Abstract: This is an article in the field of process mineralogy. In order to solve the problem of color spot impurity sorting in high-purity mica, a sorting method of mica containing impurities based on image processing is proposed in this article. According to the state of color spot impurities of mica under different light sources, the influence of image illumination environment is studied. On this basis, the processing methods such as Gaussian filtering and Canny edge detection are studied. Finally, the image recognition and discrimination of mica ores are realized accurately, and good results are obtained in the recognition of three different types of mica ores.