IndexEdge DetectionImage CollectionImage SegmentationFactors Affecting the Quality of Concrete SurfacesMedian filter algorithms also have some limitations. Hwang and Haddad et al. (1995) indicated that the median filter works quite well, but falters when the probability of impulsive noise becomes high. In their study, the median filter algorithm was used in the second selection stage to remove influence points and patterns. Due to the method used in the first selection, the R value may be modified to reduce the influence points and models. Therefore, the median filter algorithm could greatly reduce the influence points and patterns in their study. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an original essay Edge detection Liang and Sun et al. (2010) indicated that edge detection is an alternative method to identify and classify pavement cracks for automated pavement management systems. Wang et al. (2012) indicated that two types of edges are usually contained in natural photographs: step edges and line edges. Wang et al. (2012) also illustrated that step edges emphasize the boundaries of regions, while line edges lie within narrow regions. Figure 9 shows both step edges and line edges. In their study, the edges of the steps and those of the lines were present. To detect these two types of edges, a Sobel Edge detector and a Canny Edge detector have been widely used. Regarding the Sobel Edge detector, Abdel-Qader et al. (2003) stated that it is known for its simplicity and speed, compared to other computationally complex algorithms, and is based on the spatial gradient algorithm. The problem with the Sobel edge detector is that it fails to define the edge when there are many influence points or patterns in the image. Therefore, before using the Sobel edge detector, the image should be analyzed to remove influence points or patterns in order to detect edges in the image. Parker et al. (2010) described the Sobel algorithm as having image data convolved with a Sobel mask, resulting in first-order partial derivatives for the pixel at the center of the mask. Compared to the Sobel edge detector, the Canny edge detector is more complicated and will provide better results. Abdel-Qader et al. (2003) indicated that the Canny edge detector algorithm is based on three parameters, namely the standard deviation of the Gaussian mask, and flux and thigh, which are used for the threshold to determine whether a pixel belongs to an edge or not . However, Sobel mask methods are used in their study. In the second selection part of this study, a block of size 10 x 10 is created to scan the matrix without repetitions to not only minimize the influence of influence points and patterns, but also to detect edges. The edge is defined as the boundary of 0 and non-0. Image Collection Image collection is the fundamental step for the crack detection model. The goal of this process is to collect photogrammetric data for the crack detection model. Memon et al. (2005) stated that photogrammetry is an established and commonly used approach by architects and engineers to monitor highways. At the same time, Brilakis et al. (2011) also indicated that close-range photogrammetry is characterized by low equipment cost and rapid data acquisition.on-site data at the expense of intensive user intervention to generate 3D surfaces from points. Therefore, photogrammetry proved to be an effective and efficient way to collect images in this study. Furthermore, this stage is an important process in the crack detection model because the image quality greatly influences the crack detection result. Based on the distinctive visual characteristics stated by Koch and Brilakis et al. (2011), the surface texture inside a hole is much coarser and grainier than the surface texture of the surrounding area. It means that the color inside the crack is darker than the surrounding areas. Therefore, the images used in their study satisfied the following principles: The crack could be clearly identified with the naked eye. The images were taken in the same lighting situation. Shadows and object effects were reduced. The color inside the crack was darker than surrounding areas. Image Segmentation Image segmentation is the second step for the crack detection model. This step is the fundamental process for the crack detection model. The purpose of image segmentation is to transform the original image into a binary image. The binary image could be treated as a matrix of 0 and 1, where 0 represents white and 1 represents non-white. To achieve this goal, an RGB selection algorithm is used at this stage. In the study by Koch and Brilakis et al. (2011) used a histogram shape-based thresholding algorithm, which is based on the triangle algorithm presented in Zack et al. (1977). The purpose of this process was to separate the darkest regions from the background of each image. Furthermore, as mentioned in the literature review, Koch and Brilakis et al. (2011) indicated that in pavement surface images, color information, especially RGB values, was not essential when performing the segmentation process with regards to defect detection. However, compared to the algorithm used in Koch and Brilakis et al. (2011), the RGB selection algorithm makes some improvements based on the histogram shape-based thresholding algorithm. For the RGB (Red Green Blue) selection algorithm, the R (Red) value will be treated as the primary threshold value in image segmentation. RGB values ​​are the fundamental character of the image's color information, ranging from 0 to 255. When the red, green, and blue values ​​are all 255, the color of the pixel is white, when red, green, and blue are all 255, the pixel color is white, when red, green and blue are 0, the pixel color will be black. The reason why the R (red) value was selected as the primary threshold value was that the R value was more efficient at representing the black-white intensity of the pixels. In the RGB selection algorithm, P (i, j) represents the pixels in the original image, B (i, j) represents the pixels in the binary image. If the pixel's R value is less than the selected Rsel value, the pixel will be defined as black, which is 1 in the binary image. Otherwise, the pixel will be defined as white, which is 0 in the binary image. Therefore, based on the Rsel threshold the original image will be transformed into a binary image using equation 2. This equation is similar to the equation used in image segmentation in the research of Koch and Brilakis et al. (2011). As mentioned in the literature review, Koch and Brilakis et al. (2011) indicated that the threshold T is determined as the intensity value of a histogram point PT = [T, h (T)], which has the maximum distance from a line l =.