Set Of Landmark Points Research Articles

Statistical shape modeling of the left atrium from MRI of patients with atrial fibrillation

Background Atrial Fibrillation (AF) is a heart condition characterized by chaotic electrical activity and irregular contractions in the atria. AF is a progressive disease with three stages of increasing fibrillation duration and frequency: paroxysmal, persistent, and permanent. Studies show that as AF progresses, there is a significant increase in left atrial (LA) volume correlated with structural and electrical remodeling of LA tissue. While volume changes have been observed, there has been little analysis of LA shape, which could provide insight into the mechanisms behind AF. Recent literature has described algorithms for modeling anatomical shape using dense sets of landmark points on surfaces derived from MRI image segmentations. In this study, we assess the feasibility of one such method, the particle-based modeling (PBM) algorithm developed by Cates, et al. at the University of Utah, for geometric modeling and statistical comparison of LA shape in AF patients.

A template-based approach to automatic face enhancement

This paper presents Visual ENhancement of USers (VENUS), a system able to automatically enhance male and female frontal facial images exploiting a database of celebrities as reference patterns for attractiveness. Each face is represented by a set of landmark points that can be manually selected or automatically localized using active shape models. The faces can be compared remapping the landmarks by means of Catmull---Rom splines, a class of interpolating splines particularly useful to extract shape-based representations. Given the input image, its landmarks are compared against the known beauty templates and moved towards the K-nearest ones by 2D image warping. The VENUS performances have been evaluated by 20 volunteers on a set of images collected during the Festival of Creativity, held in Florence, Italy, on October 2007. The experiments show that the 73.9% of the beautified faces are more attractive than the original pictures.

Silhouetted face profiles: A new methodology for face perception research

We present a new methodology for constructing face stimuli for psychological experiments based on silhouetted face profiles. Face silhouettes carry a number of theoretical and methodological advantages compared to more complex face stimuli and lend themselves to a simple yet powerful parameterization. In five behavioral studies, we show that face silhouettes are processed like regular face stimuli: They provide enough information for accurate gender judgments (Study 1), age estimations (Study 2), and reliable and cross-valid attractiveness ratings (Study 3). Furthermore, face silhouettes elicit an inversion effect (Study 4) and allow for remarkably accurate cross-identification with front-view photographs (Study 5). We then describe a shape-based parameterization that relies on a small set of landmark points and show that face silhouettes can be effectively represented in a 20-dimensional "silhouette face space" (Study 6). We show that in this physical space, distance from the center of the space corresponds to perceived distinctiveness (Study 7), confirming a key axiom in the formulation of the face space model. Finally, we discuss straightforward applications of the face silhouette methodology and address some limitations.

Diffeomorphic statistical shape models

We describe a method of constructing parametric statistical models of shape variation which can generate continuous diffeomorphic (non-folding) deformation fields. Traditional statistical shape models are constructed by analysis of the positions of a set of landmark points. Here, we describe an algorithm which models parameters of continuous warp fields, constructed by composing simple parametric diffeomorphic warps. The warps are composed in such a way that the deformations are always defined in a reference frame. This allows the parameters controlling the deformations to be meaningfully compared from one example to another. A linear model is learnt to represent the variations in the warp parameters across the training set. This model can then be used to generalise the deformations. Models can be built either from sets of annotated points, or from unlabelled images. In the latter case, we use techniques from non-rigid registration to construct the warp fields deforming a reference image into each example. We describe the technique in detail and give examples of the resulting models.

Implicit, view invariant, linear flexible shape modelling

Flexible shape modelling in which the image of an object is represented by a finite set of landmark points is briefly reviewed. It is argued that variation in the apparent size and shape of the image of an object with change of viewpoint are extrinsic variations and that, under weak or para-perspective imaging, such changes should be taken into account by using the affine trifocal tensor to provide a mapping between image triplets. It is shown how the Procrustes error may be extended to accommodate such mappings, how the remaining intrinsic variations may be extracted, a pair of virtual basis views derived, and a statistical model constructed. An Integrated Shape and Pose Model (ISPM) that integrates a hierarchical principal components analysis model with a multi-view geometry model, was constructed and shown, on data from a small database of face images, to outperform previous models.

Functional mapping of quantitative trait loci underlying the character process: a theoretical framework.

Unlike a character measured at a finite set of landmark points, function-valued traits are those that change as a function of some independent and continuous variable. These traits, also called infinite-dimensional characters, can be described as the character process and include a number of biologically, economically, or biomedically important features, such as growth trajectories, allometric scalings, and norms of reaction. Here we present a new statistical infrastructure for mapping quantitative trait loci (QTL) underlying the character process. This strategy, termed functional mapping, integrates mathematical relationships of different traits or variables within the genetic mapping framework. Logistic mapping proposed in this article can be viewed as an example of functional mapping. Logistic mapping is based on a universal biological law that for each and every living organism growth over time follows an exponential growth curve (e.g., logistic or S-shaped). A maximum-likelihood approach based on a logistic-mixture model, implemented with the EM algorithm, is developed to provide the estimates of QTL positions, QTL effects, and other model parameters responsible for growth trajectories. Logistic mapping displays a tremendous potential to increase the power of QTL detection, the precision of parameter estimation, and the resolution of QTL localization due to the small number of parameters to be estimated, the pleiotropic effect of a QTL on growth, and/or residual correlations of growth at different ages. More importantly, logistic mapping allows for testing numerous biologically important hypotheses concerning the genetic basis of quantitative variation, thus gaining an insight into the critical role of development in shaping plant and animal evolution and domestication. The power of logistic mapping is demonstrated by an example of a forest tree, in which one QTL affecting stem growth processes is detected on a linkage group using our method, whereas it cannot be detected using current methods. The advantages of functional mapping are also discussed.

