An image processing algorithm for the reversed transformation of rotated microscope images

This paper presents an image processing algorithm for reversed transformation of rock structure images taken with polarizing microscope stage rotations. The algorithm is applied for the analysis of microscope images of Tumlin sandstone. The most important property of the proposed method is that the operation is based on global image information to find the best fit angle and vector. The idea of the algorithm is based on finding the optimal rotation angle and optimal translation vector, thus ensuring the best correspondence between analysed images. The criteria for optimization are formulated on the basis of the shapes of edges located on images. The proposed algorithm can be used as an alternative solution in the case when a rotating polarizer stage is not available. Moreover, the proposed algorithm makes it possible to use matched images for the automatic identification of the rock structures such as grain boundaries, cracks and pores.