Online Variety Discrimination of Rice Seeds Using Multispectral Imaging and Chemometric Methods

Liu, W.; Liu, Ch.; Ma, Fanyuan; Lu, Xingyu; Yang, Jian‐Bo; Zheng, Liping

doi:10.1007/s10812-016-0217-1

Cited by 27 publications

(22 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the detections of vitality and vigor for seeds of oat [17], muskmelon [18], soybean [19,20] and watermelon [21] were developed with the HSI technique. Previous studies have shown the potential of using HSI coupled with multivariate data analysis for the detection of internal conditions of rice seeds, such as origin [22], variety [23,24,25], nitrogen content [26], moisture content [27] and heavy metal concentration [28]. To the best of our knowledge, many studies were conducted only for vitality detection of artificially aged seed, and, so far, no study has been carried out to detect the vitality of rice seeds under natural ageing conditions by using HSI, even though the results obtained from natural ageing seeds were more consistent with the actual situation.…”

Section: Introductionmentioning

confidence: 99%

Rapid and Nondestructive Measurement of Rice Seed Vitality of Different Years Using Near-Infrared Hyperspectral Imaging

Feng

Sun

et al. 2019

Molecules

View full text Add to dashboard Cite

Seed vitality is one of the primary determinants of high yield that directly affects the performance of seedling emergence and plant growth. However, seed vitality may be lost during storage because of unfavorable conditions, such as high moisture content and temperatures. It is therefore vital for seed companies as well as farmers to test and determine seed vitality to avoid losses of any kind before sowing. In this study, near-infrared hyperspectral imaging (NIR-HSI) combined with multiple data preprocessing methods and classification models was applied to identify the vitality of rice seeds. A total of 2400 seeds of three different years: 2015, 2016 and 2017, were evaluated. The experimental results show that the NIR-HSI technique has great potential for identifying vitality and vigor of rice seeds. When detecting the seed vitality of the three different years, the extreme learning machine model with Savitzky–Golay preprocessing could achieve a high classification accuracy of 93.67% by spectral data from only eight wavebands (992, 1012, 1119, 1167, 1305, 1402, 1629 and 1649 nm), which could be developed for a fast and cost-effective seed-sorting system for industrial online application. When identifying non-viable seeds from viable seeds of different years, the least squares support vector machine model coupled with raw data and selected wavelengths of 968, 988, 1204, 1301, 1409, 1463, 1629, 1646 and 1659 nm achieved better classification performance (94.38% accuracy), and could be adopted as an optimal combination to identify non-viable seeds from viable seeds.

show abstract

Section: Introductionmentioning

confidence: 99%

Rapid and Nondestructive Measurement of Rice Seed Vitality of Different Years Using Near-Infrared Hyperspectral Imaging

Feng

Sun

et al. 2019

Molecules

View full text Add to dashboard Cite

show abstract

“…Also, the prediction of castor seed viability by using normalized canonical discriminant analysis (nCDA) resulted in a 96% classification accuracy, and it confirmed the feasibility to apply multispectral technology in seed viability testing (Olesen and others ). To classify rice and soybean seeds according to their varieties and genetic origins, LS‐SVM and BPNN models showed better performance (over 94%) than PLSDA models (Liu and others , , ). Additionally, multispectral imaging systems, combined with Fisher linear discriminant analysis (FLDA) and library support vector machine (Lib‐SVM), were used for nondestructive variety discrimination of 3 varieties of pears and 5 categories of teas.…”

Section: Determination Of Quality Parameters Of Plant Foodsmentioning

confidence: 96%

Multispectral Imaging for Plant Food Quality Analysis and Visualization

Sun

2018

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

The multispectral imaging technique is considered a reformation of hyperspectral imaging. It can be employed to noninvasively and rapidly evaluate food quality. Even though several imaging or sensor‐based techniques have been conducted for the quality assessment of various food products, the rise of multispectral imaging has been more promising. This paper presents a comprehensive review of the use of the multispectral sensor in the quality assessment of plant foods (such as cereals, legumes, tubers, fruits, and vegetables). Different quality parameters (such as physicochemical and microbiological aspects) of plant‐based foods that were determined and visualized by the combination of modeling methods and feature wavelength selection approaches are summarized. Based on the literature, the most frequently used wavelength selection methods are the successive projection algorithm (SPA) and the regression coefficient (RC). The most effective models developed for analyzing plant food products are the partial least squares regression (PLSR), least square support vector machine (LS‐SVM), support vector machine (SVM), partial least squares discriminant analysis (PLSDA), and multiple linear regression (MLR). This article concludes with a discussion of challenges, potential uses, and future trends of this flourishing technique that is now also being applied to plant foods.

show abstract

“…3. (3)(4)(5)(6) зависимости коэффициентов диффузного отражения (1,3,5) и пропускания (2,4,6) от длины волны при учете отражения от внешней стенки кюветы (3,4) и без него (5,6) . Данную ве-личину можно рассматривать как свидетельство хоро-шего согласия с экспериментом, учитывая то, что все дополнительные параметры были определены в облас-ти прозрачности красителя.…”

Section: моделирование спектральных зависимостейunclassified

“…Исследованные в настоящей работы эффекты мо-гут возникать в большом количестве приложений, включающих исследование оптических свойств тка-ней растительных [3,4] и животных организмов in vitro [6][7][8][9]11]. Как следует из полученных результатов, их учёт является принципиально важным, особенно при решении обратных задач построения спектраль-ных зависимостей показателей поглощения и рассея-ния на основе данных эксперимента.…”

Section: обсуждение результатовunclassified

“…К наиболее важным применениям данной группы методов отно-сятся идентификация подлинности документов [1], определение качества продуктов питания [2], семян [3] и листьев [4], оценка концентрации биологически активных веществ в крови [5] и новообразований зло-качественного характера в организмах [6 -10]. Мож-но выделить две основных стратегии при решении подобных задач:…”

Section: Introductionunclassified

See 1 more Smart Citation

Peculiarities of spectral measurements of colored suspensions in thick-walled cuvettes

Nel’ubina¹,

Pidgirny²,

Bulgakova³

et al. 2016

Computer Optics

View full text Add to dashboard Cite

The cuvette wall and sample thickness can significantly affect the results of spectral measurements of the suspension in a hardly predictable manner. We propose an approach to accounting for the cuvette wall thickness in the limiting case of thick walls and a thin sample layer when calculating the diffuse reflectance and transmittance using a one-dimensional radiative transport equation. The comparison with the experimental results for a model colored suspension is made. It is shown that with the cuvette wall influence taken into account it becomes possible to account for the fact that the scattered light fails to fully fit within the integrating sphere. There is good agreement between the experimental and calculated spectra provided that the scattering anisotropy factor is predetermined in a wavelength range where the pigment used does not absorb light.

show abstract

Online Variety Discrimination of Rice Seeds Using Multispectral Imaging and Chemometric Methods

Cited by 27 publications

References 17 publications

Rapid and Nondestructive Measurement of Rice Seed Vitality of Different Years Using Near-Infrared Hyperspectral Imaging

Rapid and Nondestructive Measurement of Rice Seed Vitality of Different Years Using Near-Infrared Hyperspectral Imaging

Multispectral Imaging for Plant Food Quality Analysis and Visualization

Peculiarities of spectral measurements of colored suspensions in thick-walled cuvettes

Contact Info

Product

Resources

About