A Pivot-Based Distributed Pseudo Facial Image Retrieval in Manifold Spaces: An Efficiency Study

Abstract

The research of cognitive science indicates that manifold-learning-based facial image retrieval is based on human perception, which can accurately capture the intrinsic similarity of two facial images. The paper proposes a pivot-based Distributed Pseudo Similarity Retrieval method called DPSR in manifold spaces with the aid of a adjacency distance list (ADL). Specifically, we first construct a two dimensional array, called ADL which records the pair-wise distance between any two facial images with a constraint in the database. Then, the distances are indexed by a B+-tree. Finally, a DPSR process in high-dimensional manifold spaces is transformed into range search over the B+-tree in the single-dimensional space at a filtering level. Extensive experimental studies show that the DPSR outperforms the conventional sequential scan in manifold spaces by a large margin, especially for the large high-dimensional datasets.