“…Whilst the latter is time-consuming and not suitable for quantitative analysis, image analysis-based detection techniques, on the other hand, can be quite challenging and fully dependent on the quality of images taken under different real-world situations (e.g., light, shadow, noise, etc.). In recent years, researchers have experimented with the application of a number of soft computing and machine learning-based detection techniques as an attempt to increase the level of automation of asset condition inspection [13,14,15,16,17,18,19,20]. The notable efforts include; structural health monitoring with Bayesian method [13], surface crack estimation using Gaussian regression, support vector machines (SVM), and neural networks [14], SVM for wall defects recognition [15], crack-detection on concrete surfaces using deep belief networks (DBN) [16], crack detection in oak flooring using ensemble methods of random forests (RF) [17], deterioration assessment using fuzzy logic [18], defect detection of ashlar masonry walls using logistic regression [19,20].…”