Analysis of segment statistics for semantic classification of natural images

Dejan Depalov, Thrasyvoulos N. Pappas*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

A major challenge facing content-based image retrieval is bridging the gap between low-level image primitives and high-level semantics. We have proposed a new approach for semantic image classification that utilizes the adaptive perceptual color-texture segmentation algorithm by Chen et al., which segments natural scenes into perceptually uniform regions. The color composition and spatial texture features of the regions are used as medium level descriptors, based on which the segments are classified into semantic categories. The segment features consist of spatial texture orientation information and color composition in terms of a limited number of spatially adapted dominant colors. The feature selection and the performance of the classification algorithms are based on the segment statistics. We investigate the dependence of the segment statistics on the segmentation algorithm. For this, we compare the statistics of the segment features obtained using the Chen et al. algorithm to those that correspond to human segmentations, and show that they are remarkably similar. We also show that when human segmentations are used instead of the automatically detected segments, the performance of the semantic classification approach remains approximately the same.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Human Vision and Electronic Imaging XII
DOIs
StatePublished - 2007
EventHuman Vision and Electronic Imaging XII - San Jose, CA, United States
Duration: Jan 29 2007Feb 1 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6492
ISSN (Print)0277-786X

Other

OtherHuman Vision and Electronic Imaging XII
CountryUnited States
CitySan Jose, CA
Period1/29/072/1/07

Keywords

  • Human segmentations
  • Image analysis
  • Perceptual models
  • Retrieval
  • Segmentation
  • Semantic classification

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Analysis of segment statistics for semantic classification of natural images'. Together they form a unique fingerprint.

Cite this