Learning image manifold using neighboring similarity integration

The perspective of image manifold and associated manifold learning methods have demonstrated promising results in finding the underlying structure from images in the high dimensional space. Conventional manifold learning methods construct the similarity relationship of image set only based on the pairwise Euclidean distance of images, so they may obtain deceptive similarity and suffer performance degradation. In this paper, we present an Neighboring Similarity Integration(NSI) algorithm to explore image manifold under probability preserving principle. NSI is based on the neighboring similarity of image samples and the local structures of image manifold, and can increases the estimation accuracy of similarity and enhance the learning ability for image manifold. The experimental results of image visualization problem on Yale and MNIST databases are presented to demonstrate the effectiveness of the proposed method.