Applications of Hyperspectral Imaging Technique for Agri-food Quality and Safety

( Hoonsoo Lee ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.2

The hyperspectral imaging technique combines imaging and conventional point-based spectroscopic technique. It has been applied in various research fields such as defense, pharmaceutical, environment, remote sensing, and medical. Since the early 2000s, it has been used mainly to evaluate the quality and safety of agri-foods. The development of systems such as visible (400nm to 1000nm), near infrared (1000nm to 2500nm), fluorescence, and Raman hyperspectral imaging systems and up-to-date analysis techniques for qualitative and quantitative have enabled us to achieve powerful results for quality and safety of agri-food. Future hyperspectral imaging technique will be required to develop on-site application, which will contribute to improve agri-food safety and quality.

Determination of the total volatile basic nitrogen (TVB-N) content in pork meat using hyperspectral fluorescence imaging

Lee, Hoonsoo,Kim, Moon S.,Lee, Wang-Hee,Cho, Byoung-Kwan Elsevier 2018 Sensors and actuators. B Chemical Vol.259 No.-

<P><B>Abstract</B></P> <P>The total volatile basic nitrogen (TVB-N) content of meats is a key factor in measuring meat quality; however, conventional chemical methods for measuring TVB-N contents are time-consuming, labor-intensive, and are destructive procedures. The objective of this study is therefore to investigate the possibility of using hyperspectral fluorescence imaging techniques to determine TVB-N contents in pork meat. Thus, high-intensity light-emitting diodes at 365 nm were employed to acquire hyperspectral fluorescence images of the excitation. Prediction algorithms based on partial least squares (PLS) analysis and least squares support vector machines (LS-SVM) were developed. The coefficient of determination for the prediction data set (R<SUB>p</SUB> <SUP>2</SUP>) and the standard error of prediction (SEP) of the optimal LS-SVM model for determining the TVB-N content were 0.967 and 1.902%, respectively. This study showed that visualization of the TVB-N distribution for the optimal model was useful for the spatial interpretation of the sample, and so we could conclude that hyperspectral fluorescence imaging exhibits potential for the rapid measurement of TVB-N contents in meats.</P> <P><B>Highlights</B></P> <P> <UL> <LI> We used hyperspectral fluorescence imaging to determine TVB-N contents in pork meat. </LI> <LI> The performance of models using peaks was superior to those using full wavelengths for TVB-N content determination. </LI> <LI> Hyperspectral fluorescence imaging has the potential to replace conventional chemical methods for measuring TVB-N contents. </LI> </UL> </P>

Detection of Microplastic in Sun-Dried Salt using Spectroscopic Technique

( Hoonsoo Lee ),( Hwanjo Chung ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.2

Plastics have recently been recognized as a major contributor to marine pollution. Plastic waste coming in through various routes is broken down finely into sunlight, leading to uptake by marine organisms. Microplastics are very small plastic particles of less than 5 mm in size. Microplastics are not degraded by microorganisms, and may cause side effects such as reproductive complications, disruption of enzymatic activity, and slow growth rate of marine organisms. In particular, the microplastics contained in the sun-dried salt obtained through seawater threaten human health. Therefore, the purpose of this study is to detect microplastics in sun-dried salts using spectroscopic techniques. A total of 8 kinds of fine plastics were used, and the particle size was used for the experiment with the particle size of 1 mm or less. Spectra from samples were analyzed using near infrared spectroscopy and Raman spectroscopy. 8 samples were able to identify intrinsic spectra of near-infrared and Raman spectra, and it was determined that near-infrared and Raman spectroscopy techniques could be possible up to 1% by limit of quantitative analysis.

