Optimization algorithms for corner features

Abstract

As one of the most important local features, corner feature contains lots of information with the shape of the objects. After analyzing of several fashionable corner features at present, some optimization algorithms are proposed. These features after optimizing are invariant to image scale and rotation, and are shown robust to addition of noise and changes in 3D viewpoint. In this paper, we describe the approaches to recognize rigid objects using these features. As baselines for comparison, we also implemented some additional recognition systems. The performance analysis on the obtained experimental results demonstrates that the proposed optimization algorithms are effective and efficient.