Landmark selection for cross-mapping muscle anatomy and volumetric images of the human tongue

The main objective of this work is to obtain reliable and detailed anatomical information for developing a quantitative 3-D tongue model. This work introduces a strategy for defining a set of landmark points in reference to a general 3-D representation of tongue structure. The landmarks define locations of anatomical significance that have identifiable geometric coordinates. They constitute common reference points for a mathematical mapping between any pair of data sets and indicate the anatomical correspondence, or homology, between the data sets. The integration of different data sets of the human tongue is based on this correspondence, and it is achieved by a method of nonuniform geometrical transformation (thin-plate spline mapping). We show the feasibility of these methods by mapping from muscle anatomy, according to a detailed hand-drawn dissection study [K. Miyawaki, Ann. Bul. RILP, Univ. Tokyo 8, 23–50 (1974)], against atlas images from freshly deep-frozen samples (Visible Man data) and MRI head scans of living subjects making a vowel articulatory gesture. As the result of this exercise, we have produced a tongue portion of the Visible Man data with muscle fiber direction identified. [Work supported in part by NSF grant RF 729550 and ATR/MIC Labs.]

Algorithms for automated montage synthesis of images from laser-scanning confocal microscopes

An efficient, robust, and widely-applicable technique is presented for computational synthesis of high-resolution, wide-area images of a specimen from a series of overlapping partial views. This technique can also be used to combine the results of various forms of image analysis, such as segmentation, automated cell counting, deblurring, and neuron tracing, to generate representations that are equivalent to processing the large wide-area image, rather than the individual partial views. This can be a first step towards quantitation of the higher-level tissue architecture. The computational approach overcomes mechanical limitations, such as hysterisis and backlash, of microscope stages. It also automates a procedure that is currently done manually. One application is the high-resolution visualization and/or quantitation of large batches of specimens that are much wider than the field of view of the microscope.The automated montage synthesis begins by computing a concise set of landmark points for each partial view. The type of landmarks used can vary greatly depending on the images of interest. In many cases, image analysis performed on each data set can provide useful landmarks. Even when no such “natural” landmarks are available, image processing can often provide useful landmarks.

Local transformation of facila features

This paper describes methodology for carrying out local transformations of a set of landmarkpoints describingfacialfeatures, so that they provide a good match to a given set of facial landmarkpoints: the landmark points are divided into groups of ‘similar ‘points that take facial symmetry into account, and the coordinate values of the points within each group are differentially stretched and contracted. The methodology is illustrated by application to sets of 195 facial landmark points.

Fast automated mosaic synthesis method for 2-D/3-D image analysis of specimens much wider than the field of view

We present an efficient, robust, and widely-applicable technique for computational synthesis of wide-area images from a series of overlapping partial views. The synthesized image is the set union of the areas covered by the partial views, and is called the “mosaic”. One application is the laser-scanning confocal microscopy of specimens that are much wider than the field of view of the microscope. Another is imaging of the retinal periphery using a standard fundus imager. This technique can also be used to combine the results of various forms of image analysis, such as cell counting and neuron tracing, to generate large representations that are equivalent to processing the total mosaic, rather than the individual partial views.The synthesis begins by computing a concise set of landmark points for each partial view. The type of landmarks used can vary greatly depending on the application. For instance, in the retinal imaging application, the vascular branching and crossover points are a natural choice. Likewise, the locations of cells in Figs. 1 and 2 provide a natural set of landmarks for joining these images.

Microevolution in Miocene Brizalina (Foraminifera) studied by canonical variate analysis and analysis of landmarks.

A stratigraphically oriented series of the Miocene foraminiferal species Brizalina mandoroveensis from Ikang, Cameroon, was analyzed both by conventional multivariate morphometric procedures and by the tensor biometric method of Bookstein (1986; Statist, Sci. 1, 181-142), a method which analyzes sets of landmark points rather than specific variables of shape or size. The conventional analysis used five size-measures upon 170 specimens from five stratigraphic levels; the tensor analysis encompassed six landmarks (12 coordinates) upon 50 specimens. Whereas certain features appeared in both analysis, such as the separation between levels one and five, the techniques did not always agree with respect to the interpretation of those findings or about most details in the sequence of mean phenotypes. The canonical variate analysis bases its ordination upon a general size factor (the meaning of which is obscured by the foreshortening of within-group variation which is built into the technique). The tensor analysis locates a similar ordination using mainly features of shape.