Date grading using rule-based fuzzy inference system

Date grading is an important process for producers and affects the fruit quality evaluation and export market. However, the high costs, low speed and variation associated with manual sorting have been forcing the post harvest industry to apply mechanization and automation in sorting operations. As a step toward mechanized grading, in this research Mamdani fuzzy inference system was applied as a decision making technique to classify the Mozafati dates. Three date quality parameters including the quantity of juice, size and freshness were measured for 100 date fruits in one orchard. These dates were graded by both a human expert and a fuzzy inference system designed for this purpose. Grading results obtained from fuzzy system showed 86% general conformity with the results from the human expert.