Corrosion detection around rivets based on improved Otsu algorithm

An improved Otsu algorithm is proposed for corrosion detection around aircraft rivets. On the basis of the traditional Otsu algorithm, which is easy to cause the loss of some corrosion areas, the maximum between-class variance value is adjusted by adding the weight value k, and the corresponding threshold value is obtained from the relationship between the threshold value and the maximum between-class variance value, so as to realize the optimal segmentation of corrosion areas. The segmentation effect of the traditional Otsu algorithm and the improved Otsu algorithm is compared with the mean square error, and according to the corrosion condition, the corrosion degree is introduced to classify the corrosion grade. The experimental results show that the algorithm is simple to extract corrosion features around aircraft rivets, has good detection effect, and has a wide range of applications.