Rough surface classification using point statistics from photometric stereo

Gerald McGunnigle, Mike Chantler

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Rough surfaces can be classified by the point statistics of their derivative fields, estimated using photometric stereo. Such a scheme is proposed and found to be more accurate and robust than image-intensity-based classification. It is particularly effective when applied to directional surfaces, even under rotation. The scheme is therefore robust and economic - suitable for many applications and worthy of further investigation. © 2000 Elsevier Science B.V.

Original languageEnglish
Pages (from-to)593-604
Number of pages12
JournalPattern Recognition Letters
Volume21
Issue number6-7
DOIs
Publication statusPublished - Jun 2000

Keywords

  • Photometric stereo
  • Rotation invariance
  • Surface classification
  • Texture analysis

Fingerprint Dive into the research topics of 'Rough surface classification using point statistics from photometric stereo'. Together they form a unique fingerprint.

Cite this