Machine learning techniques for non-destructive estimation of plum fruit weight
2025

Estimating Plum Fruit Weight Using Machine Learning

Sample size: 1028 publication 10 minutes Evidence: high

Author Information

Author(s): Sabouri Atefeh, Bakhshipour Adel, Poorsalehi Mehrnaz, Abouzari Abouzar

Primary Institution: University of Guilan

Hypothesis

What are the most effective mathematical models for estimating plum fruit weight?

Conclusion

The study found that machine learning methods can accurately estimate the weight of plum fruits based on their dimensions.

Supporting Evidence

  • The SVR model achieved an R2 of 0.9369 during training.
  • The method allows for non-destructive weight estimation.
  • Future research can apply the model to other fruit types.
  • Image processing techniques were used to extract fruit dimensions.
  • Machine learning models were validated with data from multiple years.
  • Statistical analysis showed significant correlations between dimensions and weight.
  • The study provides a framework for mobile-based fruit weight estimation.

Takeaway

This study shows that we can use pictures of plums to guess how heavy they are without picking them off the tree.

Methodology

The study used image processing and machine learning algorithms to estimate plum fruit weight based on fruit dimensions.

Potential Biases

Potential biases may arise from the limited range of fruit varieties tested.

Limitations

Variations in natural lighting and background interference can affect image quality and accuracy.

Participant Demographics

The study focused on three greengage genotypes and one myrobalan plum genotype from northern Iran.

Statistical Information

P-Value

0.1

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1038/s41598-024-85051-2

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication