In recent years, the global new crown pneumonia epidemic has accelerated the online sales of fresh products, and nondestructive testing technology has been widely applied to the design of mango grading and inspection systems. Due to the fast detection efficiency and high automation of nondestructive testing technology, it has become an important tool for the research of mango sorting technology. For this reason, this paper proposes to introduce machine vision technology to the design of high-quality mango sorting machine, using filtering and edge detection technology of images, which extracts the dimensional characteristics of mangoes and combines with weighing and sorting to effectively improve the efficiency and accuracy of sorting. After testing experiments on the sorting machine, the results show that: the adoption of mango size, weight, color and shape detection method based on machine vision technology can effectively improve the accuracy of mango sorting, which is an important reference for the optimal design of the sorting machine.