Traditional face swapping technologies require that the faces of source images and target images have similar pose and appearance (usually frontal). For overcoming this limit in applications this paper presents a pose-free face swapping method based on personalized 3D face modeling. By using a deformable 3D shape morphable model, a photo-realistic 3D face is reconstructed from a single frontal view image. With the aid of the generated 3D face, a virtual source image of the person with the same pose as the target face can be rendered, which is used as a source image for face swapping. To solve the problem of illumination difference between the target face and the source face, a color transfer merging method is proposed. It outperforms the original color transfer method in dealing with the illumination gap problem. An experiment shows that the proposed face reconstruction method is fast and efficient. In addition, we have conducted experiments of face swapping in a variety of scenarios such as children's story book, role play, and face de-identification stripping facial information used for identification, and promising results have been obtained.

To develop human interface for virtual environment, we have constructed a tensed strings based interface device called SPIDAR, which allow us to manipulate virtual object directly just like in real space. SPIDAR can both measure the movement of user's finger tip and offer force display. Since proper force feedback comes out of the proper position measurement, in this paper, we will analyze the possible reasons that may cause position measurement error, and propose an algorithm which can revise the error and improve position measurement precision.

Person re-identification is a challenging problem of matching observations of individuals across non-overlapping camera views. When pedestrians walk across disjoint camera views, continuous motion information is lost, and thus re-identification mainly relies on appearance matching. Person re-identification is actually a special case of near duplicate search in image retrieval. Given a probe, our task is to find the image containing the same person in galleries. At present many state-of-the-art methods in image retrieval are based on the Bag-of-Words (BOW) model. By adapting the BOW model to our task, Bag-of-Ensemble-Colors (BOEC) is proposed to tackle person re-identification in this paper. We combine low-level color histogram and semantic color names to represent human appearances. Meanwhile, some mature and efficient techniques in image retrieval are employed in the model containing soft quantization, burstiness punishing strategy, and negative evidence. In consideration apriori knowledge of human body structure, efficient spatial constraints are proposed to weaken the influence of background. Extensive experiments on VIPeR and ETHZ databases are performed to test the effectiveness of our approach, and promising results are obtained in the public databases. Compared with other unsupervised methods, we obtain state-of-the-art performances. The recognition rate is 32.23% on VIPeR dataset, 87% on ETHZ SEQ.#1, 83% on ETHZ SEQ.#2, and 91% on ETHZ SEQ.#3.

Middle-level parts have attracted great attention in the computer vision community, acting as discriminative elements for objects. In this paper we propose an unsupervised approach to mine discriminative parts for object detection. This work features three aspects. First, we introduce an unsupervised, exemplar-based training process for part detection. We generate initial parts by selective search and then train part detectors by exemplar SVM. Second, a part selection model based on consistency and distinctiveness is constructed to select effective parts from the candidate pool. Third, we combine discriminative part mining with the deformable part model (DPM) for object detection. The proposed method is evaluated on the PASCAL VOC2007 and VOC2010 datasets. The experimental results demons-trate the effectiveness of our method for object detection.

A brain-computer interface (BCI) translates the brain activity into commands to control external devices. P300 speller based character recognition is an important kind of application system in BCI. In this paper, we propose a framework to integrate channel correlation analysis into P300 detection. This work is distinguished by two key contributions. First, a coefficient matrix is introduced and constructed for multiple channels with the elements indicating channel correlations. Agglomerative clustering is applied to group correlated channels. Second, the statistics of central tendency are used to fuse the information of correlated channels and generate virtual channels. The generated virtual channels can extend the EEG signals and lift up the signal-to-noise ratio. The correlated features from virtual channels are combined with original signals for classification and the outputs of discriminative classifier are used to determine the characters for spelling. Experimental results prove the effectiveness and efficiency of the channel correlation analysis based framework. Compared with the state-of-the-art, the recognition rate was increased by both 6% with 5 and 10 epochs by the proposed framework.

High-speed display of 3-D objects in virtual reality environments is one of the currently important subjects. Shape simplification is considered an efficient method. This paper presents a method of hierarchical cube-based segmentation for shape simplification and multiresolution model construction. The relations among shape simplification, resolution and visual distance are derived firstly. The first level model is generated from scattered range data by cube-base segmentation with the first level cube size. Multiresolution models are then generated by re-sampling polygonal patch vertices of each former level model with hierarchical cube-based segmentation structure. The results show that the algorithm is efficient for constructing multiresolution models of free-form shape 3-D objects from scattered range data and high compression ratio can be obtained with little noticeable difference during the visualization.

For constructing the next generation education system, we have developed a new human-scale virtual reality interface device called Big-SPIDAR. This device can provide not only the visual and auditory information but also haptic/kinaesthetic display. And it has the capability for the operator or participant to move around inside it. In this paper, we introduce the construction of this interface device and show the evaluation experiments and application systems realized by proposed device.