The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
3D objects learning is a challenging problem in computer vision and digital multimedia due to the wide development of 3D objects scanning technology. Nevertheless, using machine learning for solving such problems is a potential and effective tool. In this paper, we propose a novel approach for 3D objects labeling, it relies on a multi-class boosting algorithm to train the labeling function and spectral...
Machine learning has recently become an interesting research field in 3D objects preprocessing. However, few algorithms using this automatic technique have been proposed to learn 3D objects parts. The aim of this paper is to present two simple and efficient approaches to learn parts of a 3D object. These approaches use Bagging or multiclass Boosting algorithms and the Shape Spectrum Descriptor (SSD)...
In this paper, we propose a new approach to get the optimal segmentation of a 3D mesh as a human can perceive using the minima rule and spectral clustering. This method is fully unsupervised and provides a hierarchical segmentation via recursive cuts. We introduce a new concept of the adjacency matrix based on cognitive studies. We also introduce the use of one-spectral clustering which leads to the...
3D retrieval has become an important field for applications that require 3D databases. Several descriptors have been defined in the past, most of them are based on the global geometric signature of the 3D objects and only a few of them allow a partial matching using segments of a 3D object as queries. In this paper, we propose to improve the results of global indexing by combining the partial signatures...
Three-dimensional models are more and more used in applications in which the necessity to visualize realistic objects is felt (CAD/CAO, medical simulations, games, virtual reality etc.). Consequently, the management of large sizes of 3D data collections becomes an important field. The indexation of such data allows a designer for instance to easily find similar data — in a visual or semantic sense...
The watershed transformation is a useful tool for the 3D segmentation. However, over segmentation have become the key problems for the conventional algorithm. This paper presents two new methods for solving these problems. The first method is to establish a generic-adjacencies graph of regions resulting from the application of watershed segmentation and to merge these regions according to a criterion...
This paper presents a new classification and search method of 3D object features views. This method is an application of algorithms: 1) Charm for an object views classification purpose 2) Algorithm for extracting association rules in order to extract the characteristic view. We use the geometric descriptor of Zernike Moments to index 2D views of 3D object. The proposed method relies on a Bayesian...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.