An efficient algorithm for attention-driven image interpretation from segments

Hong Fu, Zheru Chi, Dagan Feng

Research output: Journal article publicationJournal articleAcademic researchpeer-review

13 Citations (Scopus)

Abstract

In the attention-driven image interpretation process, an image is interpreted as containing several perceptually attended objects as well as the background. The process benefits greatly a content-based image retrieval task with attentively important objects identified and emphasized. An important issue to be addressed in an attention-driven image interpretation is to reconstruct several attentive objects iteratively from the segments of an image by maximizing a global attention function. The object reconstruction is a combinational optimization problem with a complexity of 2Nwhich is computationally very expensive when the number of segments N is large. In this paper, we formulate the attention-driven image interpretation process by a matrix representation. An efficient algorithm based on the elementary transformation of matrix is proposed to reduce the computational complexity to 3 ω N (N - 1)2/ 2, where ω is the number of runs. Experimental results on both the synthetic and real data show a significantly improved processing speed with an acceptable degradation to the accuracy of object formulation.
Original languageEnglish
Pages (from-to)126-140
Number of pages15
JournalPattern Recognition
Volume42
Issue number1
DOIs
Publication statusPublished - 1 Jan 2009

Keywords

  • Computer vision
  • Content-based image retrieval
  • Image understanding
  • Region combination
  • Search optimization
  • Visual attention model

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this