This is the authors' abstract. We don't add key points for this paper.
The ripening stages (RS) of bananas are very important in consumer preferences, retail markets, exports, and the food processing industry. The ripeness of bananas is affected by various factors, including temperature, humidity, chemical composition, biochemical features, and storage conditions. In post-harvest, bananas are also susceptible to damage or deterioration in quality caused by sensitive fruit skins, packaging, transportation, and inaccuracies in classifying ripeness/maturity. This condition causes the stages of damage, ripeness, and decay of bananas to occur faster. However, in general, the determination of the ripeness level is still done manually. This has the potential to be inaccurate in classifying the level of ripeness and causing food loss. The complexity of ripeness characteristics and banana varieties adds to the challenge of classification the ripeness stages. Research related to the classification of banana ripeness based on digital images has been widely proposed, but there have been no survey literatures that have reported classification of banana ripeness of various varieties and a noticeable change in skin color during the ripening stage. This paper surveys the features of banana images for non-invasive ripeness classification and identifies characteristic challenges. Widely used methods include image data collection, image augmentation, region, color, and texture analysis, as well as machine learning and deep learning techniques for classification.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Mutrofin et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: