This article proposes a method for calculating the normal direction width of cracks based on the apparent features of bridge crack image information. Firstly, the traditional image preprocessing methods are optimized based on the distribution pattern of crack image information in the histogram, extracting critical information such as crack edges and skeletons. Then, a coordinate system is established, and mathematical modeling is used to calculate the normal direction width of each point on the skeleton curve. Finally, the maximum width of the crack is obtained. The results show that the calculation accuracy of the algorithm used in this paper is 96.53%, and the average return time is 9.41 seconds, indicating high calculation accuracy and efficiency.