A novel subspace learning algorithm based on nearest feature line and directional derivative gradient is proposed in this paper. The proposed algorithm combines neighborhood discriminant nearest feature line analysis and directional derivative gradient to extract the local discriminant features of the samples. A discriminant power criterion based on nearest feature line is used to find the most discriminant direction in this paper. Some experiments are implemented to evaluate the proposed algorithm and the experimental results demonstrate the effectiveness of the proposed algorithm.
CITATION STYLE
Yan, L., Pan, J. S., & Zhu, X. (2014). Directional discriminant analysis for image feature extraction. In Advances in Intelligent Systems and Computing (Vol. 238, pp. 341–348). Springer Verlag. https://doi.org/10.1007/978-3-319-01796-9_37
Mendeley helps you to discover research relevant for your work.