José García Rodríguez

Automatic landmarking of 2 d medical shapes using the growing neural gas network

MR Imaging techniques provide a non-invasive and accurate method for determining the ultra-structural features of human anatomy. In this study, we utilise a novel approach to segment out the ventricular system in a series of high resolution T1-weighted MR images. Our approach is based on an automated landmark extraction algorithm which automatically selects points along the contour of the ventricles from a series of 2D MRI brain images. Automated landmark extraction is accomplished through the use of the self-organising network the growing neural gas (GNG) which is able to topographically map the low dimension of the network to the high dimension of the manifold of the contour without requiring a priori knowledge of the structure of the input space. The GNG method is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and an error metric is applied to quantify the performance of our algorithm compared to the other two.

Learning 2 D hand shapes using the topology preservation model GNG

Recovering the shape of a class of objects requires establishing correct correspondences between manually or automatically annotated landmark points. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. To measure the quality of the mapping throughout the adaptation process we use the topographic product. Results are given for the training set of hand outlines.

Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2D Hand Modelling

A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network, which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. The GNG is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and results are given for the training set of hand outlines, showing that the proposed method preserves accurate models.

Geodesic Topographic Product: An Improvement to Measure Topology Preservation of Self-Organizing Neural Networks

Self-organizing neural networks endeavour to preserve the topology of an input space by means of competitive learning. There are diverse measures that allow to quantify how good is this topology preservation. However, most of them are not applicable to measure non-linear input manifolds, since they don’t consider the topology of the input space in their calculation. In this work, we have modified one of the most employed measures, the topographic product, incorporating the geodesic distance as distance measure among the reference vectors of the neurons. Thus, it is possible to use it with non-lineal input spaces. This improvement allows to extend the studies realized with the original topographic product focused to the representation of objects by means of self-organizing neural networks. It would be also useful to determine the right dimensionality that a network must have to adapt correctly to an input manifold.

A growing neural gas algorithm with applications in hand modelling and tracking

Growing models have been widely used for clustering or topology learning. Traditionally these models work on stationary environments, grow incrementally and adapt their nodes to a given distribution based on global parameters. In this paper, we present an enhanced Growing Neural Gas (GNG) model for applications in hand modelling and tracking. The modified network consists of the geometric properties of the nodes, the underline local feature of the image, and an automatic criterion for maximum node growth based on the probability of the objects in the image. We present experimental results for hands and T1-weighted MRI images, and we measure topology preservation with the topographic product.

Active -GNG: model acquisition and tracking in cluttered backgrounds

The Self-Organising Artificial Neural Network Models, of which we have used the Growing Neural Gas (GNG) can be applied to preserve the topology of an input space. Traditionally these models neither do include local adaptation of the nodes nor colour information. In this paper, we extend GNG by adding an active step to the network, which we call Active-Growing Neural Gas (A-GNG) that has both global and local properties and can track in cluttered backgrounds. The approach is novel in that the topological relations of the model are based on a number of attributes (e.g. global and local transformations, mapping function and skin colour information) which allow us to automatically model and track 2D gestures. To measure the quality of the tracked correspondences we use two interlinked topology preservation measures. Experimental results have shown better performance of our proposed method over the original GNG and the Active Contour Model.

Analysis of the Topology Preservation of Accelerated Growing Neural Gas in the Representation of Bidimensional Objects

Self-organizing neural networks endeavour to preserve the topology of an input space by means of competitive learning. This capacity is used for the representation of objects and their motion. In addition, these applications usually have real-time constraints imposed on them. This paper describes several variants of a Growing Neural Gas self-organizing network that accelerate the learning process. However, in some cases this acceleration causes a loss in topology preservation and, therefore, in the quality of the representation. Our study quantifies topology preservation using different measures to establish the most suitable learning parameters, depending on the size of the network and on the time available for adaptation.

Fast 2D/3D object representation with growing neural gas

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.

Measuring GNG topology preservation in computer vision applications

Self-organizing neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In addition, these applications usually have real-time constraints. In this work we have study a kind of self-organizing network, the Growing Neural Gas with different parameters, to represent different objects. In some cases, topology preservation is lost and, therefore, the quality of the representation. So, we have made a study to quantify topology preservation to establish the most suitable learning parameters, depending on the kind of objects to represent and the size of the network.

Object representation with self-organising networks

This paper, aims to address the ability of self-organising networks to automatically extract and correspond landmark points using only topological relations derived from competitive hebbian learning. We discuss, how the Growing Neural Gas (GNG) algorithm can be used for the automatic extraction and correspondence of nodes in a set of objects, which are then used to built statistical human brain MRI and hand gesture models.