Non-destructive detection of blackspot in potatoes by Vis-NIR and SWIR hyperspectral imaging

López-Maestresalas, Ainara; Keresztes, Janos; Goodarzi, Mohammad; Arazuri, Silvia; Jarén, Carmen; Saeys, Wouter

doi:10.1016/j.foodcont.2016.06.001

Cited by 99 publications

(39 citation statements)

References 51 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The model performance of LS-SVM was significantly better than PLS, RPD was improved from 1.700 of CARS-PLS model to 1.978 of CARS-LS-SVM. In the similar study on the water content prediction of purple-fleshed sweet potato tuber slices [23], both R 2 c and R 2 p of PLS model reached 0.9, which were better than the prediction model in this study. The possible reason was that Sun et al [24] explored the water content during drying process, and the gradient of water content was large.…”

Section: Regression Models For Color Predictionsupporting

confidence: 43%

“…These studies all showed the feasibility of characterizing water content and chromaticity by HSI. As for the quality assessment of potatoes, HSI has been used in the following studies: prediction of pigment content in purple-fleshed sweet potato tuber slices [15], sugar content detection [16], determination of starch content [17], prediction of starch, soluble sugars and amino acids [18], identification of sliced organic potatoes [19], prediction of sprouting potato eyes [20], evaluation of optimal cooking time for boiled potatoes [21], classification of defective potatoes [22], as well as detection of blackspot [23]. Moreover, Sun et al [24] utilized HSI to predict the moisture content and freezable water content of purple-fleshed sweet potato slices during drying process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

Xiao

Bai

2020

Foods

View full text Add to dashboard Cite

Color index and water content are important indicators for evaluating the quality of fresh-cut potato tuber slices. In this study, hyperspectral imaging combined with multivariate analysis was used to detect the color parameters (L*, a*, b*, Browning index (BI), L*/b*) and water content of fresh-cut potato tuber slices. The successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to extract characteristic wavelengths, partial least squares (PLS) and least squares support vector machine (LS-SVM) were utilized to establish regression models. For color prediction, R2c, R2p and RPD of all the LSSVM models established for the five color indicators L*, a*, b*, BI, L*/b* were exceeding 0.90, 0.84 and 2.1, respectively. For water content prediction, R2c, R2p, and RPD of the LSSVM models were over 0.80, 0.77 and 1.9, respectively. LS-SVM model based on full spectra was used to reappear the spatial distribution of color and water content in fresh-cut potato tuber slices by pseudo-color imaging since it performed best in most cases. The results illustrated that hyperspectral imaging could be an effective method for color and water content prediction, which could provide solid theoretical basis for subsequent grading and processing of fresh-cut potato tuber slices.

show abstract

Section: Regression Models For Color Predictionsupporting

confidence: 43%

Section: Introductionmentioning

confidence: 99%

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

Xiao

Bai

2020

Foods

View full text Add to dashboard Cite

show abstract

“…The acquired hyperspectral image provides a spectral image for each spectral band and a spectral curve for each pixel in the image in a three‐dimension form called a “hypercube”; therefore, hyperspectral imaging technology is more reliable than traditional machine vision or spectroscopy techniques in analyzing the characteristics of objects . Currently, hyperspectral imaging technology is widely used in the quality inspection of agricultural products such as identification of hidden bruises on kiwi fruit, internal injury in almond nuts, common defects in jujube, and black spots in potatoes . An increasing amount of research on the detection of different types of apple bruises or diseases using hyperspectral imaging technology has also been reported .…”

Section: Introductionmentioning

confidence: 99%

“…11 Currently, hyperspectral imaging technology is widely used in the quality inspection of agricultural products such as identification of hidden bruises on kiwi fruit, 12 internal injury in almond nuts, 13 common defects in jujube, 14 and black spots in potatoes. 15 An increasing amount of research on the detection of different types of apple bruises or diseases using hyperspectral imaging technology has also been reported. 16,17 Gamal Elmasry et al 1 used hyperspectral imaging technology (400-1000 nm) to detect the early bruising of "McIntosh" apples.…”

mentioning

confidence: 99%

The feasibility of early detection and grading of apple bruises using hyperspectral imaging

