Medical DR image alignment based improved tangent space

Zuo Weiming and Li Tie

Abstract

Tangent space alignment is efficient in machine learning. This is about mapping several datasets into a global space, and is of great importance in learning the shared latent structure, data fusion and multicue data matching. In this paper, we propose an improved tangent space algorithm to solve medical DR image alignment problem. This algorithm builds the inner linear manifold constraint in Medical DR image. A cost function to measure the quality of alignment is given by combining the inner manifold constraints of each dataset and the matching points constraints among different datasets. The effectiveness of our algorithm is validated by applying it to the medical DR image alignment.