Answers are grounded in this paper and cite their sources.
Mango (Mangifera Indica L.) sorting is the most desired expertise in the evaluation of automatic mango grading systems. Traditionally, Naked eye observation is used to assess the quality of mango. Hence, there is a need to automate grading process. Image processing and machine learning provide one alternative for an automated, non-destructive and cost-effective grading. In this paper, proposed methodology is divided in two halves: First part discusses selecting healthy mangoes and then classifying it into ripe and unripe category. Second part talks about grading mangoes based on its size. The image database is used to analyze performance of CIELab colour space and to find colour ranges for different regions of mango. CIELab colour model with Dominant density range method is used for colour feature extraction which easily discriminate colour and classify healthy and diseased mangoes. Same method is used to classify Healthy mangoes in ripe and unripe category. Rest of work is devoted for size measure evaluation using fuzzy expert system for grading of mango. Size feature is calculated using ellipse properties in order to classify in different grades. At final stage, size feature is fed to fuzzy expert system for grading. Integration of whole system results 97.47% average accuracy.
No takes yet. Share an insight, caveat, or question.
Pandey et al. (2014) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: