Sparse Pixel Vectorization: An Algorithm and Its Performance Evaluation

  • Authors:
  • Dov Dori;Wenyin Liu

  • Affiliations:
  • Technion Israel Institute of Technology, Haifa, Israel;Microsoft Research, Beijing, People's Republic of China

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 1999

Quantified Score

Hi-index 0.14

Visualization

Abstract

Accurate and efficient vectorization of line drawings is essential for their higher level processing. We present a thinningless Sparse Pixel Vectorization (SPV) algorithm. Rather than visiting all the points along the wire's black area, SPV sparsely visits selected medial axis points. The result is a crude polyline, which is refined through polygonal approximation by removing redundant points. Due to the sparseness of pixel examination and the use of a specialized data structure, SPV is both time efficient and accurate, as evaluated by our proposed performance evaluation criteria.