A simple and efficient video image clustering algorithm for person specific query and image retrieval

Md Shafaeat Hossain, Khandaker A. Rahman, Md Hasanuzzaman, Vir V. Phoha

Research output: Chapter in Book/Entry/PoemConference contribution

Abstract

Video image clustering is the backbone of person specific query and image retrieval from a video sequence. This paper presents a video image clustering algorithm based on the human face. Clustering in different video streams has been achieved in unsupervised manner where no prior knowledge about the input video clip is required. For face detection, multi-resolution based template matching and skin color segmentation strategies have been employed. In order to evaluate the performance of the proposed method, 11 video clips of various durations were used. Experimental results demonstrate that the performance of the method with respect to precision and recall rate are quite satisfactory and in worst case video image sequences the figures are about 83% and 79%, respectively.

Original languageEnglish (US)
Title of host publication1st International Conference on Internet Multimedia Computing and Service, ICIMCS 2009
Pages85-89
Number of pages5
DOIs
StatePublished - 2009
Externally publishedYes
Event1st International Conference on Internet Multimedia Computing and Service, ICIMCS 2009 - Kunming, Yunnan, China
Duration: Nov 23 2009Nov 25 2009

Publication series

Name1st International Conference on Internet Multimedia Computing and Service, ICIMCS 2009

Other

Other1st International Conference on Internet Multimedia Computing and Service, ICIMCS 2009
Country/TerritoryChina
CityKunming, Yunnan
Period11/23/0911/25/09

Keywords

  • Face detection
  • Mean to face image distance
  • Multi-resolution template
  • Skin area segmentation
  • Video image clustering

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'A simple and efficient video image clustering algorithm for person specific query and image retrieval'. Together they form a unique fingerprint.

Cite this