Object-level image segmentation using low level cues

Hongyuan Zhu, Jianmin Zheng, Jianfei Cai, Nadia M. Thalmann

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)

Abstract

This paper considers the problem of automatically segmenting an image into a small number of regions that correspond to objects conveying semantics or high-level structure. Although such object-level segmentation usually requires additional high-level knowledge or learning process, we explore what low level cues can produce for this purpose. Our idea is to construct a feature vector for each pixel, which elaborately integrates spectral attributes, color Gaussian mixture models, and geodesic distance, such that it encodes global color and spatial cues as well as global structure information. Then, we formulate the Potts variational model in terms of the feature vectors to provide a variational image segmentation algorithm that is performed in the feature space.We also propose a heuristic approach to automatically select the number of segments. The use of feature attributes enables the Potts model to produce regions that are coherent in color and position, comply with global structures corresponding to objects or parts of objects and meanwhile maintain a smooth and accurate boundary. We demonstrate the effectiveness of our algorithm against the stateof- the-art with the data set from the famous Berkeley benchmark.

Original languageEnglish
Pages (from-to)4019-4027
Number of pages9
JournalIEEE Transactions on Image Processing
Volume22
Issue number10
DOIs
Publication statusPublished - Oct 2013
Externally publishedYes

Keywords

  • Image segmentation
  • Low level cues
  • Object segmentation
  • Variational model

Cite this