Web-scale computer vision using MapReduce for multimedia data mining

Brandyn White, Tom Yeh, Jimmy Lin, Larry Davis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

65 Scopus citations

Abstract

This work explores computer vision applications of the Map-Reduce framework that are relevant to the data mining community. An overview of MapReduce and common design patterns are provided for those with limited MapReduce background. We discuss both the high level theory and the low level implementation for several computer vision algorithms: classifier training, sliding windows, clustering, bag-of-features, background subtraction, and image registration. Experimental results for the k-means clustering and single Gaussian background subtraction algorithms are performed on a 410 node Hadoop cluster.

Original languageEnglish
Title of host publicationProceedings of the 10th International Workshop on Multimedia Data Mining, MDMKDD '10
DOIs
StatePublished - 2010
Event10th International Workshop on Multimedia Data Mining, MDMKDD '10 - Washington, DC, United States
Duration: 25 Jul 201025 Jul 2010

Publication series

NameProceedings of the 10th International Workshop on Multimedia Data Mining, MDMKDD '10

Conference

Conference10th International Workshop on Multimedia Data Mining, MDMKDD '10
Country/TerritoryUnited States
CityWashington, DC
Period25/07/1025/07/10

Keywords

  • Background subtraction
  • Bag-of-features
  • Cloud computing
  • Clustering
  • Computer vision
  • Image registration
  • MapReduce

Fingerprint

Dive into the research topics of 'Web-scale computer vision using MapReduce for multimedia data mining'. Together they form a unique fingerprint.

Cite this