Weighted Two-Phase Linear Reconstruction Measure-based Classification

摘要

Linear reconstruction measure (LRM) is a promising similarity measure of data. In this paper, we consider the locality of data in LRM, and propose weighted two-phase linear reconstruction measure-based classification (WTPLRMC). In WTPLRMC, the first phase determines the representative training samples from all training samples by LRM, and the second phase constrains the linear reconstruction coefficients of the chosen representative training samples in first phase using the locality of data, which is reflected by the similarity weights between each test sample and the representative training samples. The effectiveness of the proposed WTPLRMC is well demonstrated on some benchmark face databases with satisfactory classification results.