Li Bai

Technical Section: Fitting 3D garment models onto individual human models

Designing an elegant 3D virtual garment model for a 3D virtual human model is labor-intensive, because most existing garment models are custom-made for a specific human model and cannot be easily reused for other individuals. In this paper, we propose a novel method for fitting a given 3D garment model onto human models of various body shapes and poses. The fitting is accomplished by deforming the garment mesh to match the shapes of the human models by using a combination of the following: skeleton-driven volumetric deformation, garment-human shape similarity matching and evaluation, the constraints of garment-human contact, and garment-human ease allowance. Experiments show that our approach performs very well and has the potential to be used in the garment design industry.

Gabor feature selection for face recognition using improved adaboost learning

Though AdaBoost has been widely used for feature selection and classifier learning, many of the selected features, or weak classifiers, are redundant. By incorporating mutual information into AdaBoost, we propose an improved boosting algorithm in this paper. The proposed method fully examines the redundancy between candidate classifiers and selected classifiers. The classifiers thus selected are both accurate and non-redundant. Experimental results show that the strong classifier learned using the proposed algorithm achieves a lower training error rate than AdaBoost. The proposed algorithm has also been applied to select discriminative Gabor features for face recognition. Even with the simple correlation distance measure and 1-NN classifier, the selected Gabor features achieve quite high recognition accuracy on the FERET database, where both expression and illumination variance exists. When only 140 features are used, the selected features achieve as high as 95.5% accuracy, which is about 2.5% higher than that of features selected by AdaBoost.

3D object modelling for entertainment applications

Recent advances in three-dimensional (3D) data acquisition techniques have offered an alternative to the traditional 2D metamorphosis (or morphing) approaches, which gradually change a source object through intermediate objects into a target object. In this paper, we approach 3D metamorphosis via a novel 3D modelling technique, which reconstructs a fairly complex object with a single B-Spline patch. Our object representation is compact - over 90% compression rate can be achieved. Despite such huge amount of data reduction, our method achieves similar rendering result to that using polygonal representation. Our approach also allows a one-to-one mapping from the object space to a common parameter space to be established, to allow automatic correspondence between a pair of objects. This way to establishing object correspondence is advantageous over the common connectivity generation process, with which, if either the source or target object is changed, the whole process of establishing correspondences must be repeated. Several aesthetically pleasing examples of 3D morphing are demonstrated using the proposed method.

Mesh smoothing via adaptive bilateral filtering

In this paper, we present an adaptive bilateral filtering algorithm that can be used to remove unavoidable noise from 3D mesh data generated by initial stages. Selecting the parameters for bilateral filters automatically, this algorithm smoothes meshes in the normal field using anisotropic character of local neighborhood triangles. Experimental results demonstrate that the proposed method remove light noise from meshes and reserve fine features of meshes as good as best results of other methods, with the advantage of none user-assisted parameters setting. Visual comparisons display that the method proposed in this paper performs better than other smoothing method for heavy noisy mesh.

3D surface reconstruction and recognition

In this paper we propose a novel 3D face recognition system. Furthermore we propose and discuss the development of a 3D reconstruction system designed specifically for the purpose of face recognition. The reconstruction subsystem utilises a capture rig comprising of six cameras to obtain two independent stereo pairs of the subject face during a structured light projection with the remaining two cameras obtaining texture data under normal lighting conditions. Whilst the most common approaches to 3D reconstruction use least square comparison of image intensity values, our system achieves dense point matching using Gabor Wavelets as the primary correspondence measure. The matching process is aided by Voronoi segmentation of the input images using strong confidence correlations as Voronoi seeds. Additional matches are then propagated outwards from the initial seed matches to produce a dense point cloud and surface model. Within the recognition subsystem models are first registered to a generic head model, and then an ICP variant is applied between the recognition subject and each model in the comparison database, using the average point-to-plane error as the recognition metric. Our system takes full advantage of the additional information obtained from the shape and structure of the face, thus combating some of the inherent weaknesses of traditional 2D methods such as pose and illumination variations. This novel reconstruction / recognition process achieves 98.2% accuracy on databases containing in excess of 175 meshes.

InfoBoost for selecting discriminative gabor features

We proposed a novel boosting algorithm – InfoBoost. Though AdaBoost has been widely used for feature selection and classifier learning, many of the selected features are redundant. By incorporating mutual information into AdaBoost, InfoBoost fully examines the redundancy between candidate classifiers and selected classifiers. The classifiers thus selected are both accurate and non-redundant. Experimental results show that InfoBoost learned strong classifier has lower training error than AdaBoost. InfoBoost learning has also been applied to selecting discriminative Gabor features for face recognition. Even with the simple correlation distance measure and 1-NN classifier, the selected Gabor features achieve quite high recognition accuracy on the FERET database, where both expression and illumination variance are present. When only 140 features are used, InfoBoost selected features achieve 95.5% accuracy, about 2.5% higher than that achieved by AdaBoost.

Hand tracking and animation

In this paper we present an approach for animating a virtual hand model with the animation data extracting from hand tracking results. We track the hand by using particle filters and deformable contour templates with a web camera; then we extend the 2D tracking results into 3D animation data using inverse kinematics method; finally, local frame based method is proposed to simulate a 3D virtual hand with the 3D animation data. Our system performs in real time.

Animating Unstructured 3D Hand Models

We present a novel approach for automatically animating unstructured hand models. Skeletons of the hand models are automatically extracted. Local frames on hand skeletons are created to skin and animate hand models. Self-intersection of hand surfaces is avoided. Our method produces realistic hand animation efficiently.

A Novel Face Recognition Method

This paper introduces a new face recognition method that treats 2D face images as 1D signals to take full advantages of wavelet multi-resolution analysis. Though there have been many applications of wavelet multi-resolution analysis to recognition tasks, the effectiveness of the approach on 2D images of varying lighting conditions, poses, and facial expressions remains to be resolved. We present a new face recognition method and the results of extensive experiments of the new method on the ORL face database, using a neural network classifier trained by randomly selected faces. We demonstrate that the method is computationally efficient and robust in dealing with variations in face images. The performance of the method also decreases gracefully with the reduction of the number of training faces.

3D Modelling for Metamorphosis for Animation

In this paper, we propose a novel 3D B-Spline surface reconstruction technique for 3D metamorphosis for animation and entertainment. The approach allows one-to-one mapping between the object space and a parameter space, and therefore automatic correspondence between a pair of reconstructed objects. B-Spline-based shape representation also has the advantages of: 1) easy shape editing, 2) level of detail control, and 3) compact storage.