Learning 2D Hand Shapes Using the Topology Preservation Model GNG
نویسندگان
چکیده
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.
منابع مشابه
Automatically Building 2D Statistical Shapes Using the Topology Preservation Model GNG
Image segmentation is very important in computer based image interpretation and it involves the labeling of the image so that the labels correspond to real world objects. In this study, we utilise a novel approach to automatically segment out the ventricular system from a series of MR brain images and to recover the shape of hand outlines from a series of 2D training images. Automated landmark ...
متن کاملAutomatic landmark extraction using Growing Neural Gas (GNG)
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 method, landmark extraction is achieved using a self-organising neural network, the Growing Neural Gas (GNG), which is used to preserve the topology of any input space. Using GNG, the topological relations of a given set of deformable shapes can be le...
متن کاملVisual Surveillance of Objects Motion Using GNG
Self-organising neural networks preserves the topology of an input space by using their competitive learning. In this work we use a kind of self-organising network, the Growing Neural Gas, to represent non rigid objects as a result of an adaptive process by a topology-preserving graph that constitutes an induced Delaunay triangulation of their shapes. The neural network is used to build a syste...
متن کاملTowards Coherent Image Space Stylization of Animated 3D Shapes
We describe a rendering technique for creating animations of 3D shapes in a range of non-photorealistic styles based on 2D patterns that resemble hand-made drawings, prints, and paintings. Producing 3D animations of such styles presents a challenge: ensuring that the 2D patterns follow 3D motions while preserving their 2D appearance are conflicting goals. Our solution is to use texture synthesi...
متن کاملDAMAGE IDENTIFICATION BY USING MODAL EXPANSION AND TOPOLOGY OPTIMIZATION IN THREE DIMENSIONAL ELASTICITY PROBLEMS
In this paper, topology optimization is utilized for damage detection in three dimensional elasticity problems. In addition, two mode expansion techniques are used to derive unknown modal data from measured data identified by installed sensors. Damages in the model are assumed as reduction of mass and stiffness in the discretized finite elements. The Solid Isotropic Material with Penalization (...
متن کامل