Hierarchical Shape Modeling for Automatic Face Localization

Abstract

Abstract. Many approaches have been proposed to locate faces in an image. There are, however, two problems in previous facial shape models using feature points. First, the dimension of the solution space is too big since a large number of key points are needed to model a face. Second, the local features associated with the key points are assumed to be independent. Therefore, previous approaches require good initialization (which is often done manually), and may generate inaccurate localization. To automatically locate faces, we propose a novel hierarchical shape model (HSM) or multi-resolution shape models corresponding to a Gaussian pyramid of the face image. The coarsest shape model can be quickly located in the lowest resolution image. The located coarse model is then used to guide the search for a finer face model in the higher resolution image. Moreover, we devise a Global and Local (GL) distribution to learn the likelihood of the joint distribution of facial features. A novel hierarchical data-driven Markov chain Monte Carlo (HDDMCMC) approach is proposed to achieve the global optimum of face localization. Experimental results demonstrate that our algorithm produces accurate localization results quickly, bypassing the need for good initialization.

A Monte Carlo Strategy to Integrate Detection and Model-Based Face Analysis

“…A newer development in the sampling literature are data-driven proposal distributions which make use of the input data to form probably useful proposals (heuristics). DDMCMC methods have been used to segment images [21], do inference about a complex 3D scene using only monocular input [22], to infer the pose of a human body model [19] or to localize faces [15].…”

Segmenting Multiple Objects with Overlapping Appearance and Uncertainty

“…The results showed that the exploration of the multi-modal posterior was suboptimal using the standard MCMC techniques. The use of data-driven and mode-hopping MCMC schemes for better exploration of the posterior should be investigated [8,9]. Better models of the shape-free appearance also need to be incorporated in this framework.…”

A Hierarchical Compositional Model for Face Representation and Sketching

“…Others model each object as one point in the high-dimensional feature space and increase the dimension to match the augmented complexity [21]. Both methods are inefficient and inadequate for human faces, where dramatic variabilities are exhibited due to the absence of feature semantics and lack of structural flexibility.…”