Figure 5 - uploaded by Petros Daras
Content may be subject to copyright.
Source publication
In this paper a working multimedia asset management system is presented which provides the means for storage, annotation, retrieval and re-use of any multimedia data such as 3D objects, images, sound, video and text. The working prototype is modular, customizable, secure, offers intranet and Internet connectivity and also software inter-operability...
Contexts in source publication
Context 1
... search can be either simple, in- volving minimal description of the desired data, e.g. artifact name and type, or advanced ( Figure 5(a)). In the latter case great flexibility is given as multiple queries can been com- bined with binary operators and certain fields can be set to the desired. ...
Context 2
... the latter case great flexibility is given as multiple queries can been com- bined with binary operators and certain fields can be set to the desired. Further, a keyword type search is supported ( Figure 5(b)), which takes into consideration also the the- saurus features of the proposed system (Section 4.4). ...
Similar publications
Remote sensing (RS) image retrieval based on visual content is of great significance for geological information mining. Over the past two decades, a large amount of research on this task has been carried out, which mainly focuses on the following three core issues of image retrieval: visual feature, similarity metric and relevance feedback. Along w...
Citations
... 3D content based retrieval (3DCBR) is an advanced data indexing and management mechanism that can be used to automate the identification of shape similarities within 3D digital archives. Most of the experimental 3DCBR systems found in literature, follow the traditional thumbnail-image tiling visualization approach for presenting query results [1]- [11]. A 2D thumbnail render is used instead of the actual 3D model in order to reduce the amount of data being transferred. ...
The ongoing evolution of the Internet has enabled web applications that use real time three-dimensional (3D) graphics and virtual environments. Moreover, in recent years, cultural technology has also flourished notably. Virtual museums represent one significant application that combines culture with modern technologies and the internet, requiring an interdisciplinary approach aiming both at dissemination and education. We present our approach to enhance virtual museums by incorporating content-based retrieval that refers to 3D objects. In this context, a virtual visitor is able to navigate within the museum, examine the exhibited artifacts and perform queries-by-example in order to locate the position of related artifacts. The retrieval mechanism responds to the visitor's queries by indicating similar artifacts, which are ranked according to their similarity scores. This way, the visitor is able to navigate within a virtual museum not only by means of a virtual walkthrough but also by means of the context.
To retrieve non-rigid models and models of free-form surfaces is in actual demand, and the retrieval of 3D head models is very important in the field of entertainment, graphics design industry and medicine. Therefore, researchers are paying more attention to 3D head retrieval. This survey focuses on the relevant technique on 3D head model retrieval. Firstly, it concludes existing researches about feature extraction. Two kinds of approaches are introduced, namely common approaches and special approaches. Furthermore, special approaches are categorized into local feature based methods and global feature based methods. Secondly, the indexing technology and some prototype system are introduced. Finally, the paper performs an analysis and recommends some challenging topic.
3D models are increasing greatly, and have been used in different fields. The need of retrieving 3D models is constantly emerging. Especially, how to reduce the ‘semantic gap’ between the low-level features and high-level semantics, becomes one of the most hot topic. This paper gives a deep survey about the state of the art on semantic processing in content-based 3D model retrieval. Firstly, a framework of contend-based 3D model retrieval system integrated with high-level semantics is presented. Secondly, this paper concludes existing researches and divides the way of high-level semantic processing into three main categories: (1) using relevance feedback based on-line learning to integrate effectively users’ high level semantic knowledge; (2) using off-line machine learning methods to narrow the gap between high-level semantic knowledge and low-level object representation; (3) using object ontology to define high-level concepts. Finally, the paper recommends some challenges in this field.
