A Novel Integration of Intensity Order and Texture for Effective Feature Description

Thao-Ngoc NGUYEN; Bac LE; Kazunori MIYATA

doi:10.1587/transinf.E97.D.2021

A Novel Integration of Intensity Order and Texture for Effective Feature Description

Thao-Ngoc NGUYEN, Bac LE, Kazunori MIYATA

Full Text Views

0

Share
Cite this

Summary :

This paper introduces a novel approach of feature description by integrating the intensity order and textures in different support regions into a compact vector. We first propose the Intensity Order Local Binary Pattern (IO-LBP) operator, which simultaneously encodes the gradient and texture information in the local neighborhood of a pixel. We divide each region of interest into segments according to the order of pixel intensities, build one histogram of IO-LBP patterns for each segment, and then concatenate all histograms to obtain a feature descriptor. Furthermore, multi support regions are adopted to enhance the distinctiveness. The proposed descriptor effectively describes a region at both local and global levels, and thus high performance is expected. Experimental results on the Oxford benchmark and images of cast shadows show that our approach is invariant to common photometric and geometric transformations, such as illumination change and image rotation, and robust to complex lighting effects caused by shadows. It achieves a comparable accuracy to that of state-of-art methods while performs considerably faster.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.8 pp.2021-2029

Publication Date: 2014/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.2021

Type of Manuscript: Special Section PAPER (Special Section on Cyberworlds)

Category: Computer Vision

Authors

Thao-Ngoc NGUYEN
  Japan Advanced Institute of Science and Technology
Bac LE
  University of Science
Kazunori MIYATA
  Japan Advanced Institute of Science and Technology

Keyword

Center-Symmetric Local Binary Pattern, feature description, image matching, texture, intensity order

Cite this

Copy

Thao-Ngoc NGUYEN, Bac LE, Kazunori MIYATA, "A Novel Integration of Intensity Order and Texture for Effective Feature Description" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 8, pp. 2021-2029, August 2014, doi: 10.1587/transinf.E97.D.2021.
Abstract: This paper introduces a novel approach of feature description by integrating the intensity order and textures in different support regions into a compact vector. We first propose the Intensity Order Local Binary Pattern (IO-LBP) operator, which simultaneously encodes the gradient and texture information in the local neighborhood of a pixel. We divide each region of interest into segments according to the order of pixel intensities, build one histogram of IO-LBP patterns for each segment, and then concatenate all histograms to obtain a feature descriptor. Furthermore, multi support regions are adopted to enhance the distinctiveness. The proposed descriptor effectively describes a region at both local and global levels, and thus high performance is expected. Experimental results on the Oxford benchmark and images of cast shadows show that our approach is invariant to common photometric and geometric transformations, such as illumination change and image rotation, and robust to complex lighting effects caused by shadows. It achieves a comparable accuracy to that of state-of-art methods while performs considerably faster.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.2021/_p

Copy

@ARTICLE{e97-d_8_2021,
author={Thao-Ngoc NGUYEN, Bac LE, Kazunori MIYATA, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Integration of Intensity Order and Texture for Effective Feature Description},
year={2014},
volume={E97-D},
number={8},
pages={2021-2029},
abstract={This paper introduces a novel approach of feature description by integrating the intensity order and textures in different support regions into a compact vector. We first propose the Intensity Order Local Binary Pattern (IO-LBP) operator, which simultaneously encodes the gradient and texture information in the local neighborhood of a pixel. We divide each region of interest into segments according to the order of pixel intensities, build one histogram of IO-LBP patterns for each segment, and then concatenate all histograms to obtain a feature descriptor. Furthermore, multi support regions are adopted to enhance the distinctiveness. The proposed descriptor effectively describes a region at both local and global levels, and thus high performance is expected. Experimental results on the Oxford benchmark and images of cast shadows show that our approach is invariant to common photometric and geometric transformations, such as illumination change and image rotation, and robust to complex lighting effects caused by shadows. It achieves a comparable accuracy to that of state-of-art methods while performs considerably faster.},
keywords={},
doi={10.1587/transinf.E97.D.2021},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - A Novel Integration of Intensity Order and Texture for Effective Feature Description
T2 - IEICE TRANSACTIONS on Information
SP - 2021
EP - 2029
AU - Thao-Ngoc NGUYEN
AU - Bac LE
AU - Kazunori MIYATA
PY - 2014
DO - 10.1587/transinf.E97.D.2021
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2014
AB - This paper introduces a novel approach of feature description by integrating the intensity order and textures in different support regions into a compact vector. We first propose the Intensity Order Local Binary Pattern (IO-LBP) operator, which simultaneously encodes the gradient and texture information in the local neighborhood of a pixel. We divide each region of interest into segments according to the order of pixel intensities, build one histogram of IO-LBP patterns for each segment, and then concatenate all histograms to obtain a feature descriptor. Furthermore, multi support regions are adopted to enhance the distinctiveness. The proposed descriptor effectively describes a region at both local and global levels, and thus high performance is expected. Experimental results on the Oxford benchmark and images of cast shadows show that our approach is invariant to common photometric and geometric transformations, such as illumination change and image rotation, and robust to complex lighting effects caused by shadows. It achieves a comparable accuracy to that of state-of-art methods while performs considerably faster.
ER -