Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Content-based filtering for fast 3D reconstruction from unstructured web-based image data

Matsatsinis Nikolaos, Doulamis, Anastasios, Marinos Ioannides, Konstantinos Makantasis

Full record


URI: http://purl.tuc.gr/dl/dias/985D713D-C71D-4E8B-B450-275EA8C1A626
Year 2014
Type of Item Conference Full Paper
License
Details
Bibliographic Citation K. Makantasis, A. Doulamis, N. Doulamis, M. Ioannides, N. Matsatsinis ," Content-based filtering for fast 3D reconstruction from unstructured web-based image data,"in 2014 5th Intern.Conf. (EuroMed) ,pp. 91-101.doi:10.1007/978-3-319-13695-0_9 https://doi.org/10.1007/978-3-319-13695-0_9
Appears in Collections

Summary

The huge amount of visual collections provides a unique opportunity for cultural heritage e-documentation and 3D reconstruction. The main difficulty, however, is its unstructured nature. In this paper a new content-based image filtering is proposed to discard image outliers that either confuse or significantly delay the 3D reconstruction process. The presented approach exploits a dense-based unsupervised paradigm applied on multi-dimensional manifolds where images are represented as image points. The multidimensional scaling algorithm is adopted to relate the space of the image distances with the space of Gram matrices to compute the image coordinates. Evaluation on a dataset of about 31,000 cultural heritage images being retrieved from internet collections with many outliers indicate the robustness and cost effectiveness of the proposed method towards an affordable 3D reconstruction.

Services

Statistics