Performance evaluation using Mandelbrot images for image registration algorithms

High-accuracy image registration is an important fundamental task in many fields, such as image sensing, image/video processing, computer vision, etc. In order to evaluate accuracy of image registration algorithms, the reference images transformed with known parameters have to be used. Reference images taken by a camera may include human errors, while reference images generated by a computer may require pixel interpolation in the process. To address these problems, this paper proposes a performance evaluation method using the Mandelbrot set which is one of the famous fractals. Experimental evaluation shows effectiveness of the proposed method.