DMCA
Inference of segmented color and texture description by tensor voting (2004)
| Venue: | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
| Citations: | 25 - 2 self |
BibTeX
@ARTICLE{Jia04inferenceof,
author = {Jiaya Jia and Chi-keung Tang},
title = {Inference of segmented color and texture description by tensor voting},
journal = {IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE},
year = {2004},
volume = {26},
number = {6},
pages = {771--786}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A robust synthesis method is proposed to automatically infer missing color and texture information from a damaged 2D image by ND 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 ND tensor, followed by a voting process that infers noniteratively the optimal color values in the ND 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 ND 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.
Keyphrases
tensor voting texture description texture information segmented color nd tensor voting difficult input robust synthesis method tensor voting approach complete segmentation index term image restoration two-step method voting process adaptive nd tensor optimal color value nd texture space insufficient geometry tensor scale analysis partitioning boundary different feature scale
