Non-Destructive Quality Estimation Using a Machine Learning-Based Spectroscopic Approach in Kiwifruits

Tziotzios, Georgios; Pantazi, Xanthoula Eirini; Paraskevas, Charalambos; Tsitsopoulos, Christos; Valasiadis, Dimitrios; Nasiopoulou, Elpida; Michailidis, Michail; Molassiotis, Athanassios

doi:10.3390/horticulturae10030251

Cited by 3 publications

(1 citation statement)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, a destructive approach with a minimum impact on fruit physiology could provide accessibility to firmness while still preserving the fruit for further physiological analysis [42]. Although we can claim that deforming the fruit to 1% of the small thickness dimension had minimal effect on the fruit physiological responses (Figures 3 and 4), the non-destructive approach is well-defined, and concerns, among others, include the correlation of profiles in the infrared spectrum with physiological characteristics of the fruit such as firmness, SSC, DM and its biochemical traits [43].…”

Section: Discussionmentioning

confidence: 99%

Sweet Cherry Fruit Firmness Evaluation Using Compression Distance Methods

Karageorgiadou,

Rodovitou,

Nasiopoulou

et al. 2024

Horticulturae

Self Cite

View full text Add to dashboard Cite

Flesh firmness in sweet cherries is determined using the measurement of normalized deformation force, i.e., determining the required force for a distance equal to 5 or 10% of the diameter of the cherries per millimeter. However, a firmness method involving a defined distance is quite simple and suitable for easy applications. Hence, our study focuses on the impact of fruit physiology under various and fixed distances. To assess the firmness evaluation, two sweet cherry cultivars (Canada Giant and Regina) were selected and subjected to three different levels of compression distance equal to 1%, 5%, 10% of the fruit’s small thickness dimension along with a consistent compression distance of 0.16 mm. There was a strong correlation between panelists’ preferences and the fruit that had been subjected to both a 1% deformation force and a fixed distance of 0.16 mm within each cultivar. Physiological traits, membrane integrity, and the metabolome of the fruit in these categories were mostly unaffected by the control (0%), or 1%, deformation force, as shown by clustering and PCA analysis. The control and 1% deformation force groups showed similar patterns, contrary to those of the 5% and 10% deformation force groups. Given these considerations, a fixed distance of 0.16 mm and a minimal 1% deformation force possess the potential to be employed and implemented for monitoring the firmness of sweet cherries during postharvest preservation.

show abstract

Section: Discussionmentioning

confidence: 99%

Sweet Cherry Fruit Firmness Evaluation Using Compression Distance Methods

Karageorgiadou,

Rodovitou,

Nasiopoulou

et al. 2024

Horticulturae

Self Cite

View full text Add to dashboard Cite

show abstract

Predictive modeling and correlation between the sensory and physicochemical attributes in ‘Rama Forte’ astringent persimmon

Amorim,

Filho,

Garruti

et al. 2024

Scientia Horticulturae

View full text Add to dashboard Cite

The Potential for Hyperspectral Imaging and Machine Learning to Classify Internal Quality Defects in Macadamia Nuts

Farrar,

Martinez,

Jones

et al. 2024

Horticulturae

View full text Add to dashboard Cite

Tree nuts are rich in nutrients, and global production and consumption have doubled during the last decade. However, nuts have a range of quality defects that must be detected and removed during post-harvest processing. Tree nuts can develop hidden internal discoloration, and current sorting methods are prone to subjectivity and human error. Therefore, non-destructive, real-time methods to evaluate internal nut quality are needed. This study explored the potential for VNIR (400–1000 nm) hyperspectral imaging to classify brown center disorder in macadamias. This study compared the accuracy of classifiers developed using images of kernels imaged in face-up and face-down orientations. Classification accuracy was excellent using face-up (>97.9%) and face-down (>94%) images using ensemble and linear discriminate models before and after wavelength selection. Combining images to form a pooled dataset also provided high accuracy (>90%) using artificial neural network and support vector machine models. Overall, HSI has great potential for commercial application in nut processing to detect internal brown centers using images of the outside kernel surface in the VNIR range. This technology will allow rapid and non-destructive evaluation of intact nut products that can then be marketed as a high-quality, defect-free product, compared with traditional methods that rely heavily on representative sub-sampling.

show abstract

Non-Destructive Quality Estimation Using a Machine Learning-Based Spectroscopic Approach in Kiwifruits

Cited by 3 publications

References 52 publications

Sweet Cherry Fruit Firmness Evaluation Using Compression Distance Methods

Sweet Cherry Fruit Firmness Evaluation Using Compression Distance Methods

Predictive modeling and correlation between the sensory and physicochemical attributes in ‘Rama Forte’ astringent persimmon

The Potential for Hyperspectral Imaging and Machine Learning to Classify Internal Quality Defects in Macadamia Nuts

Contact Info

Product

Resources

About