An automatic sorting system for fresh white button mushrooms based on image processing

摘要

White button mushrooms, one of the most commonly and widely consumed mushrooms worldwide, require grading before entering the market. The diameter of the pileus is an important factor that affects the selling price. The aim of this study is to develop an automatic sorting system for fresh white button mushrooms based on image processing according to the pileus diameter. First, an automatic sorting hardware system is designed that consists of a conveying mechanism, an image acquisition system, a control module and an actuator. Second, we present an image algorithm based on the watershed method, Canny operator, OR operation, and closed operation to determine the pileus diameter of fresh white button mushrooms. The algorithm eliminates the influence of the shadow and petiole on the image. Third, a precise control strategy is introduced based on the conveyor speed, distance between the trigger and the flap piece, trigger time and algorithm processing time. Finally, we present analysis and control software based on OpenCV 2.4.10 and Visual Studio 2010. In the experimental portion, a prototype system was tested to validate its applicability and reliability by the grading performance and results. The experimental results showed that the average maximum grading speed was 102.41 mushrooms/minute, the accuracy of grading was 97.42%, the damage rate was 0.05%, and the undetected rate was 0.96%. Relative to manual grading, the grading speed was improved by 38.86%, and the accuracy was improved by 6.84%. The system can operate stably and continuously. For long-duration grading in particular, the advantage of the automatic sorting system is apparent because it eliminates labourer fatigue. The system achieves online automatic sorting and grading of fresh white button mushrooms with minimal destruction.