Metal corrosion damage quantitative evaluation method based on image recognition

The invention discloses a metal corrosion damage quantitative evaluation method based on image recognition. The method comprises the following steps: acquiring a corrosion image of a carrier where metal is located; acquiring image features including a damage type A, a damage area B and a damage degree C in the corrosion image and digitalizing the features; analyzing the damage type A, the damage area B and the damage degree C through a BP neural network and data statistics reverse analysis and acquiring the influence D of corrosion damage on the mechanical property, and digitalizing the influence D; and taking the damage type A, the damage area B, the damage degree C and the influence D of corrosion damage on mechanical properties as evaluation indexes, obtaining weight values omegaA, omegaB, omegaC and omegaD of each evaluation index by adopting an expert consultation method, calculating a metal corrosion damage comprehensive quantity value W according to a formula W = A omegaA + B omegaB + C omegaC + D omeg