A Novel Approach for Detection of Pavement Crack and Sealed Crack Using Image Processing and Salp Swarm Algorithm Optimized Machine Learning

During the phase of periodic survey, sealed crack and in asphalt pavement surface should be detected accurately. Moreover, capability identifying these two defects can help reduce false-positive rate for detection. Because are both line-based may resemble each other shape, this study puts forward an innovative method based on computer vision detecting crack. This is integration feature extraction image processing metaheuristic optimized machine learning. Image used to compute features that characterize visual appearance texture image. Subsequently, Salp Swarm Algorithm integrated with multiclass support vector employed pattern recognition. Based experimental results, newly developed has achieved most desired predictive performance accuracy = 91.33% detection 92.83%