A major goal of this research is the automation of crack monitoring in concrete structures by quantifying the changes detected from the sequential images during monitoring period. The periodic image series for monitoring are taken using a precise metric camera. This task is based on the idea that one can derive information about the change strictly from its imagery once the geometric relationship between data sets is correctly recovered. The goal is achieved by using the conformal transformation based on the Modified Iterated Hough Transform (MIHT) algorithm, the result of which solves the orientation parameters of the camera when the correspondence is not known. To improve the computational operation of MIHT, the optimum sequence and regions of parameter estimation are also investigated. The developed algorithm is applied to a simulated set of linear crack changes. Finally, the changes of cracks pattern occurred in the sequence of images of the actual concrete specimen are detected.