Search

Discriminative approaches for human pose estimation model the functional mapping, or conditional distribution, between image features and 3D pose. Learning such multi-modal models in high dimensional spaces, however, is challenging with limited training data; often resulting in over-fitting and poor generalization. To address these issues latent variable models (LVMs) have been introduced. Shared LVMs attempt to learn a coherent, typically non-linear, latent space shared by image features and 3D poses, distribution of data in that latent space, and conditional distributions to and from this latent space to carry out inference. Discovering the shared manifold structure can, in itself, however, be challenging. In addition, shared LVMs models are most often non-parametric, requiring the model representation to be a function of the training set size. We present a parametric framework that addresses these shortcoming. In particular, we learn latent spaces, and distributions within them, for image features and 3D poses separately first, and then learn a multi-modal conditional density between these two low-dimensional spaces in the form of Gaussian Mixture Regression. Using our model we can address the issue of over-fitting and generalization, since the data is denser in the learned latent space, as well as avoid the necessity of learning a shared manifold for the data. We quantitatively evaluate and compare the performance of the proposed method to several state-of-the-art alternatives, and show that our method gives a competitive performance. [ABSTRACT FROM AUTHOR]

The existing methods of facial expression recognition are always affected by different illumination and individual. A facial expression recognition method based on local Gabor filter bank and fractional power polynomial kernel PCA is presented for this problem in this paper. Local Gabor filter bank can overcome the disadvantage of the traditional Gabor filter bank, which needs a lot of time to extract Gabor feature vectors and the high-dimensional Gabor feature vectors are very redundant. The KPCA algorithm is capable of deriving low dimensional features that incorporate higher order statistic. In addition, SVM is used to classify the features. Experimental results show that this method can reduce the influence of illumination effectively and yield better recognition accuracy with much fewer features. [ABSTRACT FROM AUTHOR]

In this paper, a newly image segmentation method for remote sensing image is presented. The proposed method consists of three steps: 1) multi-resolution image sequences are constructed by a multi-resolution model, in which pixels between two neighboring resolutions are linked by computing parent-child distance, 2) the evolution of local variance at multi-resolution is studied, on which images are segmented based on image sequence and 3) an actual segmented result corresponding to the original image is obtained by using the parent-child link. The experimental results show that we can get favorable segmentation performance by using this method. [ABSTRACT FROM AUTHOR]

The requirement for high-quality product with reduced cost and time-to-market in multidisciplinary project is demanding. Integration of design and process planning with computer aided techniques can provide a solution to this challenge. This paper describes a reference model of integrating computer aided techniques to aid the concurrent development of a multi-nozzle 3D printer for fabricating artificial bone scaffold at the University of Strathclyde and the Northwestern Polytechnical University. This integration reference model, including design tools such as Material Computation (MC), Computational Fluid Dynamics (CFD), and CAD, and planning tool such as CAM techniques, is employed to support this special 3D printer development. The high precision multi-nozzle development was used as a case study to validate this integration of concurrent design and process planning. CAD tools were used to provide several nozzle design concepts and a rigorous CFD analysis of several nozzle designs under the same boundary conditions were undertaken to refine and evaluate them by research staff from both institutions. This cooperative conceptual design case study demonstrated that it drastically reduced development time and cost in devising nozzle conceptual sketch design and optimizing the nozzle design for 3D printer. This makes it an important step in designing a high precision artificial bone rapid manufacturing machine. [ABSTRACT FROM AUTHOR]

This article proposes a neural network for building Chinese and English semantic resources connection. Abundant monolingual semantic information is stored into its bipartite graph structure respectively. Two hidden layers are also set in every part, word layer and concept layer. Every word associates with different concepts separately; every concept includes different vocabularies; and these two layers also independently connect to their counterparts through bipartite graph. These distributed characteristics in hidden layers meet the need of parallel network computing. The unsupervised method is used to train the network, and samples are translation lexicons, results of the bilingual word-level alignment algorithm. The training principle comes from the inspiration of bilingual semantic asymmetry. Every translational equivalent contains the unambiguous information by comparison between source and target languages. These translation lexicons are viewed as a kind of special context. They almost have definite meaning. Every input will activate and suppress various kinds of potential connections by the interaction of hidden layers, and modify their connective weights. Finally a demo test presents. [ABSTRACT FROM AUTHOR]

Because of the specialty of undersea channel and the complexity of undersea environment, many uncertain factors affect the quality of undersea image. Consequently, it is a difficult problem to segment and identify targets for undersea image. In this paper, a novel target segmentation and feature extraction approach for undersea image based on function transformation is presented. The approach overcomes the influence of complex environment and uneven illumination effectively. Experimental results demonstrate that the approach is valid for target segmentation and feature extraction for undersea hydrothermal vent image. [ABSTRACT FROM AUTHOR]

An iterative hybrid interpolation method is proposed in this study, which is an integration of the bilinear and the bi-cubic interpolation methods and implemented by an iterative scheme. First, the implement procedure of the iterative hybrid interpolation method is described. This covers (a) a low resolution image is interpolated by using the bilinear and the bi-cubic interpolators respectively; (b) a hybrid interpolated result is computed according to the weighted sum of both bilinear interpolation result and bi-cubic interpolation result and (c) the final interpolation result is obtained by repeating the similar steps for the successive two hybrid interpolation results by a recursive manner. Second, a further discussion on the method - the relation between hybrid parameter and details of an image is provided from the theoretical point of view, at the same time, an approach used for the determining of the parameter is proposed based on the analysis of error parameter curve. Third, the effectiveness of the proposed method is verified based on the experimental study. [ABSTRACT FROM AUTHOR]