On-line seam detection in rolling processes using snake projection and discrete wavelet transform

Jing Li, Jtanjun Shi, Tzyy Shuh Chang

Research output: Contribution to journalArticlepeer-review

21 Scopus citations


This paper describes the development of an on-line quality inspection algorithm for detecting the surface defect "seam" generated in rolling processes. A feature-preserving "snake-projection" method is proposed for dimension reduction by converting the suspicious seam-containing images to one-dimensional sequences. Discrete wavelet transform is then performed on the sequences for feature extraction. Finally, a T 2 control chart is established based on the extracted features to distinguish real seams from false positives. The snake-projection method has two parameters that impact the effectiveness of the algorithm. Thus, selection of the parameters is discussed. Implementation of the proposed algorithm shows that it satisfies the speed and accuracy requirements for on-line seam detection.

Original languageEnglish (US)
Pages (from-to)926-933
Number of pages8
JournalJournal of Manufacturing Science and Engineering, Transactions of the ASME
Issue number5
StatePublished - Oct 2007


  • Discrete wavelet transform (DWT)
  • Feature extraction
  • Seam detection
  • T control chart

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Mechanical Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering


Dive into the research topics of 'On-line seam detection in rolling processes using snake projection and discrete wavelet transform'. Together they form a unique fingerprint.

Cite this