On-line fresh-cut lettuce quality measurement system using hyperspectral imaging

Mo, Changyeun,Kim, Giyoung,Kim, Moon S.,Lim, Jongguk,Lee, Kangjin,Lee, Wang-Hee,Cho, Byoung-Kwan Elsevier 2017 BIOSYSTEMS ENGINEERING Vol.156 No.-

<P>In this study, an online quality measurement system for detecting foreign substances on fresh-cut lettuce was developed using hyperspectral reflectance imaging. The online detection system with a single hyperspectral camera in the range of 400–1000 nm was able to detect contaminants on both surfaces of fresh-cut lettuce. Algorithms were developed for this system to detect contaminants such as slugs and worms. The optimal wavebands for discriminating between contaminants and sound lettuce as well as between contaminants and the conveyor belt were investigated using the one-way analysis of variance (ANOVA) method. The subtraction imaging (SI) algorithm to classify slugs resulted in a classification accuracy of 97.5%, sensitivity of 98.0%, and specificity of 97.0%. The ratio imaging (RI) algorithm to discriminate worms achieved classification accuracy, sensitivity, and specificity rates of 99.5%, 100.0%, and 99.0%, respectively. The overall results suggest that the online quality measurement system using hyperspectral reflectance imaging can potentially be used to simultaneously discriminate foreign substances on fresh-cut lettuces.</P> <P><B>Highlights</B></P> <P> <UL> <LI> We developed online fresh-cut lettuce quality measurement system. </LI> <LI> The online measurement system was capable to detect defects on both surfaces of fresh-cut lettuce. </LI> <LI> The multispectral imaging algorithms were developed to detect the foreign substances. </LI> <LI> The imaging algorithms for slug and worm achieved the accuracy of 97.5% and 99.5%, respectively. </LI> </UL> </P>

Determination of Germination Quality of Cucumber (Cucumis Sativus) Seed by LED-Induced Hyperspectral Reflectance Imaging

Mo, Changyeun,Lim, Jongguk,Lee, Kangjin,Kang, Sukwon,Kim, Moon S.,Kim, Giyoung,Cho, Byoung-Kwan Korean Society for Agricultural Machinery 2013 바이오시스템공학 Vol.38 No.4

Purpose: We developed a viability evaluation method for cucumber (Cucumis sativus) seed using hyperspectral reflectance imaging. Methods: Reflectance spectra of cucumber seeds in the 400 to 1000 nm range were collected from hyperspectral reflectance images obtained using blue, green, and red LED illumination. A partial least squares-discriminant analysis (PLS-DA) was developed to predict viable and non-viable seeds. Various ranges of spectra induced by four types of LEDs (Blue, Green, Red, and RGB) were investigated to develop the classification models. Results: PLS-DA models for spectra in the 600 to 700 nm range showed 98.5% discrimination accuracy for both viable and non-viable seeds. Using images based on the PLS-DA model, the discrimination accuracy for viable and non-viable seeds was 100% and 99%, respectively Conclusions: Hyperspectral reflectance images made using LED light can be used to select high quality cucumber seeds.

Hyperspectral Imaging and Partial Least Square Discriminant Analysis for Geographical Origin Discrimination of White Rice

Mo, Changyeun,Lim, Jongguk,Kwon, Sung Won,Lim, Dong Kyu,Kim, Moon S.,Kim, Giyoung,Kang, Jungsook,Kwon, Kyung-Do,Cho, Byoung-Kwan Korean Society for Agricultural Machinery 2017 바이오시스템공학 Vol.42 No.4

Purpose: This study aims to propose a method for fast geographical origin discrimination between domestic and imported rice using a visible/near-infrared (VNIR) hyperspectral imaging technique. Methods: Hyperspectral reflectance images of South Korean and Chinese rice samples were obtained in the range of 400 nm to 1000 nm. Partial least square discriminant analysis (PLS-DA) models were developed and applied to the acquired images to determine the geographical origin of the rice samples. Results: The optimal pixel dimensions and spectral pretreatment conditions for the hyperspectral images were identified to improve the discrimination accuracy. The results revealed that the highest accuracy was achieved when the hyperspectral image's pixel dimension was $3.0mm{\times}3.0mm$. Furthermore, the geographical origin discrimination models achieved a discrimination accuracy of over 99.99% upon application of a first-order derivative, second-order derivative, maximum normalization, or baseline pretreatment. Conclusions: The results demonstrated that the VNIR hyperspectral imaging technique can be used to discriminate geographical origins of rice.

