Toward automatic undersea search using pattern recognition techniques

Thomas S Huang, R. Y. Tsai, J. K. Cheng, L. M. Buckler, H. A. Johnson

Research output: Contribution to journalArticlepeer-review


We are interested in automating search operations for man-made objects on the ocean floor. Although multiple sensors (TV, sonar, etc.) will be used eventually, we limit ourselves in this paper to optical photographs and present some results of using automatic shape analysis in distinguishing between man-made objects and empty ocean floor. The shape descriptors we use do not demand closed boundaries.

Original languageEnglish (US)
Pages (from-to)307-318
Number of pages12
JournalPattern Recognition
Issue number3
StatePublished - 1983


  • Edge extraction
  • Shape analysis
  • Undersea search
  • Underwater sensing

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Toward automatic undersea search using pattern recognition techniques'. Together they form a unique fingerprint.

Cite this