In this paper, we study how a multidimensional local binary pattern (LBP) texture feature data can be visually explored and analyzed. The goal is to determine how true paper properties can be characterized with local texture features from visible light images. We utilize isometric feature mapping (Isomap) for the LBP texture feature data and perform non-linear dimensionality reduction for the data. These 2D projections are then visualized with original images to study data properties. Visualization is utilized in the manner of selecting texture models for unlabeled data and analyzing feature performance when building a training set for a classifier. The approach is experimented on with simulated image data illustrating different paper properties and on-line transilluminated paper images taken from a running paper web in the paper mill. The simulated image set is used to acquire quantitative figures on the performance while the analysis of real-world data is an example of semi-supervised learning.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Markus TURTINEN, Matti PIETIKAINEN, Olli SILVEN, "Visual Characterization of Paper Using Isomap and Local Binary Patterns" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 7, pp. 2076-2083, July 2006, doi: 10.1093/ietisy/e89-d.7.2076.
Abstract: In this paper, we study how a multidimensional local binary pattern (LBP) texture feature data can be visually explored and analyzed. The goal is to determine how true paper properties can be characterized with local texture features from visible light images. We utilize isometric feature mapping (Isomap) for the LBP texture feature data and perform non-linear dimensionality reduction for the data. These 2D projections are then visualized with original images to study data properties. Visualization is utilized in the manner of selecting texture models for unlabeled data and analyzing feature performance when building a training set for a classifier. The approach is experimented on with simulated image data illustrating different paper properties and on-line transilluminated paper images taken from a running paper web in the paper mill. The simulated image set is used to acquire quantitative figures on the performance while the analysis of real-world data is an example of semi-supervised learning.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2076/_p
Copy
@ARTICLE{e89-d_7_2076,
author={Markus TURTINEN, Matti PIETIKAINEN, Olli SILVEN, },
journal={IEICE TRANSACTIONS on Information},
title={Visual Characterization of Paper Using Isomap and Local Binary Patterns},
year={2006},
volume={E89-D},
number={7},
pages={2076-2083},
abstract={In this paper, we study how a multidimensional local binary pattern (LBP) texture feature data can be visually explored and analyzed. The goal is to determine how true paper properties can be characterized with local texture features from visible light images. We utilize isometric feature mapping (Isomap) for the LBP texture feature data and perform non-linear dimensionality reduction for the data. These 2D projections are then visualized with original images to study data properties. Visualization is utilized in the manner of selecting texture models for unlabeled data and analyzing feature performance when building a training set for a classifier. The approach is experimented on with simulated image data illustrating different paper properties and on-line transilluminated paper images taken from a running paper web in the paper mill. The simulated image set is used to acquire quantitative figures on the performance while the analysis of real-world data is an example of semi-supervised learning.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2076},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Visual Characterization of Paper Using Isomap and Local Binary Patterns
T2 - IEICE TRANSACTIONS on Information
SP - 2076
EP - 2083
AU - Markus TURTINEN
AU - Matti PIETIKAINEN
AU - Olli SILVEN
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2076
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - In this paper, we study how a multidimensional local binary pattern (LBP) texture feature data can be visually explored and analyzed. The goal is to determine how true paper properties can be characterized with local texture features from visible light images. We utilize isometric feature mapping (Isomap) for the LBP texture feature data and perform non-linear dimensionality reduction for the data. These 2D projections are then visualized with original images to study data properties. Visualization is utilized in the manner of selecting texture models for unlabeled data and analyzing feature performance when building a training set for a classifier. The approach is experimented on with simulated image data illustrating different paper properties and on-line transilluminated paper images taken from a running paper web in the paper mill. The simulated image set is used to acquire quantitative figures on the performance while the analysis of real-world data is an example of semi-supervised learning.
ER -