Non‐destructive evaluation of bacteria‐infected watermelon seeds using visible/near‐infrared hyperspectral imaging

Lee, Hoonsoo,Kim, Moon S.,Song, Yu‐,Rim,Oh, Chang‐,Sik,Lim, Hyoun‐,Sub,Lee, Wang‐,Hee,Kang, Jum‐,Soon,Cho, Byoung‐,Kwan John Wiley Sons, Ltd 2017 Journal of the Science of Food and Agriculture Vol.97 No.4

<P>BACKGROUND: There is a need to minimize economic damage by sorting infected seeds from healthy seeds before seeding. However, current methods of detecting infected seeds, such as seedling grow-out, enzyme-linked immunosorbent assays, the polymerase chain reaction (PCR) and the real-time PCR have a critical drawbacks in that they are time-consuming, labor-intensive and destructive procedures. The present study aimed to evaluate the potential of visible/near-infrared (Vis/NIR) hyperspectral imaging system for detecting bacteria-infected watermelon seeds. RESULTS: A hyperspectral Vis/NIR reflectance imaging system (spectral region of 400-1000 nm) was constructed to obtain hyperspectral reflectance images for 336 bacteria-infected watermelon seeds, which were then subjected to partial least square discriminant analysis (PLS-DA) and a least-squares support vector machine (LS-SVM) to classify bacteria-infected watermelon seeds from healthy watermelon seeds. The developed system detected bacteria-infected watermelon seeds with an accuracy > 90% (PLS-DA: 91.7%, LS-SVM: 90.5%), suggesting that the Vis/NIR hyperspectral imaging system is effective for quarantining bacteria-infected watermelon seeds. CONCLUSION: The results of the present study show that it is possible to use the Vis/NIR hyperspectral imaging system for detecting bacteria-infected watermelon seeds. (C) 2016 Society of Chemical Industry</P>

Detection of melamine in milk powder using MCT-based short-wave infrared hyperspectral imaging system

Lee, Hoonsoo,Kim, Moon S.,Lohumi, Santosh,Cho, Byoung-Kwan Informa UK (TaylorFrancis) 2018 Food additives & contaminants. Part A. Chemistry, Vol.35 No.6

<P>Extensive research has been conducted on non-destructive and rapid detection of melamine in powdered foods in the last decade. While Raman and near-infrared hyperspectral imaging techniques have been successful in terms of non-destructive and rapid measurement, they have limitations with respect to measurement time and detection capability, respectively. Therefore, the objective of this study was to develop a mercury cadmium telluride (MCT)-based short-wave infrared (SWIR) hyperspectral imaging system and algorithm to detect melamine quantitatively in milk powder. The SWIR hyperspectral imaging system consisted of a custom-designed illumination system, a SWIR hyperspectral camera, a data acquisition module and a sample transfer table. SWIR hyperspectral images were obtained for melamine-milk samples with different melamine concentrations, pure melamine and pure milk powder. Analysis of variance and the partial least squares regression method over the 1000-2500nm wavelength region were used to develop an optimal model for detection. The results showed that a melamine concentration as low as 50ppm in melamine-milk powder samples could be detected. Thus, the MCT-based SWIR hyperspectral imaging system has the potential for quantitative and qualitative detection of adulterants in powder samples.</P>

Comparison of Prediction of Crude Oil Content in Rice using FT-NIR and Raman Spectroscopy

( Hoonsoo Lee ),( Byoung-kwan Cho ) 한국농업기계학회 2012 한국농업기계학회 학술발표논문집 Vol.17 No.2

Machine Vision Technique for Rapid Measurement of Soybean Seed Vigor

Lee, Hoonsoo,Huy, Tran Quoc,Park, Eunsoo,Bae, Hyung-Jin,Baek, Insuck,Kim, Moon S.,Mo, Changyeun,Cho, Byoung-Kwan Korean Society for Agricultural Machinery 2017 바이오시스템공학 Vol.42 No.3

Purpose: Morphological properties of soybean roots are important indicators of the vigor of the seed, which determines the survival rate of the seedlings grown. The current vigor test for soybean seeds is manual measurement with the human eye. This study describes an application of a machine vision technique for rapid measurement of soybean seed vigor to replace the time-consuming and labor-intensive conventional method. Methods: A CCD camera was used to obtain color images of seeds during germination. Image processing techniques were used to obtain root segmentation. The various morphological parameters, such as primary root length, total root length, total surface area, average diameter, and branching points of roots were calculated from a root skeleton image using a customized pixel-based image processing algorithm. Results: The measurement accuracy of the machine vision system ranged from 92.6% to 98.8%, with accuracies of 96.2% for primary root length and 96.4% for total root length, compared to manual measurement. The correlation coefficient for each measurement was 0.999 with a standard error of prediction of 1.16 mm for primary root length and 0.97 mm for total root length. Conclusions: The developed machine vision system showed good performance for the morphological measurement of soybean roots. This image analysis algorithm, combined with a simple color camera, can be used as an alternative to the conventional seed vigor test method.

