INVESTIGATION OF IMAGE STITCHING REFINEMENT WITH ENHANCED CORRELATION COEFFICIENT

Abstract

Image stitching combines multiple overlapping scenes into a panorama. It can be applied in video stitching, super-resolution, and medical imaging. Post-processing routines such as exposure compensation, seam line adjustment, and blending are often performed to increase its visual appeal. Our aim is to increase the registration accuracy between adjacent image pairs in a stitching algorithm. This is done by adding an area-based registration step, namely Enhanced Correlation Coefficient (ECC), which refines the original feature-based image registration. The performance of registrations in the stitching algorithm is evaluated using root-mean-squared error of control points, structural similarity index, and universal image quality index. The Boat and Graffiti datasets from the Oxford Robotics Database are used for experiments. It is found that ECC largely improves registrations in stitching except for a slight increase in root-mean-squared error of control points in the Boat dataset. In addition, ECC’s enhancement makes the registration outperform the ground truth in one image of both datasets.