Recognition of rust grade and rust ratio of steel structures based on ensembled convolutional neural network

Ensembled convolutional neural network (ECNN) was utilized to recognize the rust grade and rust ratio of steel structure to partially replace traditional visual inspection. The performance of ECNN was demonstrated by theoretical analysis and experimental verification, and the application scenarios of ECNN in the task of rust grade recognition and rust ratio recognition were discussed. The accuracy of ECNN classifier reached 93%, which improves upon the highest accuracy of 90% achieved by using a single classifier. By visualizing the misclassified images, it was found that the rust grade of misclassified image is indistinguishable and the classifiers show strong fault tolerance. The ensembled model is more robust than the single model in the task of rust ratio recognition. Gaussian blur was applied to the test images to study the effect of image blur on model performance, and the results show that the rust segmentation model was not susceptible to image blur.