Introduction: Pistachio cereals are one of the most important products in the export sector. Therefore, accurate grading of pistachios is very important. By counting the number of pistachios in 100gr according to the national standard of Iran, this product is classified into three categories of large, medium and small.
Materials and methods: In this paper, the image of some pistachio cereals with different random size and shape was taken and stored in computers using the machine vision technique. Then, the image processing operations consisted of improving the pistachio images to increase the accuracy of edge detection was done. The exact calibration process was performed with a chessboard plate was conducted to extract the geometrical dimensions including the largest diameter and area. In the national standard of Iran, intact or broken pistachios are not considered to grade this product. Therefore, in this research, Fourier series method is used to extract morphological characteristics of pistachio cereals including roundness, elongation, asymmetry, triangularity and squareness using the low order descriptors. According to the results of the calibration operation, the dimensional measurement of pistachios with an average error of 0.09 mm is possible
Results & Discussion: According to the experimental results, it is possible to improve the current standard of pistachio using image processing and fourier series techniques in terms of increasing measurement speed, reducing costs, and adding the shape characteristics of pistachios to determine the amount of intact or broken pistachios.