3-D Head Model Retrieval Using a Single Face View Query

• Published in: IEEE transactions on multimedia Vol. 9; no. 5; pp. 1026 - 1036
• Main Authors: Hau-San Wong, Bo Ma, Zhiwen Yu, Pui Fong Yeung, Ip, H.H.S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2007; Institute of Electrical and Electronic Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3-D model retrieval; Applied sciences; Artificial intelligence; Character generation; Computer science; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Construction; Content based retrieval; Exact sciences and technology; Facial features; Head; Image retrieval; Information systems. Data bases; Kernel; kernel principal component analysis; Mapping; Mathematical analysis; Memory organisation. Data processing; neural network; Neural networks; Pattern recognition. Digital image processing. Computational geometry; Principal component analysis; Principal components analysis; Query processing; Similarity; Software; Studies; Three dimensional; Two dimensional; Vectors (mathematics); Videos; Multimedia; Database query; Face recognition; Similarity; Image retrieval; Neural network; Computer animation; Modeling; Adaptive method; Kernel method; Dimension reduction; Model matching; User interface; News; Virtual reality; Character set; kernel principal component analysis; Principal component analysis; 3-D model retrieval
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2007.898915

In this paper, a novel 3D head model retrieval approach is proposed, in which only a single 2D face view query is required. The proposed approach will be important for multimedia application areas such as virtual world construction and game design, in which 3D virtual characters with a given set of facial features can be rapidly constructed based on 2D view queries, instead of having to generate each model anew. To achieve this objective, we construct an adaptive mapping through which each 2D view feature vector is associated with its corresponding 3D model feature vector. Given this estimated 3D model feature vector, similarity matching can then be performed in the 3D model feature space. To avoid the explicit specification of the complex relationship between the 2D and 3D feature spaces, a neural network approach is adopted in which the required mapping is implicitly specified through a set of training examples. In addition, for efficient feature representation, principal component analysis (PCA) is adopted to achieve dimensionality reduction for facilitating both the mapping construction and the similarity matching process. Since the linear nature of the original PCA formulation may not be adequate to capture the complex characteristics of 3D models, we also consider the adoption of its nonlinear counterpart, i.e., the so-called kernel PCA approach, in this work. Experimental results show that the proposed approach is capable of successfully retrieving the set of 3D models which are similar in appearance to a given 2D face view.