Search

In this paper, we analyse patterns in face shape variation due to weight gain. We propose the use of persistent homology descriptors to get geometric and topological information about the configuration of anthropometric 3D face landmarks. In this way, evaluating face changes boils down to comparing the descriptors computed on 3D face scans taken at different times. By applying dimensionality reduction techniques to the dissimilarity matrix of descriptors, we get a space in which each face is a point and face shape variations are encoded as trajectories in that space. Our results show that persistent homology is able to identify features which are well related to overweight and may help assessing individual weight trends. The research was carried out in the context of the European project SEMEOTICONS, which developed a multisensory platform which detects and monitors over time facial signs of cardio-metabolic risk. [ABSTRACT FROM AUTHOR]

Paper introduces a 3-D shape representation scheme for automatic face analysis and identification, and demonstrates its invariance to facial expression. The core of this scheme lies on the combination of statistical shape modelling and non-rigid deformation matching. While the former matches 3-D faces with facial expression, the latter provides a low-dimensional feature vector that controls the deformation of model for matching the shape of new input, thereby enabling robust identification of 3-D faces. The proposed scheme is also able to handle the pose variation without large part of missing data. To assist the establishment of dense point correspondences, a modified free-form-deformation based on B-spline warping is applied with the help of extracted landmarks. The hybrid iterative closest point method is introduced for matching the models and new data. The feasibility and effectiveness of the proposed method was investigated using standard publicly available Gavab and BU-3DFE datasets, which contain faces with expression and pose changes. The performance of the system was compared with that of nine benchmark approaches. The experimental results demonstrate that the proposed scheme provides a competitive solution for face recognition. [ABSTRACT FROM AUTHOR]

Existing approaches to recover structure of 3D deformable objects and camera motion parameters from an uncalibrated images assume the object's shape could be modelled well by a linear subspace. These methods have been proven effective and well suited when the deformations are relatively small, but fail to reconstruct the objects with relatively large deformations. This paper describes a novel approach for 3D non-rigid shape reconstruction, based on manifold decision forest technique. The use of this technique can be justified by noting that a specific type of shape variations might be governed by only a small number of parameters, and therefore can be well represented in a low-dimensional manifold. The key contributions of this work are the use of random decision forests for the shape manifold learning and robust metric for calculation of the re-projection error. The learned manifold defines constraints imposed on the reconstructed shapes. Due to a nonlinear structure of the learned manifold, this approach is more suitable to deal with large and complex object deformations when compared to the linear constraints. The robust metric is applied to reduce the effect of measurement outliers on the quality of the reconstruction. In many practical applications outliers cannot be completely removed and therefore the use of robust techniques is of particular practical interest. The proposed method is validated on 2D points sequences projected from the 3D motion capture data for ground truth comparison and also on real 2D video sequences. Experiments show that the newly proposed method provides better performance compared to previously proposed ones, including the robustness with respect to measurement noise, missing measurements and outliers present in the data. [ABSTRACT FROM AUTHOR]

This paper describes a novel method for shape representation and robust image segmentation. The proposed method combines two well known methodologies, namely, statistical shape models and active contours implemented in level set framework. The shape detection is achieved by maximizing a posterior function that consists of a prior shape probability model and image likelihood function conditioned on shapes. The statistical shape model is built as a result of a learning process based on nonparametric probability estimation in a PCA reduced feature space formed by the Legendre moments of training silhouette images. A greedy strategy is applied to optimize the proposed cost function by iteratively evolving an implicit active contour in the image space and subsequent constrained optimization of the evolved shape in the reduced shape feature space. Experimental results presented in the paper demonstrate that the proposed method, contrary to many other active contour segmentation methods, is highly resilient to severe random and structural noise that could be present in the data. [ABSTRACT FROM AUTHOR]

