A High Performance Point Based Image Alignment Approach Using an Artificial Immune System

Abstract

In this paper, a high performance image alignment approach is presented. This approach is classified as a point based alignment approach. An artificial immune system (AIS) with a modified mutation formula is used to find the correspondence points between the reference and the input images. After the correspondence is found, the least mean squares technique (LMS) is used to determine the transformation which is used to align the two images. This approach doesn't require any additional refinement or features detector as some others approaches required. To demonstrate the effectiveness of proposed algorithm, it compared with two state-of-the-art algorithms for different data sets. formula based on an uniform distribution was used. F. Ye et. al (7) proposed two step image registration by artificial immune system and chamfer matching, in this paper the artificial immune system has been used to find an initial transformation where the edge distance used as a fitness function then an area based method has been used to refine the transformation estimation. The artificial immune systems are used for function optimization, the clonal selection and affinity mutation principles are used to explain how the immune systems perform the optimization process. There are many artificial immune systems were published in the context. An immune algorithm, named CLONALG, was developed to perform pattern recognition and optimization. De Castro and J. Timmis proposed opti-aiNet for Multimodal Function Optimization (8). This algorithm is used in our registration approach. The mutation formula proposed at (8) was: