Multi-locality correlation feature learning for image recognition

Locality-based feature learning has drawn more and more attentions recently. However, most of locality-based feature learning methods only consider a kind of local neighbor information, and such the locality-based methods are difficult to well reveal intrinsic geometrical structure of raw high-dimensional data. In this paper, we propose a novel multi-locality correlation feature learning algorithm for multi-view data, called multi-locality discrimination canonical correlation analysis (MLDCCA), which can learn nonlinear correlation features with strong discriminative power. Different from the locality-based methods, our algorithm not only employs multiple local patches of each raw data to well capture the intrinsic geometrical structure information, but also fully considers intraclass scatter information for further enhancing the class separability of the learned correlation features. Extensive experimental results on several real-word image datasets have demonstrated the effectiveness of our algorithm.