Applications of Hyperspectral Imaging and Convolutional Neural Networks (CNN) for Agricultural Products and Food Quality

( Hoonsoo Lee ),( Byoung-kwan Cho ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

Hyperspectral imaging techniques have been used for decades to measure the quality and safety of food. Chemometrics methods such as principal components analysis (PCA), and partial least-squares (PLS) have mainly been employed for hyperspectral imaging analysis. However, the methods do not consider the relationship between the neighboring pixel information constituting an image. The objective of this study is to identify the applicability of the convolutional neural networks (CNN) method to hyperspectral images for the assessment of food quality. We compared the accuracy of the proposed CNN-based method with that of the chemometrics method. The results revealed that the 3-D CNN-based method provided competitive results for the assessment of food quality.

Machine Vision Technique for Rapid Measurement of Soybean Seed Vigor

( Hoonsoo Lee ),( Tran Quoc Huy ),( Eunsoo Park ),( Hyung-jin Bae ),( Insuck Baek ),( Moon S Kim ),( Changyeun Mo ),( Byoung-kwan Cho ) 한국농업기계학회 2017 바이오시스템공학 Vol.42 No.3

Purpose: Morphological properties of soybean roots are important indicators of the vigor of the seed, which determines the survival rate of the seedlings grown. The current vigor test for soybean seeds is manual measurement with the human eye. This study describes an application of a machine vision technique for rapid measurement of soybean seed vigor to replace the time-consuming and labor-intensive conventional method. Methods: A CCD camera was used to obtain color images of seeds during germination. Image processing techniques were used to obtain root segmentation. The various morphological parameters, such as primary root length, total root length, total surface area, average diameter, and branching points of roots were calculated from a root skeleton image using a customized pixel-based image processing algorithm. Results: The measurement accuracy of the machine vision system ranged from 92.6% to 98.8%, with accuracies of 96.2% for primary root length and 96.4% for total root length, compared to manual measurement. The correlation coefficient for each measurement was 0.999 with a standard error of prediction of 1.16 mm for primary root length and 0.97 mm for total root length. Conclusions: The developed machine vision system showed good performance for the morphological measurement of soybean roots. This image analysis algorithm, combined with a simple color camera, can be used as an alternative to the conventional seed vigor test method.

가시광/근적외선 분광기술을 이용한 유기질 비료 내 음식물류폐기물건조분말 정성검출 모델 개발

이훈수 ( Hoonsoo Lee ),류진환 ( Jinhwan Ryu ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

유기질비료는 비료공정규격에 의한 부산물비료 중 유기질비료와 유기농업자재 중 유기질비료로 구분된다. 2019년 3월 비료관리법이 개정되기 전까지는 모든 유기질비료의 원료로 음식물류폐기물건조분말의 사용이 허용되지 않았으나 2019년 3월 개정된 비료관리법에서는 유기농업자재로 인증 받지 않은 유기질비료에는 염분 2%이하, 수분 15%이하의 음식물류폐기물건조분말을 전체원료의 30% 내에서 사용할 수 있도록 허용하였다. 하지만, 유기농업자재로 인증받기 위한 유기질비료의 원재료로는 음식물류폐기물건조분말의 사용은 금지되어 있다. 따라서 본 연구목적은 가시광/근적외선 분광기술을 이용하여 유기농업자재 중 유기질비료 내 음식물류 폐기물건조분말의 정성검출 가능성을 평가하는 것이다. 가시광/근적외선 스펙트럼은 200-1100nm 파장을 획득할 수 있는 분광기를 이용하였고, 유기질 비료 원재료와 음식물류폐기물건조분말을 0, 5, 10, 15, 20, 30, 40, 50%로 혼합하여 시료를 제조하였다. 모델 개발은 PLSR 기법을 이용하였고, 획득한 스펙트럼 데이터의 75%는 모델개발에, 나머지 25%는 모델검증에 사용하였다. 최적모델의 검출 정확도는 95.8%를 나타내어 가시광/근적외선 분광기술의 유기질 비료 내 음식물류폐기물건조분말의 혼입여부의 검출에 활용될 수 있을것으로 판단되었다.