Search

Hand gesture recognition is an important aspect in Human-Computer interaction, and can be used in various applications, such as virtual reality and computer games. In this paper, we propose a real time hand gesture recognition system. It includes three major procedures: detection, tracking and recognition. In hand detection stage, an open hand is detected by the histograms of oriented gradient and AdaBoost method. The hand detector is trained by the AdaBoost algorithm with HOG features. A contour based tracker is applied in combining condensation and partitioned sampling. After a hand is detected in the image, the tracker can track the hand contour in real time. During the tracking, the trajectory is saved to perform hand gesture recognition in the last stage. Recognition of the hand moving trajectory is implemented by hidden Markov models. Several HMMs are trained in advance, and the results from the tracking stage are then recognized using the trained HMMs. Experiments have been conducted to validate the performance of the proposed system. Under normal webcam it can recognize the predefined gestures quickly and precisely. As it is easy to develop other hand gestures, the proposed system has good potential in many applications. [ABSTRACT FROM AUTHOR]

This paper proposes an adaptive background model which combines the advantages of both Eigenbackground and pixel-based gaussian models. This method exploits the illumination changes by Eigenbackground. Moreover, it can detect the chroma changes and remove shadow pixels using gaussian models. An adaptively strategy is used to integrate two models. A binary graph cut is used to implement the foreground/background segmentation by developing our data term and smooth term. We validate our method on indoor videos and test it on the benchmark video. Experiments demonstrate our method΄s efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we present a visual articulated hand contour tracker which is capable of tracking in real-time the contour of an unadorned articulated hand with the palm approximately parallel to the camera΄s image plane. In our implementation, a B-spline deformable template is used to represent human hand contour, and a 14-dimensions non-linear state space which is divided into 7 parts is used to represent the dynamics of a hand contour. The tracking is performed in grey-scale skin-color image based on particle filter and partitioned sampling. Firstly, a Gaussian model is used to extract the skin pixels. Secondly, particles for each of the 7 parts of the non-linear state space are generated hierarchically based on second-order auto-regressive processes and partitioned sampling, and then each generated particle is weighted by an observation density. Finally, the best complete particle is chosen as the tracking result, and several complete particles are stored to be used in the next frame. The experiments show that our tracker performs well when tracking both rigid movements of the whole hand and non-rigid movements of each finger. [ABSTRACT FROM AUTHOR]

We use RBF deformation and normal projection to regulate the scanned facial model, which makes their topology equivalent to a regular grid mesh and can generate principle components. Then the synthesized individual face model can be directly flatten to a regular plan, so the motion vectors of vertexes can be interpolated with barycentric coordinate. The regulation and animation remapping needs less than 40 key points and can work in real-time [ABSTRACT FROM AUTHOR]

A new approach of generating textures from multi-view images is presented in this paper. The generated textures can be mapped onto a 3D face model seamlessly. Angle Based Flattening(ABF) surface parameterization is used to build the correspondence between a 3D face model and its 2D texture domain. Feature points on face model are defined according to face anatomy, and their counterparts on images are automatically extracted with AAM method, plus by some little user interaction. The correspondence between feature points on 3D model and 2D images sets up the correspondence between images and the texture domain. With above methods, we can efficiently synthesis texture seamlessly from multi-view images, and map it onto the 3D face model. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This paper presents a Bayesian network based multi-cue fusion method for robust and real-time fist tracking. Firstly, a new strategy, which employs the latest work in face recognition, is used to create accurate color model of the fist automatically. Secondly, color cue and motion cue are used to generate the possible position of the fist. Then, the posterior probability of each possible position is evaluated by Bayesian network, which fuses color cue and appearance cue. Finally, the fist position is approximated by the hypothesis that maximizes a posterior. Experimental results show that our algorithm is real-time and robust. [ABSTRACT FROM AUTHOR]

It has been demonstrated that combining the decisions of several classifiers can lead to better recognition results. The combination can be implemented using a variety of schemes, among which voting method is the simplest, but it has been found to be just as effective as more complicated strategies in improving the recognition results. In this paper, we propose a voting method for object location, which can be viewed as generalization of majority vote rule. Using this method, we locate eye centers in face region. The experimental results demonstrate that the locating performance is comparable with other newly proposed eye locating methods. The voting method can be considered as a general fusion scheme for precise location of object. [ABSTRACT FROM AUTHOR]

Shadows produce troublesome effects in many computer vision applications. The idea behind most current shadow removal approaches is locating shadows and then removing them[1][4]. However, distinguishing shadow edges due to shadows from reflectance edges due to reflectance changes is a difficult problem, particularly in a single image. In this paper, we focus on the shadow removal problem in face recognition, and take a novel method based on ICA (Independent Component Analysis) to remove shadows from a single face images. The training set contains face images without shadows. Firstly, we applied derivative filters on training images to derive face edge maps, and then perform ICA on filtered training set to construct pixel ICA subspaces which can be used to remove shadow edges from the filtered versions of a single test image. After the shadow edges removal process, a shadow free image can be reconstructed using an approach similar to [7]. Unlike previous shadow removal approaches, our method can remove shadows from a single gray image. Experimental results demonstrate that the proposed approach can effectively eliminate the effects of shadows in face recognition. [ABSTRACT FROM AUTHOR]

In this work, we present a novel approach for face recognition which use boosted statistical local Gabor feature based classifiers. Firstly, two Gabor parts, real part and imaginary part, are extracted for each pixel of face images. The two parts are transformed into two kinds of Gabor features, magnitude feature and phase feature. 40 magnitude Gaborfaces and 40 phase Gaborfaces are generated for each face image by convoluting face images with five scales and eight orientations Gabor filters. Then these Gaborfaces are scanned with a sub-window from which the quantified Gabor features histograms are extracted representing efficiently the face image. The multi-class problem of face recognition is transformed into a two-class one of intra-and extra-class classification using intra-personal and extra-personal images, as in [5]. The intra/extra features are constructed based on these histograms of two different face images with Chi square statistic as dissimilarity measure. A strong classifier is learned using boosting examples, similar to the way in face detection framework [10]. Experiments on FERET database show good results comparable to the best one reported in literature [6]. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]