Evaluation of machine learning in recognizing images of reinforced concrete damage

Damage to reinforced concrete (RC) facilities occurs through the process of natural deterioration. Machine learning can be employed to effectively identify various damage areas and ensure safety. The performance of machine vision methods depends on image quality. In this study, five image types (Types I-V) with combinations of image deficiencies pertaining to uniform illuminance, uneven illuminance, orthoimage, tilt angle, and image blur were used to evaluate the damage recognition capabilities of maximum likelihood (MLH), support vector machine (SVM), and random forest (RF) methods. Type I images were orthoimages with uniform illuminance, Type II images were tilted images with uniform illuminance, Type III images were orthoimages with uneven illuminance, Type IV images were tilted images with uneven illuminance, and Type V images were tilted, blurred images with uneven illuminance. MLH was most accurate (98.6%) in Type I images, and RF was the least accurate (62.8%) in Type V images. Image tilt (in Type II images) did not diminish the damage recognition capabilities of the three types of machine learning methods (mean accuracy = 97.2%). For tilted images with uneven illuminance (Type IV), a severe expansion effect was produced, reducing the mean accuracy to 70.1%. Type III images were recognized with a mean accuracy of 87.1%; uneven illuminance increased the error rate for three classes of damage. By testing various image types, the impact of image quality on the variability of machine learning recognition is understood, and the ability of automated machine learning recognition in the future is improved.