Fuzzy logic was applied as a decision support system to grade Golden Delicious apples. Such features as color, and size are measured through a data acquisition system consisting of an apple sorter, illumination chamber, webcam and a PC. In total 250 apples were selected for the test. The selected apples were graded by human experts based on their color and size. Five different sets or grades ranging from very low quality, to very high, were produced. In order to find the performance of proposed fuzzy inference system (FIS) the same sets of fruits were fed to the Fuzzy expert system. For input (color and size) and output (apple grade) fuzzy linguistic variables of the FIS, triangular and trapezoidal membership functions were selected. Totally, 125 rules with logical AND operator, Mamdani implication, and Center of maximum method for defuzzification were employed to develop an efficient fuzzy expert system for decision making concerning apples’ grades. The algorithm is implemented in Visual Basic 6 programming language in 1825 lines of program. The developed VB program can automatically capture image of each apple and extract its RGB color and size features. The software generates all the 125 rules by comparing these features with the reference input. The rules are then exported to Matlab’s for further investigation concerning the precision of algorithm. These tests were conducted on a two way system i.e. off-line and on-line. Grading results obtained from the developed FIS scheme shows 91.2%, and 95.2% agreement for off-line and on-line methods, respectively, as compared with the results obtainted through human expert. These show the good correlation between the results obtained from the FIS and human expert tests. Therefore, based on these results the automatic apple sorter can be designed and developed
)