Inference of Segmented Color and Texture Description by Tensor Voting

  • Authors:
  • Jiaya Jia;Chi-Keung Tang

  • Affiliations:
  • -;-

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2004

Quantified Score

Hi-index 0.14

Visualization

Abstract

Abstract--A robust synthesis method is proposed to automatically infer missing color and texture information from a damaged 2D image by N\rm D tensor voting (N 3). The same approach is generalized to range and 3D data in the presence of occlusion, missing data and noise. Our method translates texture information into an adaptive N\rm D tensor, followed by a voting process that infers noniteratively the optimal color values in the N\rm D texture space. A two-step method is proposed. First, we perform segmentation based on insufficient geometry, color, and texture information in the input, and extrapolate partitioning boundaries by either 2D or 3D tensor voting to generate a complete segmentation for the input. Missing colors are synthesized using N\rm D tensor voting in each segment. Different feature scales in the input are automatically adapted by our tensor scale analysis. Results on a variety of difficult inputs demonstrate the effectiveness of our tensor voting approach.