Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques

Munera, Sandra; Gómez-Sanchís, Juan; Vila‐Francés, Joan; Colelli, G.; Cubero, Sergio; Soler, Esteban; Blasco, José

doi:10.1016/j.postharvbio.2020.111356

Cited by 50 publications

(27 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result gave a good performance with the accuracy of up to 99.24% for the ensemble classifiers. These findings are in good agreement with those of Munera et al [ 53 ] who reported an overall accuracy of up to 97.5% in classifying the healthy and defective pixels in hyperspectral images of loquat fruits using the manual ROI selection method.…”

Section: Resultssupporting

confidence: 92%

“…Thus, this NIR reflectance difference for healthy and infested samples shows the potential to be applied for the binary classification. As reported by several authors [ 26 , 52 , 53 ], the absorbance of defective samples was higher than the healthy ones due to the cellular structure difference. As a result of plant tissue infestation, there will be biochemical, tissue structure, and pigment composition changes, leading to the different spectral signatures [ 54 ].…”

Section: Resultsmentioning

confidence: 63%

See 1 more Smart Citation

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection

Ekramirad

Khaled

Doyle

et al. 2021

Foods

View full text Add to dashboard Cite

Codling moth (CM) (Cydia pomonella L.), a devastating pest, creates a serious issue for apple production and marketing in apple-producing countries. Therefore, effective nondestructive early detection of external and internal defects in CM-infested apples could remarkably prevent postharvest losses and improve the quality of the final product. In this study, near-infrared (NIR) hyperspectral reflectance imaging in the wavelength range of 900–1700 nm was applied to detect CM infestation at the pixel level for three organic apple cultivars, namely Gala, Fuji and Granny Smith. An effective region of interest (ROI) acquisition procedure along with different machine learning and data processing methods were used to build robust and high accuracy classification models. Optimal wavelength selection was implemented using sequential stepwise selection methods to build multispectral imaging models for fast and effective classification purposes. The results showed that the infested and healthy samples were classified at pixel level with up to 97.4% total accuracy for validation dataset using a gradient tree boosting (GTB) ensemble classifier, among others. The feature selection algorithm obtained a maximum accuracy of 91.6% with only 22 selected wavelengths. These findings indicate the high potential of NIR hyperspectral imaging (HSI) in detecting and classifying latent CM infestation in apples of different cultivars.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Resultsmentioning

confidence: 63%

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection

Ekramirad

Khaled

Doyle

et al. 2021

Foods

View full text Add to dashboard Cite

show abstract

“…The hyperspectral imaging system used in this work was previously described in Munera et al [15]. It consisted of an industrial camera (CoolSNAP ES, Photometrics, Tucson, AZ, USA), coupled to two liquid-crystal tuneable filters (Varispec VIS-07 and NIR-07, Cambridge Research & Instrumentation, Inc., Hopkinton, MA, USA).…”

Section: Image Acquisitionmentioning

confidence: 99%

“…This technique has demonstrated the ability to detect mechanical damage in fruit and vegetables such as citrus fruit [7], apples [8,9], peaches [10,11], pears [12], mangos [13], blueberries [14], loquats [15] or potatoes [16,17]. Regarding persimmon fruit, hyperspectral imaging has been studied as a mean to assess the internal quality such as firmness, soluble solids content and maturity [1,18] or astringency [19].…”

Section: Introductionmentioning

confidence: 99%

Detection of Invisible Damages in ‘Rojo Brillante’ Persimmon Fruit at Different Stages Using Hyperspectral Imaging and Chemometrics

Munera

Rodríguez-Ortega

Cubero

et al. 2021

Foods

Self Cite

View full text Add to dashboard Cite

The main cause of flesh browning in ‘Rojo Brillante’ persimmon fruit is mechanical damage caused during harvesting and packing. Innovation and research on nondestructive techniques to detect this phenomenon in the packing lines are necessary because this type of alteration is often only seen when the final consumer peels the fruit. In this work, we have studied the application of hyperspectral imaging in the range of 450–1040 nm to detect mechanical damage without any external symptoms. The fruit was damaged in a controlled manner. Later, images were acquired before and at 0, 1, 2 and 3 days after damage induction. First, the spectral data captured from the images were analysed through an algorithm based on principal component analysis (PCA). The aim was to automatically separate intact and damaged fruit, and to detect the damage in the PC images when present. With this algorithm, 90.0% of intact fruit and 90.8% of damaged fruit were correctly detected. A model based on partial least squares—discriminant analysis (PLS-DA), was later calibrated using the mean spectrum of the pixels detected as damaged, to determine the moment when the fruit was damaged. The model differentiated fruit corresponding correctly to 0, 1, 2 and 3 days after damage induction, achieving a total accuracy of 99.4%.

