Recognition of Human Pose From Images Based on Graph Spectra

Abstract

ABSTRACT:Recognition of human pose is an actual problem in computer vision. To increase the reliability of the recognition it is proposed to use structured information in the form of graphs. The spectrum of graphs is applied for the comparison of the structures. Image skeletonization is used to construct graphs. Line segments are the nodes of the graph. The end point of line segments are the edges of the graph. The angles between adjacent segments are used to set the weights of the adjacency matrix. The Laplacian matrix is used to generate the spectrum graph. The algorithm consists of the following steps. The graph on the basis of the vectorized image is constructed. The angles between the adjacent segments are calculated. The Laplacian matrix on the basis of the linear graph is calculated. The eigenvalues and eigenvectors of the Laplacian matrix are calculated. The spectral matrix is calculated using its eigenvalues and eigenvectors of the Laplacian matrix. The principal component method is used for the data representation in the space of smaller dimensions. The results of the algorithm are given.

Clustering using a random walk on graph for head pose estimation

“…The clustering is used in pattern recognition [14], object tracking [15] or reconstruction of the three-dimensional scenes [16,17]. The main problem is considered to be the question of the graph connectivity, the similarity of vertices and edges.…”

Automatic building detection from satellite images using spectral graph theory

“…Spectral clustering is used to group regions with similar characteristics. Spectral graph theory is used in pattern recognition [11], reconstruction of three-dimensional scenes [12], tracking the movement of objects [13].…”