Original Article Journal of Biosystems Engineering : Detecting Drought Stress in Soybean Plants Using Hyperspectral Fluorescence Imaging

( Changyeun Mo ),( Moon S. Kim ),( Giyoung Kim ),( Eun Ju Cheong ),( Jinyoung Yang ),( Jongguk Lim ) 한국농업기계학회 2015 바이오시스템공학 Vol.40 No.4

Purpose: Soybean growth is adversely affected by environmental stresses such as drought, extreme temperatures, and nutrient deficiency. The objective of this study was to develop a method for rapid measurement of drought stress in soybean plants using a hyperspectral fluorescence imaging technique. Methods: Hyperspectral fluorescence images were obtained using UV-A light with 365 nm excitation. Two soybean cultivars under drought stress were analyzed. A partial least square regression (PLSR) model was used to predict drought stress in soybeans. Results: Partial least square (PLS) images were obtained for the two soybean cultivars using the results of the developed model during the period of drought stress treatment. Analysis of the PLS images showed that the accuracy of drought stress discrimination in the two cultivars was 0.973 for an 8-day treatment group and 0.969 for a 6-day treatment group. Conclusions: These results validate the use of hyperspectral fluorescence images for assessing drought stress in soybeans.

Fluorescence hyperspectral imaging technique for foreign substance detection on fresh‐cut lettuce

Mo, Changyeun,Kim, Giyoung,Kim, Moon S,Lim, Jongguk,Cho, Hyunjeong,Barnaby, Jinyoung Yang,Cho, Byoung‐,Kwan John Wiley & Sons 2017 Journal of the Science of Food and Agriculture Vol.97 No.12

<P>CONCLUSIONThe overall results demonstrate that fluorescence HSI techniques have the potential to detect worms on fresh-cut lettuce. In the future, we will focus on developing a multi-spectral imaging system to detect foreign substances such as worms, slugs and earthworms on fresh-cut lettuce. (c) 2017 Society of Chemical Industry</P>

Hyperspectral Imaging and Partial Least Square Discriminant Analysis for Geographical Origin Discrimination of White Rice

( Changyeun Mo ),( Jongguk Lim ),( Sung Won Kwon ),( Dong Kyu Lim ),( Moon S. Kim ),( Giyoung Kim ),( Jungsook Kang ),( Kyung-do Kwon ),( Byoung-kwan Cho ) 한국농업기계학회 2017 바이오시스템공학 Vol.42 No.4

Purpose: This study aims to propose a method for fast geographical origin discrimination between domestic and imported rice using a visible/near-infrared (VNIR) hyperspectral imaging technique. Methods: Hyperspectral reflectance images of South Korean and Chinese rice samples were obtained in the range of 400 nm to 1000 nm. Partial least square discriminant analysis (PLS-DA) models were developed and applied to the acquired images to determine the geographical origin of the rice samples. Results: The optimal pixel dimensions and spectral pretreatment conditions for the hyperspectral images were identified to improve the discrimination accuracy. The results revealed that the highest accuracy was achieved when the hyperspectral image’s pixel dimension was 3.0 mm × 3.0 mm. Furthermore, the geographical origin discrimination models achieved a discrimination accuracy of over 99.99% upon application of a first-order derivative, second-order derivative, maximum normalization, or baseline pretreatment. Conclusions: The results demonstrated that the VNIR hyperspectral imaging technique can be used to discriminate geographical origins of rice.

Discrimination methods for biological contaminants in fresh-cut lettuce based on VNIR and NIR hyperspectral imaging

Mo, Changyeun,Kim, Giyoung,Kim, Moon S.,Lim, Jongguk,Lee, Seung Hyun,Lee, Hong-Seok,Cho, Byoung-Kwan Elsevier 2017 Infrared physics & technology Vol.85 No.-

<P><B>Abstract</B></P> <P>The rapid detection of biological contaminants such as worms in fresh-cut vegetables is necessary to improve the efficiency of visual inspections carried out by workers. Multispectral imaging algorithms were developed using visible-near-infrared (VNIR) and near-infrared (NIR) hyperspectral imaging (HSI) techniques to detect worms in fresh-cut lettuce. The optimal wavebands that can detect worms in fresh-cut lettuce were investigated for each type of HSI using one-way ANOVA. Worm-detection imaging algorithms for VNIR and NIR imaging exhibited prediction accuracies of 97.00% (RI<SUB>547/945</SUB>) and 100.0% (RI<SUB>1064/1176</SUB>, SI<SUB>1064-1176</SUB>, RSI-I<SUB>(1064-1173)/1064</SUB>, and RSI-II<SUB>(1064-1176)/(1064+1176)</SUB>)<SUB>,</SUB> respectively. The two HSI techniques revealed that spectral images with a pixel size of 1×1mm or 2×2mm had the best classification accuracy for worms. The results demonstrate that hyperspectral reflectance imaging techniques have the potential to detect worms in fresh-cut lettuce. Future research relating to this work will focus on a real-time sorting system for lettuce that can simultaneously detect various defects such as browning, worms, and slugs.</P> <P><B>Highlights</B></P> <P> <UL> <LI> VNIR- and NIR- HSI algorithms to detect worm on fresh-cut lettuce were developed. </LI> <LI> The optimal wavebands to discriminate worm were investigated by the one-way ANOVA. </LI> <LI> The worm detection algorithm achieved the accuracy of 100% for NIR-HSI. </LI> <LI> The best pixel size of spectral images to detect worm were 1×1 or 2×2mm. </LI> </UL> </P>

농식품 가공 시설의 오염 신속 측정에 관한 연구

모창연 ( Changyeun Mo ),김기영 ( Giyoung Kim ),김문성 ( Moon S. Kim ),황찬송 ( Chansong Hwang ),서영욱 ( Youngwook Seo ),이아영 ( Ah-yeong Lee ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.1

장출혈 대장균에 오염된 새싹채소 등으로 인한 식중독 사고 발생에 의해 고품질의 안전한 농식품에 대한 소비자의 요구가 증대되고 있으며 또한 농식품의 위해요소에 대한 국제기준 강화로 농식품 안전성 검사 수요가 증가하고 있다. 이에 농식품 생산 및 가공단계에서 농식품 안전성을 향상시키기 위해서 식품가공 공장의 안전성을 신속하게 검사할 수 있는 기술이 요구되고 있다. 따라서 본 연구에서는 분광 영상 기술을 이용하여 식품 가공시설의 오염여부를 신속하게 측정할 수 있는 기술을 개발하였다. 농식품 가공 장치의 표면 재질에 미생물 번식 가능성이 높은 오염원 검출을 위해 초분광 형광 영상 시스템을 이용하였다. 이 시스템은 365nm 파장의 UV-A 여기광, 시료 이송부, 초분광 형광 영상 획득부로 구성되어 있고 형광 영상 스펙트럼의 파장영역은 420 ~ 780 nm 이다. 측정한 형광 영상을 이용하여 토마토, 오렌지, 사과의 오염 여부를 검출할 수 있는 알고리즘을 개발하였다. 500, 660, 780 nm 파장 대역에서 토마토, 오렌지, 사과의 오염된 부분이 스테인리스 표면 재질보다 형광의 세기가 크게 나타나는 특성을 보였다. 농식품 가공 장치 표면에서 형광 분광 영상으로 20배 희석된 잔류유기물에 의한 오염부위의 검출가능성을 확인하였다.

신선편이 식품의 생물학적 이물질 신속 검출에 관한 연구

모창연 ( Changyeun Mo ),김기영 ( Giyoung Kim ),임종국 ( Jongguk Lim ),이강진 ( Kangjin Lee ),김문성 ( Moon S. Kim ) 한국농업기계학회 2017 한국농업기계학회 학술발표논문집 Vol.22 No.2

신선편이 농산물의 국내 시장규모는 매년 성장하고 있으며, 대상도 엽채류, 과채류로 확대되고 있다. 소비자들이 신선편이 농산물을 기피하는 주요 원인은 안전성 우려로 위생에 대한 불신이 존재하고 있다. 이를 해결하기 위해 신선편이 식품에 존재하는 생물학적 이물질인, 애벌레, 파리, 지렁이 등을 신속하게 검출할 수 있는 기술이 요구되고 있다. 본 연구에서는 형광 영상을 이용하여 신선편이 식품에서 생물학적 이물질을 판별할 수 있는 기술을 개발하고자 한다. 이를 위해 365 nm의 여기광을 조사하여 400~740nm 파장의 형광 영상을 측정하였다. 생물학적 이물질과 신선편이 식품을 구별하기 위한 파장 특성을 조사하였다. 그 결과 식선편이 식품은 엽록소 파장 대역인 686 nm 영역에서 생물학적 이물질보다 높게 나타나는 경향을 보였다. 이러한 형광 특성은 생물학적 이물질의 검출 가능성을 보여주었다. 본 연구는 신선편이 식품에 존재하는 이물질 뿐만 아니라 신선편이 가공시설에 존재하는 생물학적 이물질도 신속하게 검출할 수 있는 검사 장치 개발을 위한 기초 자료로 활용 가능하다.

국내 원산지별 고춧가루의 매운맛 비파괴 측정기술 개발

모창연(Changyeun Mo),이강진(Kangjin Lee),임종국(Jong-Guk Lim),강석원(Sukwon Kang),이현동(Hyun-Dong Lee),조병관(Byoung-Kwan Cho) 충남대학교 농업과학연구소 2012 농업과학연구 Vol.39 No.4

In this research, the feasibility of non-destructive measurement technique of pungency measurement was investigated for the red-pepper powders produced in different domestic areas in South Korea. The near-infrared absorption spectra in the range of 1100 nm~2300 ㎚ was used to measure capsaicinoids content in red-pepper powders by using a NIR spectroscopy equipped with Acousto-optic tunable filters (AOTF). Fourth three different red-pepper powders from 14 different locations were collected and separated in three different particle size (below 0.425 ㎜, 0.425~0.71 ㎜, 0.71~1.4 ㎜) for the spectral measurements. The partial least square regression (PLSR) models to predict the capsaicinoids content depends on particle size were developed with the measured spectra. The determinant coefficients and standard errors of the developed models for the red-pepper powders of below 0.425 ㎜, 0.425~0.71 ㎜, and 0.71~1.4 ㎜ were in the range of 0.859~0.887 and 12.90~12.99 ㎎/100 g, respectively. The PLS model with the pretreatment of Standard Normal Variate (SNV) for the red-pepper powders below 1.4 mm particle size showed the best performance with the determinant coefficient of 0.844 and the standard error of 14.63 ㎎/100 g.