Tan

Sun

Yang

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

The ability to determine if an apple is bruised and to provide quantitative and objective descriptions of the degree of bruising is not the only important basis for assessing apple quality but also has significance for improving the postharvest handling of apples. In this study, segmented principal component analysis for hyperspectral images in the spectral range of 401 to 1037 nm was carried out, and seven characteristic wavelengths were selected based on the weight coefficients of the principal component images. By using the principal component analysis operations with the selected wavelengths and image processing methods, an accurate recognition algorithm for apple bruises was proposed. For 40 intact samples and 160 bruised samples, the average correct recognition rate was 99.1%. Moreover, this paper obtained the average spectra of 157 segmented bruised regions by applying a binary mask. A characteristic wavelength selection method that combines competitive adaptive reweighted sampling with correlation coefficient methods and supports vector machine modeling methods based on grid parameter optimization was put forward for the classification and identification of the bruising degrees of apples. The results showed that the classification accuracy was as high as 97.5% for the test set. Overall, this study demonstrated that hyperspectral imaging technology can be used to accurately and effectively identify early bruises and determine the bruising degree of apples, which provides a new method for on‐line, nondestructive detection, and grading of early bruises in apples.

show abstract

“…Studies have determined the chemical and physical mechanisms that underly the development of black spots, have classified the mechanical damage that results in BSD, and have determined the factors that make potato susceptible to this physiological disorder. Recent studies have determined that a tuber with a small spot can be accurately and effectively identified by hyper‐spectral imaging. Other studies have aimed to predict the formation of BSD in potato tubers based on features such as enzymatic darkening of tubers, natural losses during storage, concentration of metabolites under the peel of tubers, impact of dry matter, starch content and specific gravity, energy and type of impact, and thickness, flexibility, size and degree of hydration of cell structures .…”

Section: Introductionmentioning

confidence: 99%

Reconditioning and weather conditions affect black spot damage during storage of potato (Solanum tuberosum L.) tubers

Grudzińska

Mańkowski

2019

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUND In potatoes (Solanum tuberosum L.), mechanical damage can cause the formation of black spots in the tuber flesh as the result of oxidation of phenolic compounds. This damage can result in substantial economic losses and degradation of quality. External factors contributing to the formation and the prevention of black spot damage (BSD) are not fully understood. The aim of this study was to determine the effect of weather conditions, using a hydrothermal coefficient, and of two potato tuber reconditioning methods on the formation of BSD. Five potato varieties were divided into high, moderate and low BSD susceptibility groups. The research was carried out over two growing seasons that differed greatly in precipitation and temperature. The black spot index was determined immediately after harvest and after 3 and 7 months of storage. Two reconditioning methods, applied for 7 days at 8 °C and for 7 days at 15 °C, were used for each variety. RESULTS The incidence of BSD in susceptible varieties did not depend significantly on weather conditions, although statistically significant variation was observed. We found a correlation between the hydrothermal coefficient (dry conditions) and BSD in the Etiuda variety. There was no significant effect of storage time and temperature on BSD incidence in susceptible or moderately susceptible varieties. The reconditioning methods significantly reduced the formation of BSD in tubers after storage in all three groups. Regardless of the level of susceptibility of the variety, storage time and storage temperature, the most efficient treatment to limit BSD was reconditioning for 7 days at 15 °C. CONCLUSION Identification of the significant effects of weather, and strong reduction of BSD in tubers that had been reconditioned, allows examination of the underlying mechanisms. The described reconditioning method can lead to satisfactory reduction of BSD in potato tubers. Data from this research will be of interest to potato breeders, particularly if valuable alleles that affect this phenomeon can be isolated. © 2019 Society of Chemical Industry

show abstract

Non-destructive detection of blackspot in potatoes by Vis-NIR and SWIR hyperspectral imaging

Cited by 99 publications

References 51 publications

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

The feasibility of early detection and grading of apple bruises using hyperspectral imaging

Reconditioning and weather conditions affect black spot damage during storage of potato (Solanum tuberosum L.) tubers

Contact Info

Product

Resources

About