Full text
![[thumbnail of INVE_MEM_2013_162676.pdf]](https://oa.upm.es/style/images/fileicons/application_pdf.png) Preview |
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (893kB) |
Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching
Citation
Espinosa, Silvia and Ordieres-Meré, Joaquín and Bello García, Antonio (2013). Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching. In: "VII Simposio Teoría y Aplicaciones de Minería de Datos (TAMIDA 2013) . IV Congreso Nacional de Informática. CEDI 2013", 17/09/2014 - 20/09/2014, Madrid, España. ISBN 978-84-695-8348-7. pp. 1437-1446.
Description
| Title: | Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching |
|---|---|
| Author/s: |
|
| Item Type: | Presentation at Congress or Conference (Article) |
| Event Title: | VII Simposio Teoría y Aplicaciones de Minería de Datos (TAMIDA 2013) . IV Congreso Nacional de Informática. CEDI 2013 |
| Event Dates: | 17/09/2014 - 20/09/2014 |
| Event Location: | Madrid, España |
| Title of Book: | Multiconferencia CAEPIA'13 |
| Date: | 2013 |
| ISBN: | 978-84-695-8348-7 |
| Subjects: | |
| Freetext Keywords: | video retrieval, pattern recognition, motion, distortion, hashing, data mining |
| Faculty: | E.T.S.I. Industriales (UPM) |
| Department: | Ingeniería de Organización, Administración de Empresas y Estadística |
| Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
Abstract
A real-time large scale part-to-part video matching algorithm, based on the cross correlation of the intensity of motion curves, is proposed with a view to originality recognition, video database cleansing, copyright enforcement, video tagging or video result re-ranking. Moreover, it is suggested how the most representative hashes and distance functions - strada, discrete cosine transformation, Marr-Hildreth and radial - should be integrated in order for the matching algorithm to be
invariant against blur, compression and rotation distortions: (R; _) 2 [1; 20]_[1; 8], from 512_512 to 32_32pixels2 and from 10 to 180_. The DCT hash is invariant against blur and compression up to 64x64 pixels2.
Nevertheless, although its performance against rotation is the best, with a success up to 70%, it should be combined with the Marr-Hildreth distance function. With the latter, the image selected by the DCT hash should be at a distance lower than 1.15 times the Marr-Hildreth minimum
distance.
More information
| Item ID: | 26118 |
|---|---|
| DC Identifier: | https://oa.upm.es/26118/ |
| OAI Identifier: | oai:oa.upm.es:26118 |
| Official URL: | http://www.congresocedi.es/images/site/actas/Actas... |
| Deposited by: | Memoria Investigacion |
| Deposited on: | 14 May 2015 17:17 |
| Last Modified: | 23 Apr 2018 07:49 |
