Multiple Hashing Integration for Real-Time Large Scale Part-to-Part Video Matching

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:
  • Espinosa, Silvia
  • Ordieres-Meré, Joaquín
  • Bello García, Antonio
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

Full text

[thumbnail of INVE_MEM_2013_162676.pdf]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (893kB)

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
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM