In recent years, the dimensionality reduction methods based on graph theory have attracted more and more attention. Aiming at the core problem of face recognition, namely the dimensionality reduction of high-dimensional data, this paper first introduces the basic concepts of graph theory, summarizes various methods of face image dimensionality reduction, and unifies these methods into the graph embedding framework. Then, the advantages and disadvantages of various algorithms are analyzed from the perspective of linear and nonlinear, and it is concluded that nonlinear graph embedding algorithms are superior to traditional methods in mining nonlinear features in face images and in data dimensionality reduction. Finally, the future research and development directions are discussed in view of the problems existing in the existing composition methods.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore