An Image Mosaics Algorithm Based on Improved Phase Correlation

An image mosaics algorithm based on improved phase correlation is proposed in this paper. The improved phase correlation improves on the conventional phase correlation in three aspects. Firstly, the contours of images are extracted, and the phase correlation is applied to the contours of images instead of the whole original images. Secondly, when there are multiple peak values approximate to the maximum peak value in the function array, their corresponding translations can be regarded as candidate translations and calculated separately, and the best translation should be determined by the optimization of conformability of two images in the overlapping area. Thirdly, the effect of minor rotations on mosaics is taken into consideration. The running results show that the proposed algorithm can stably yield high quality mosaics, even in the cases of poor or differential lighting conditions and multiple peak values approximate to the maximum peak value, existences of minor rotations and other complicated displacements between images.