Evaluates AI-based image classification for fruit grading in mini pumpkins, indicating potential for improved market quality.
The mini pumpkin (Cucurbita maxima × Cucurbita moschata) has gained increasing amounts of attention in fresh produce markets owing to its high sugar content and suitability for single-serving consumption.Efficient and objective fruit grading is essential for maintaining consistent market quality in commercial production systems.This study evaluated the performance of an artificialintelligence (AI)-based image classification model for the automated grading of mini pumpkins and investigated the relationships between external fruit traits and internal quality attributes.A total of 6,800 RGB images of mini pumpkins were collected and classified as marketable or immature fruits.A deep-learning model based on the ConvNeXt V2 architecture was trained and evaluated to classify mini pumpkin images.Additionally, morphological and physicochemical properties, in this case the fruit size, rind and flesh color, soluble solids content (SSC), and firmness, were measured to analyze the differences in fruit quality characteristics between the two fruit classes.Pearson's correlation analysis was conducted to examine the relationships between external and internal fruit traits.The AI-based classification model achieved high overall accuracy of 99.0%, with F1-scores of 0.991 for both fruit classes.Marketable fruits showed significantly lower rind lightness (L*) and higher fruit weights, SSC values, and firmness levels relative to those of immature fruits.A correlation analysis revealed that darker rind color was associated with greater values for fruit weight, SSC, and firmness, indicating that external visual characteristics were associated with internal fruit quality attributes.Overall, the AI-based image analysis effectively classified mini pumpkin maturity and marketability based on external fruit characteristics.This approach provides a promising non-destructive method for automated fruit grading and quality evaluations in commercial pumpkin production systems.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: