The research on a method for detecting the appearance quality of de-stemmed fresh Shiitake mushrooms based on machine vision

The grading of the appearance quality of shiitake mushrooms is an important process in the mushroom production. Aiming at the problems of slow speed and strong subjectivity in manual grading, this paper proposes a method for grading the appearance quality of shiitake mushrooms based on machine vision. Shiitake mushrooms can be divided into regions such as the cap, the rolled - edge, and the gills. The geometric features of each region are the main basis for quality grading. According to the detection requirements, the key hardware of the detection system is selected first. Then, the Support Vector Machine (SVM) is used to segment the shiitake mushrooms based on color features, and the rolled - edge and gill regions are obtained. The diameter, roundness, rolled - edge thickness, and consistency of each region are quantified, and different grading standards are set according to the quantified parameters to finally achieve grading. The experimental results show that, compared with the traditional manual grading method, this method is fast, efficient, and not affected by subjectivity, with obvious advantages.