Projection-based image registration algorithms use the sum of the pixel values along a given axis of an image to detect spatial changes in temporally separated images. These algorithms have been shown to be computationally efficient and effective for aligning temporally separated images and for visually detecting sensor motion. Registering images via projections has also been shown as a method for overcoming registration errors caused by the presence of fixed pattern noise. This work describes a method that exploits the statistical properties of images with significant local correlation to improve the performance of projection-based image registration algorithms. The algorithm is shown to operate in low signal-to-noise ratio (SNR) conditions and to significantly improve registration performance by as much as a factor of 5.5 in mean squared error over existing projection-based registration algorithms at a minimal computational cost.