Related Experiment Video
Updated: Aug 13, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.3K
Non-Destructive Banana Ripeness Detection Using Shallow and Deep Learning: A Systematic Review
Preety Baglat1,2, Ahatsham Hayat1,2, Fábio Mendonça1,2
1University of Madeira, 9000-082 Funchal, Portugal.
Sensors (Basel, Switzerland)
|January 21, 2023
Summary
Automating banana ripeness analysis is crucial for nutrient composition and demand. This review highlights sensor cameras and color features for accurate ripeness prediction, favoring four stages and specific machine learning models.
Area of Science:
- Agricultural Science
- Computer Vision
- Food Science
Background:
- Banana ripeness significantly impacts nutrient content and market demand.
- Traditional ripeness assessment requires expert knowledge and manual labor.
- Automated methods are being developed to reduce human intervention in ripeness analysis.
Conclusions:
- Existing studies face limitations including insufficient dataset and device information, limited data availability, and underutilization of data augmentation.
- Future research should address these shortcomings and involve expert collaboration for robust ripeness prediction.
- Developing standardized datasets and capturing protocols is essential for advancing automated banana ripeness assessment.
