition, a temperature range can be specified that maximizes information content. Results: We compared GTRS and DSC data for five commercial fish oils that are excellent sources of docosahexaenoic acid (DHA; 22:6n-3) and eicosapentaenoic acid (EPA; 20:5n-3). Each product has a unique, distinctive response to the thermal gradient, which graphically and spectroscopically differentiates them. We also present detailed Raman data and full vibrational mode assignments for EPA and DHA. Conclusion: Complex lipids with a variety of fatty acids and isomers have three dimensional structures based mainly on how structurally similar sites pack. Any localized non-uniformity in packing results in discrete "fingerprint" molecular sites due to increased elasticity and decreased torsion.

Non-destructive technique for determining the viability of soybean (Glycine max) seeds using FT-NIR spectroscopy.

BACKGROUND: The viability of seeds is important for determining their quality. A high-quality seed is one that has a high capability of germination that is necessary to ensure high productivity. Hence, developing technology for the detection of seed viability is a high priority in agriculture. Fourier transform near-infrared (FT-NIR) spectroscopy is one of the most popular devices among other vibrational spectroscopies. This study aims to use FT-NIR spectroscopy to determine the viability of soybean seeds. RESULTS: Viable and artificial ageing seeds as non-viable soybeans were used in this research. The FT-NIR spectra of soybean seeds were collected and analysed using a partial least-squares discriminant analysis (PLS-DA) to classify viable and non-viable soybean seeds. Moreover, the variable importance in projection (VIP) method for variable selection combined with the PLS-DA was employed. The most effective wavelengths were selected by the VIP method, which selected 146 optimal variables from the full set of 1557 variables. CONCLUSIONS: The results demonstrated that the FT-NIR spectral analysis with the PLS-DA method that uses all variables or the selected variables showed good performance based on the high value of prediction accuracy for soybean viability with an accuracy close to 100%. Hence, FT-NIR techniques with a chemometric analysis have the potential for rapidly measuring soybean seed viability. © 2017 Society of Chemical Industry.

Classification of Fusarium-Infected Korean Hulled Barley Using Near-Infrared Reflectance Spectroscopy and Partial Least Squares Discriminant Analysis.

The purpose of this study is to use near-infrared reflectance (NIR) spectroscopy equipment to nondestructively and rapidly discriminate Fusarium-infected hulled barley. Both normal hulled barley and Fusarium-infected hulled barley were scanned by using a NIR spectrometer with a wavelength range of 1175 to 2170 nm. Multiple mathematical pretreatments were applied to the reflectance spectra obtained for Fusarium discrimination and the multivariate analysis method of partial least squares discriminant analysis (PLS-DA) was used for discriminant prediction. The PLS-DA prediction model developed by applying the second-order derivative pretreatment to the reflectance spectra obtained from the side of hulled barley without crease achieved 100% accuracy in discriminating the normal hulled barley and the Fusarium-infected hulled barley. These results demonstrated the feasibility of rapid discrimination of the Fusarium-infected hulled barley by combining multivariate analysis with the NIR spectroscopic technique, which is utilized as a nondestructive detection method.

Raman Hyperspectral Imaging for Detection of Watermelon Seeds Infected with Acidovorax citrulli.

The bacterial infection of seeds is one of the most important quality factors affecting yield. Conventional detection methods for bacteria-infected seeds, such as biological, serological, and molecular tests, are not feasible since they require expensive equipment, and furthermore, the testing processes are also time-consuming. In this study, we use the Raman hyperspectral imaging technique to distinguish bacteria-infected seeds from healthy seeds as a rapid, accurate, and non-destructive detection tool. We utilize Raman hyperspectral imaging data in the spectral range of 400-1800 cm-1 to determine the optimal band-ratio for the discrimination of watermelon seeds infected by the bacteria Acidovorax citrulli using ANOVA. Two bands at 1076.8 cm-1 and 437 cm-1 are selected as the optimal Raman peaks for the detection of bacteria-infected seeds. The results demonstrate that the Raman hyperspectral imaging technique has a good potential for the detection of bacteria-infected watermelon seeds and that it could form a suitable alternative to conventional methods.

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.