3-D head model retrieval using a single face view query

In this paper, a novel 3-D head model retrieval approach is proposed, in which only a single 2-D 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 3-D virtual characters with a given set of facial features can be rapidly constructed based on 2-D view queries, instead of having to generate each model anew. To achieve this objective, we construct an adaptive mapping through which each 2-D view feature vector is associated with its corresponding 3-D model feature vector. Given this estimated 3-D model feature vector, similarity matching can then be performed in the 3-D model feature space. To avoid the explicit specification of the complex relationship between the 2-D and 3-D 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 3-D 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 3-D models which are similar in appearance to a given 2-D face view.