Non-destructive porosity mapping of fruit and vegetables using X-ray CT

Nugraha, Bayu; Verboven, Pieter; Janssen, Siem; Wang, Zi; Nicolaı̈, Bart

doi:10.1016/j.postharvbio.2018.12.016

Cited by 55 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher intensities due to higher tissue density were observed around the core. When moving from the core towards the fruit surface, the intensities first decreased and thereafter increased again closer to the surface, confirming the observed density distributions from other research (Nugraha et al, 2019). The 'defective' 'Conference' fruit (Figure 4, row a) showed regions of lower voxel intensities that were affected by internal browning (Franck et al, 2007;Lammertyn et al, 2003a;van Dael et al, 2017).…”

Section: X-ray Micro Ct Reconstructions and Labeled Datasetssupporting

confidence: 86%

“…In pome fruit, tissue of higher density can typically be observed around the core and in the surface region. In between those regions, typically a higher porosity can be found (Nugraha et al, 2019). Low-density and high-density tissue regions are thus generally always present, however, a large difference between those regions can indicate the occurrence of water loss due to internal tissue breakdown.…”

Section: Feature Extraction Algorithmmentioning

confidence: 99%

“…This might indicate that on average, the 'Cepuna' fruit have a lower density, i.e. higher porosity, than 'Conference' fruit (Nugraha et al, 2019).…”

Section: Internal Variability Must Be Measured To Separate 'Defective' From 'Healthy' Pear Fruitmentioning

confidence: 99%

See 2 more Smart Citations

Nondestructive internal quality inspection of pear fruit by X-ray CT using machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

To preserve the quality of fresh pear fruit after harvest and deliver quality fruit year-round a controlled supply chain and long-term storage are applied. During storage, however, internal disorders can develop due to suboptimal storage conditions that may not cause externally visible symptoms. This makes them impossible to be detected by current commercial quality grading systems in a reliable and non-destructive way. A combination of a Support Vector Machine coupled with a feature extraction algorithm and X-ray Computed Tomography is proposed to successfully detect internal disorders in 'Conference' and 'Cepuna' pear fruit nondestructively. Classifiers were able to distinguish defective from sound fruit with classification accuracies ranging between 90.2 and 95.1 % depending on the cultivar and number of used features. Moreover, low false positive and negative rates were obtained, respectively ranging between 0.0 and 6.7 %, and 5.7 and 13.3 %. Classifiers trained on 'Conference' data were transferred effectively to the 'Cepuna' cultivar, suggesting generalizability to other cultivars as well. With continuing developments in both hardware and software to increase inspection speed and reduce equipment costs, the method can be implemented in industrial applications, e.g., inline translational X-ray CT.

show abstract

Section: X-ray Micro Ct Reconstructions and Labeled Datasetssupporting

confidence: 86%

Section: Feature Extraction Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Nondestructive internal quality inspection of pear fruit by X-ray CT using machine learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…These outcomes indicate the need to investigate microporosity and cell size distributions simultaneously in order to understand links between fruit size and cell size. They also provide valuable input to the results obtained in previous X‐ray CT (Nugraha et al ., 2019), X‐ray microtomography (Herremans et al ., 2013) and MRI (Winisdorffer et al ., 2015a) studies on mature apple fruits, indicating that the heterogeneity of the airspace network within the mesocarp is set during the early stage of fruit development. In future work, the development of methods to assess the 3D histological structure of fruit tissues will open up new approaches to the understanding of fruit growth and quality, as suggested by Legland et al .…”

Section: Discussionmentioning

confidence: 99%

Spatial and temporal evolution of quantitative magnetic resonance imaging parameters of peach and apple fruit – relationship with biophysical and metabolic traits

et al. 2020

View full text Add to dashboard Cite

SUMMARYFruits are complex organs that are spatially regulated during development. Limited phenotyping capacity at cell and tissue levels is one of the main obstacles to our understanding of the coordinated regulation of the processes involved in fruit growth and quality. In this study, the spatial evolution of biophysical and metabolic traits of peach and apple fruit was investigated during fruit development. In parallel, the multi‐exponential relaxation times and apparent microporosity were assessed by quantitative magnetic resonance imaging (MRI). The aim was to identify the possible relationships between MRI parameters and variations in the structure and composition of fruit tissues during development so that transverse relaxation could be proposed as a biomarker for the assessment of the structural and functional evolution of fruit tissues during growth. The study provides species‐specific data on developmental and spatial variations in density, cell number and size distribution, insoluble and soluble compound accumulation and osmotic and water potential in the fruit mesocarp. Magnetic resonance imaging was able to capture tissue evolution and the development of pericarp heterogeneity by accessing information on cell expansion, water status and distribution at cell level, and microporosity. Changes in vacuole‐related transverse relaxation rates were mostly explained by cell/vacuole size. The impact of cell solute composition, microporosity and membrane permeability on relaxation times is also discussed. The results demonstrate the usefulness of MRI as a tool to phenotype fruits and to access important physiological data during development, including information on spatial variability.

show abstract

“…Therefore, it offers versatility for direct and simultaneous measurements of several constituents in seed samples [10,[14][15][16][17]. On the other hand, X-ray imaging is based on differences in X-ray attenuation in different types of tissues [18]. Hence, it can reveal the physical state of the seed, i.e., its internal morphology [5].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning for Seed Quality Classification: An Advanced Approach Using Merger Data from FT-NIR Spectroscopy and X-ray Imaging

Medeiros

Silva

Ribeiro

et al. 2020

Sensors

View full text Add to dashboard Cite

Optical sensors combined with machine learning algorithms have led to significant advances in seed science. These advances have facilitated the development of robust approaches, providing decision-making support in the seed industry related to the marketing of seed lots. In this study, a novel approach for seed quality classification is presented. We developed classifier models using Fourier transform near-infrared (FT-NIR) spectroscopy and X-ray imaging techniques to predict seed germination and vigor. A forage grass (Urochloa brizantha) was used as a model species. FT-NIR spectroscopy data and radiographic images were obtained from individual seeds, and the models were created based on the following algorithms: linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), naive Bayes (NB), and support vector machine with radial basis (SVM-r) kernel. In the germination prediction, the models individually reached an accuracy of 82% using FT-NIR data, and 90% using X-ray data. For seed vigor, the models achieved 61% and 68% accuracy using FT-NIR and X-ray data, respectively. Combining the FT-NIR and X-ray data, the performance of the classification model reached an accuracy of 85% to predict germination, and 62% for seed vigor. Overall, the models developed using both NIR spectra and X-ray imaging data in machine learning algorithms are efficient in quickly, non-destructively, and accurately identifying the capacity of seed to germinate. The use of X-ray data and the LDA algorithm showed great potential to be used as a viable alternative to assist in the quality classification of U. brizantha seeds.

show abstract

Non-destructive porosity mapping of fruit and vegetables using X-ray CT

Cited by 55 publications

References 30 publications

Nondestructive internal quality inspection of pear fruit by X-ray CT using machine learning

Nondestructive internal quality inspection of pear fruit by X-ray CT using machine learning

Spatial and temporal evolution of quantitative magnetic resonance imaging parameters of peach and apple fruit – relationship with biophysical and metabolic traits

Machine Learning for Seed Quality Classification: An Advanced Approach Using Merger Data from FT-NIR Spectroscopy and X-ray Imaging

Contact Info

Product

Resources

About