Purpose: Non-invasive imaging assessment of cardiac function is important in cardiovascular disease diagnosis, especially for evaluation of local cardiac motion. Tagged cardiac MRI has been developed for this purpose, but evaluation of the results requires quantification and automation. Methods: Two methods utilizing active contour modeling for wall motion extraction based on tagged cardiac MRI scans were evaluated based on properties of tracking methods in the image domain and frequency domain. Three criteria were used: accuracy, inter-subject and intra-subject sensitivity. The tracking results were evaluated by a medical expert. The evaluation methodology and its possible generalization to other diagnostic methods were considered. Results: Image domain and frequency domain analysis of tagged cardiac MRI data sets were evaluated demonstrating that the image domain method provides better results. The image domain method method is much more resistant to changes in the data, this time, due to a different subject being scanned. The frequency domain approach is not suitable for clinical applications, as the global error is significantly increased (more than 20%). Conclusion: The image domain method was found most effective, and it can generate a set of clearly identified parameters. The evaluation approach can be an interesting alternative to classical psychovisual studies which are time-consuming and often fastidious for clinicians. [ABSTRACT FROM AUTHOR]

This paper describes a novel method for representing different facial expressions based on the shape space vector (SSV) of the statistical shape model (SSM) built from 3D facial data. The method relies only on the 3D shape, with texture information not being used in any part of the algorithm, that makes it inherently invariant to changes in the background, illumination, and to some extent viewing angle variations. To evaluate the proposed method, two comprehensive 3D facial data sets have been used for the testing. The experimental results show that the SSV not only controls the shape variations but also captures the expressive characteristic of the faces and can be used as a significant feature for facial expression recognition. Finally the paper suggests improvements of the SSV discriminatory characteristics by using 3D facial sequences rather than 3D stills. [ABSTRACT FROM AUTHOR]

Several approaches to the separation of four stereoisomers, 1-4, of a novel, topically active, carbonic anhydrase inhibitor, 1, with two chiral centers in the molecule and four isomers, 5-8, of its chiral metabolite, 5, were evaluated. These methods include nonchiral derivatization followed by separation on chiral stationary phases (CSPs) and chiral derivatization and separation on nonchiral columns and on CSPs. Baseline separation of stereoisomers 1-4 was achieved in less than 15 min after chiral derivatization with (S)-(+)-l-(l-naphthyl)ethyl isocyanate (NEIC) and chiral chromatography on a (R)- N-(3,5-dinitrobenzoyl)phenyl glycine (DNBPG) column under normal phase (NP) conditions. Similarly, isomers 5-8 were baseline separated in less than 20 min after derivatization with NEIC and chromatography on nonchiral (nitrophenyl) and chiral [( S)-(3,5-dinitrobenzoyl)leucine; DNBL] columns in series under the same NP chromatographic conditions. Only partial separation of the diastereomeric derivatives was observed on a variety of nonchiral columns. In addition, all other direct and indirect chiral separation approaches gave only partial separation of at least two stereoisomers within the group of 1-4 or 5-8. The details of chiral separations using various methods and separation (α) and capacity factors (k′) of the derivatized isomers 1-8 on a series of chiral and nonchiral columns are presented. Using these methods, the absolute configuration of the human metabolite of 1 was established as S S ( 5), and the heat (HD) and light (LD) degradation products of 1 as R S ( 3) and S S ( 5), respectively. [ABSTRACT FROM AUTHOR]

A method for the determination of a 2-pyridinone-based specific HIV-1 reverse transcriptase inhibitor in human plasma is described. Plasma samples are extracted using phenyl solid phase extraction columns. The extract is analyzed via HPLC using a column-switching system to remove interferences from late-eluting endogenous components. Detection is based on UV absorbance at 314 nm. The assay was linear in the concentration range of 10-500 ng/ml, when 1-ml aliquots of plasma were extracted. The mean precision of the assay, expressed as the coefficient of variation, was 3.8%. The assay has been validated and utilized to support human pharmacokinetic studies. [ABSTRACT FROM AUTHOR]