Synchronized Submanifold Embedding for Person-Independent Pose Estimation and Beyond

• Published in: IEEE transactions on image processing Vol. 18; no. 1; pp. 202 - 210
• Main Authors: Shuicheng Yan, Huan Wang, Yun Fu, Jun Yan, Xiaoou Tang, Huang, T.S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.01.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3-D pose estimation; Age estimation; Aging; Algorithms; Applied sciences; Artificial Intelligence; Asia; Biometry - methods; Exact sciences and technology; Face - anatomy & histology; Face recognition; Head; Head - anatomy & histology; Humans; Image databases; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Information, signal and communications theory; manifold learning; Nearest neighbor searches; Pattern recognition; Pattern Recognition, Automated - methods; Posture; Reproducibility of Results; Sensitivity and Specificity; Signal processing; simplex; Spatial databases; Studies; subspace learning; Subtraction Technique; Telecommunications and information theory; Testing; Biometrics; Nearest neighbour; Age estimation; Face recognition; Image processing; Ageing; Subspace method; simplex; Man machine dialogue; Pattern recognition; Unsupervised learning; manifold learning; subspace learning; User interface; Database; Position measurement; 3-D pose estimation; Automatic recognition; Learning algorithm
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2008.2006400

Precise 3-D head pose estimation plays a significant role in developing human-computer interfaces and practical face recognition systems. This task is challenging due to the particular appearance variations caused by pose changes for a certain subject. In this paper, the pose data space is considered as a union of submanifolds which characterize different subjects, instead of a single continuous manifold as conventionally regarded. A novel manifold embedding algorithm dually supervised by both identity and pose information, called snchronized submanifold embedding (SSE), is proposed for person-independent precise 3-D pose estimation, which means that the testing subject may not appear in the model training stage. First, the submanifold of a certain subject is approximated as a set of simplexes constructed using neighboring samples. Then, these simplexized submanifolds from different subjects are embedded by synchronizing the locally propagated poses within the simplexes and at the same time maximizing the intrasubmanifold variances. Finally, the pose of a new datum is estimated as the propagated pose of the nearest point within the simplex constructed by its nearest neighbors in the dimensionality reduced feature space. The experiments on the 3-D pose estimation database, CHIL data for CLEAR07 evaluation, and the extended application for age estimation on FG-NET aging database, demonstrate the superiority of SSE over conventional regression algorithms as well as unsupervised manifold learning algorithms.