“…The proposed methods are evaluated on three datasets, CFD (Shi et al., ), Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) (Amhaz et al., ), and Customized Field Test Dataset (CFTD). In CFD, MSMP‐CAOPF increases the Boundary F1 (BF) score of state‐of‐the‐art crack detection algorithms by 2.71% over Probabilistic Generative Model (PGM)‐SVM (Ai et al., ), by 14.2% over Multi‐scale Fusion Crack Detection (MFCD) (Li et al., ), and outperforms the other recent crack detection algorithms, such as CrackForest (Shi et al., ), ConvNet (Zhang et al., ), and CrackIT (Oliveira & Correia, ) by an average of 34.2%. In TRIMMD, MSMP‐CAOPF increases the BF score by an average of 2.6% over state‐of‐the‐art algorithms including MFCD and MPS (Amhaz et al., ), and outperforms the other recent crack detection algorithms, that is, 21.7% over CrackIT.…”