Matching of Images with Rotation Transformation Based on the Virtual Electromagnetic Interaction
This addresses image registration challenges in computer vision, particularly for rotated images, but appears incremental as it builds on existing edge-based methods with a novel physical analogy.
The paper tackles image matching under rotation by proposing a method inspired by electromagnetic interaction, using virtual currents from edge lines to compute forces and moments for alignment, with experimental results demonstrating its effectiveness for image registration.
A novel approach of image matching for rotating transformation is presented and studied. The approach is inspired by electromagnetic interaction force between physical currents. The virtual current in images is proposed based on the significant edge lines extracted as the fundamental structural feature of images. The virtual electromagnetic force and the corresponding moment is studied between two images after the extraction of the virtual currents in the images. Then image matching for rotating transformation is implemented by exploiting the interaction between the virtual currents in the two images to be matched. The experimental results prove the effectiveness of the novel idea, which indicates the promising application of the proposed method in image registration.