show abstract

“…normality) about the distribution of soil properties (Hastie et al, 2009). In recent years, machine learning (ML) techniques have been widely applied in soil science fields (Munera et al, 2021). ML is a collection of algorithms or techniques that can identify patterns in a data set and make predictions based on those patterns.…”

Section: Introductionmentioning

confidence: 99%

A comparison of machine learning algorithms for mapping soil iron parameters indicative of pedogenic processes by hyperspectral imaging of intact soil profiles

Zhao

Wang

et al. 2021

European J Soil Science

View full text Add to dashboard Cite

Soil iron (Fe) performs vital functions in the biogeochemical cycles of soil environments. The amount and profile allocation of various Fe parameters can be used as sensitive indicators of soil development and pedogenic processes. This study aimed to evaluate the potential of ground‐based hyperspectral imaging (HSI: 400–1010 nm) spectroscopy to predict and map six Fe parameters indicative of pedogenic processes: total Fe (Fet), dithionite‐citrate‐bicarbonate (DCB)‐extracted Fe (Fed), oxalate‐extracted Fe (Feo), weathering index (FeW), active ratio (FeA) and crystallinity ratio (FeC). In total, 17 intact soil profiles at a depth of 100 ± 5 cm were collected to acquire HSI images. Four non‐linear machine learning techniques, namely, random forest (RF), XGBoost, CatBoost and support vector machine regression (SVMR), were implemented and compared with linear partial least squares (PLS) to identify the models with the best performance for different soil Fe parameters. Our results indicate that the four non‐linear machine learning models outperformed PLS for most soil Fe parameters, with low root mean square error (RMSE) and high Lin's concordance correlation coefficient (LCCC) values. Based on the testing set, SVMR showed better performance over the other tested models for Fet (RMSEP = 2.645 g kg−1, LCCCP = 0.89), Fed (RMSEP = 0.972 g kg−1, LCCCP = 0.97), Feo (RMSEP = 0.273 g kg−1, LCCCP = 0.97), FeW (RMSEP = 0.035, LCCCP = 0.97), FeA (RMSEP = 0.033, LCCCP = 0.97) and FeC (RMSEP = 0.031, LCCCP = 0.97). According to the LCCCP values, soil Fet was predicted to be in substantial agreement by SVMR, and the other soil Fe predictions were considered to be in near perfect agreement. Moreover, SVMR required lower computational costs. Given these results, the combination of HSI spectroscopy and SVMR is recommended due to its more reliable estimation and profile mapping of the selected soil Fe parameters than that of PLS, RF, XGBoost and CatBoost. Highlights Hyperspectral imaging was used to map six soil Fe parameters of intact profiles. Nonlinear machine learning models were compared to select the most suitable model. Nonlinear techniques outperformed the linear PLS model in most cases. SVMR showed higher comprehensive performance than other models. Hyperspectral imaging combined with SVMR is recommended to map soil Fe in profiles.

show abstract

Discrimination of common defects in loquat fruit cv. ‘Algerie’ using hyperspectral imaging and machine learning techniques

Cited by 50 publications

References 30 publications

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection

Nondestructive Detection of Codling Moth Infestation in Apples Using Pixel-Based NIR Hyperspectral Imaging with Machine Learning and Feature Selection

Detection of Invisible Damages in ‘Rojo Brillante’ Persimmon Fruit at Different Stages Using Hyperspectral Imaging and Chemometrics

A comparison of machine learning algorithms for mapping soil iron parameters indicative of pedogenic processes by hyperspectral imaging of intact soil profiles

Contact Info

Product

Resources

About