Nicole M. Artner

Comparison of three-dimensional surface-imaging systems

BACKGROUND In recent decades, three-dimensional (3D) surface-imaging technologies have gained popularity worldwide, but because most published articles that mention them are technical, clinicians often have difficulties gaining a proper understanding of them. This article aims to provide the reader with relevant information on 3D surface-imaging systems. In it, we compare the most recent technologies to reveal their differences. METHODS We have accessed five international companies with the latest technologies in 3D surface-imaging systems: 3dMD, Axisthree, Canfield, Crisalix and Dimensional Imaging (Di3D; in alphabetical order). We evaluated their technical equipment, independent validation studies and corporate backgrounds. RESULTS The fastest capturing devices are the 3dMD and Di3D systems, capable of capturing images within 1.5 and 1 ms, respectively. All companies provide software for tissue modifications. Additionally, 3dMD, Canfield and Di3D can fuse computed tomography (CT)/cone-beam computed tomography (CBCT) images into their 3D surface-imaging data. 3dMD and Di3D provide 4D capture systems, which allow capturing the movement of a 3D surface over time. Crisalix greatly differs from the other four systems as it is purely web based and realised via cloud computing. CONCLUSION 3D surface-imaging systems are becoming important in todays plastic surgical set-ups, taking surgeons to a new level of communication with patients, surgical planning and outcome evaluation. Technologies used in 3D surface-imaging systems and their intended field of application vary within the companies evaluated. Potential users should define their requirements and assignment of 3D surface-imaging systems in their clinical as research environment before making the final decision for purchase.

Matching 2D and 3D articulated shapes using the eccentricity transform

This paper presents a novel method for 2D and 3D shape matching that is insensitive to articulation. It uses the eccentricity transform, which is based on the computation of geodesic distances. Geodesic distances computed over a 2D or 3D shape are articulation insensitive. The eccentricity transform considers the length of the longest geodesics. Histograms of the eccentricity transform characterize the compactness of a shape, in a way insensitive to rotation, scaling, and articulation. To characterize the structure of a shape, a histogram of the connected components of the level-sets of the transform is used. These two histograms make up a highly compact descriptor and the resulting method for shape matching is straightforward. Experimental results on established 2D and 3D benchmarks show results similar to more complex state of the art methods, especially when considering articulation. The connection between the geometrical modification of a shape and the corresponding impact on its histogram representation is explained. The influence of the number of bins in the two histograms and the respective importance of each histogram is studied in detail.

Evolution of the 3-dimensional video system for facial motion analysis: ten years' experiences and recent developments.

AbstractSince the implementation of the computer-aided system for assessing facial palsy in 1999 by Frey et al (Plast Reconstr Surg. 1999;104:2032–2039), no similar system that can make an objective, three-dimensional, quantitative analysis of facial movements has been marketed.This system has been in routine use since its launch, and it has proven to be reliable, clinically applicable, and therapeutically accurate. With the cooperation of international partners, more than 200 patients were analyzed. Recent developments in computer vision—mostly in the area of generative face models, applying active-appearance models (and extensions), optical flow, and video-tracking—have been successfully incorporated to automate the prototype system.Further market-ready development and a business partner will be needed to enable the production of this system to enhance clinical methodology in diagnostic and prognostic accuracy as a personalized therapy concept, leading to better results and higher quality of life for patients with impaired facial function.

3D shape matching by geodesic eccentricity

This paper makes use of the continuous eccentricity transform to perform 3D shape matching. The eccentricity transform has already been proved useful in a discrete graph-theoretic setting and has been applied to 2D shape matching. We show how these ideas extend to higher dimensions. The eccentricity transform is used to compute descriptors for 3D shapes. These descriptors are defined as histograms of the eccentricity transform and are naturally invariant to Euclidean motion and articulation. They show promising results for shape discrimination.

Multi-scale 2D tracking of articulated objects using hierarchical spring systems

This paper presents a flexible framework to build a target-specific, part-based representation for arbitrary articulated or rigid objects. The aim is to successfully track the target object in 2D, through multiple scales and occlusions. This is realized by employing a hierarchical, iterative optimization process on the proposed representation of structure and appearance. Therefore, each rigid part of an object is described by a hierarchical spring system represented by an attributed graph pyramid. Hierarchical spring systems encode the spatial relationships of the features (attributes of the graph pyramid) describing the parts and enforce them by spring-like behavior during tracking. Articulation points connecting the parts of the object allow to transfer position information from reliable to ambiguous parts. Tracking is done in an iterative process by combining the hypotheses of simple trackers with the hypotheses extracted from the hierarchical spring systems.

Rigid Part Decomposition in a Graph Pyramid

This paper presents an approach to extract the rigid parts of an observed articulated object. First, a spatio-temporal filtering in a video selects interest points that correspond to rigid parts. This selection is driven by the spatial relationships and the movement of the interest points. Then, a graph pyramid is built, guided by the orientation changes of the object parts in the scene. This leads to a decomposition of the scene into its rigid parts. Each vertex in the top level of the pyramid represents one rigid part in the scene.

Tracking Objects beyond Rigid Motion

Tracking multiple features of a rigid or an articulated object, without considering the underlying structure, becomes ambiguous if the target model (for example color histograms) is similar to other nearby regions or to the background. Instead of tracking multiple features independently, we propose an approach that integrates the underlying structure into the tracking process using an attributed graph. The independent tracking processes are driven to a solution that satisfies the visual as well as the structural constraints. An approach for rigid objects is presented and extended to handle articulated objects consisting of rigid parts. Experimental results on real and synthetic videos show promising results in scenes with considerable amount of occlusion.

Video Object Segmentation Using Graphs

This paper presents an approach for video object segmentation. The main idea of our approach is to generate a planar, triangulated, and labeled graph that describes the scene, foreground objects and background. With the help of the Kanade-Lucas-Tomasi Tracker, corner points are tracked within a video sequence. Then the movement of the points adaptively generates a planar triangulation. The triangles are labeled as rigid, articulated, and separatingdepending on the variation of the length of their edges.

Convex Deficiencies for Human Action Recognition

A human action can be identified by visualizing the sequence of 2D binary projections over time. Here, one of the most representative features is shape and a wide range of algorithms have been proposed using its descriptors. This paper proposes convex deficiencies, the difference between an object and its convex hull, to be considered as a representation for the human action classification problem. A simple description using the centroids of the convex deficiencies over time is presented. Recognition of human actions is done with a fast matching algorithm that considers the spatial distribution of the centroid trajectories and the shape of the clusters in its 2D projection. The proposed representation is robust to deformations, scale, speed of the performed action and to the starting point of the movement sequence. Experiments using the videos of the Weizmann database show promising results demonstrating the effectiveness of the proposed methodology in classifying simple human actions, e.g. walking and running. The new proposed methodology should be extendable to a broader set of actions.

On the Evaluation of Graph Centrality for Shape Matching

Graph centrality has been extensively applied in Social Network Analysis to model the interaction of actors and the information flow inside a graph. In this paper, we investigate the usage of graph centralities in the Shape Matching task. We create a graph-based representation of a shape and describe this graph by using different centrality measures. We build a Naive Bayes classifier whose input feature vector consists of the measurements obtained by the centralities and evaluate the different performances for each centrality.