Automatic seeded region growing for color image segmentation

Frank Y. Shih, Shouxian Cheng

Research output: Contribution to journalArticlepeer-review

342 Scopus citations


In this paper, we present an automatic seeded region growing algorithm for color image segmentation. First, the input RGB color image is transformed into YCbCr color space. Second, the initial seeds are automatically selected. Third, the color image is segmented into regions where each region corresponds to a seed. Finally, region-merging is used to merge similar or small regions. Experimental results show that our algorithm can produce good results as favorably compared to some existing algorithms.

Original languageEnglish (US)
Pages (from-to)877-886
Number of pages10
JournalImage and Vision Computing
Issue number10
StatePublished - Sep 20 2005

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition


  • Color image processing
  • Image segmentation
  • Region-merging
  • Seeded region growing


Dive into the research topics of 'Automatic seeded region growing for color image segmentation'. Together they form a unique fingerprint.

Cite this