To ensure the coating quality of the port machinery,the spraying defects on the surface of the steel structure of port machinery were detected and studied in this paper.Firstly,the component spraying defect detection test is designed,and the sample data set is established;Then,combined with,the morphological features of the image,the improved Canny algorithm is applied to improve the.detection effect of feature edges.The data such as circumference,area and correlation were selected as the threshold conditions for classification,and five kinds of coating defect classification were realized.The actual results show that the proposed method can detect and identify the spray defect category more effectively.