Local pixel patterns

Fangjun Huang, Xiaochao Qu, Hyong Joong Kim, Jiwu Huang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, a new class of image texture operators is proposed. We firstly determine that the number of gray levels in each B · B subblock is a fundamental property of the local image texture. Thus, an occurrence histogram for each B · B sub-block can be utilized to describe the texture of the image. Moreover, using a new multi-bit plane strategy, i.e., representing the image texture with the occurrence histogram of the first one or more significant bit-planes of the input image, more powerful operators for describing the image texture can be obtained. The proposed approach is invariant to gray scale variations since the operators are, by definition, invariant under any monotonic transformation of the gray scale, and robust to rotation. They can also be used as supplementary operators to local binary patterns (LBP) to improve their capability to resist illuminance variation, surface transformations, etc.

Original languageEnglish
Pages (from-to)157-170
Number of pages14
JournalComputational Visual Media
Volume1
Issue number2
DOIs
Publication statusPublished - 2015 Jun 1

Fingerprint

Image texture
Pixels
Textures

Keywords

  • Gray scale
  • Multi-bit
  • Rotation
  • Texture

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Local pixel patterns. / Huang, Fangjun; Qu, Xiaochao; Kim, Hyong Joong; Huang, Jiwu.

In: Computational Visual Media, Vol. 1, No. 2, 01.06.2015, p. 157-170.

Research output: Contribution to journalArticle

Huang, F, Qu, X, Kim, HJ & Huang, J 2015, 'Local pixel patterns', Computational Visual Media, vol. 1, no. 2, pp. 157-170. https://doi.org/10.1007/s41095-015-0014-4
Huang, Fangjun ; Qu, Xiaochao ; Kim, Hyong Joong ; Huang, Jiwu. / Local pixel patterns. In: Computational Visual Media. 2015 ; Vol. 1, No. 2. pp. 157-170.
@article{c87215d7e519481ab704d95b98828e82,
title = "Local pixel patterns",
abstract = "In this paper, a new class of image texture operators is proposed. We firstly determine that the number of gray levels in each B · B subblock is a fundamental property of the local image texture. Thus, an occurrence histogram for each B · B sub-block can be utilized to describe the texture of the image. Moreover, using a new multi-bit plane strategy, i.e., representing the image texture with the occurrence histogram of the first one or more significant bit-planes of the input image, more powerful operators for describing the image texture can be obtained. The proposed approach is invariant to gray scale variations since the operators are, by definition, invariant under any monotonic transformation of the gray scale, and robust to rotation. They can also be used as supplementary operators to local binary patterns (LBP) to improve their capability to resist illuminance variation, surface transformations, etc.",
keywords = "Gray scale, Multi-bit, Rotation, Texture",
author = "Fangjun Huang and Xiaochao Qu and Kim, {Hyong Joong} and Jiwu Huang",
year = "2015",
month = "6",
day = "1",
doi = "10.1007/s41095-015-0014-4",
language = "English",
volume = "1",
pages = "157--170",
journal = "Computational Visual Media",
issn = "2096-0433",
publisher = "Tsinghua University Press",
number = "2",

}

TY - JOUR

T1 - Local pixel patterns

AU - Huang, Fangjun

AU - Qu, Xiaochao

AU - Kim, Hyong Joong

AU - Huang, Jiwu

PY - 2015/6/1

Y1 - 2015/6/1

N2 - In this paper, a new class of image texture operators is proposed. We firstly determine that the number of gray levels in each B · B subblock is a fundamental property of the local image texture. Thus, an occurrence histogram for each B · B sub-block can be utilized to describe the texture of the image. Moreover, using a new multi-bit plane strategy, i.e., representing the image texture with the occurrence histogram of the first one or more significant bit-planes of the input image, more powerful operators for describing the image texture can be obtained. The proposed approach is invariant to gray scale variations since the operators are, by definition, invariant under any monotonic transformation of the gray scale, and robust to rotation. They can also be used as supplementary operators to local binary patterns (LBP) to improve their capability to resist illuminance variation, surface transformations, etc.

AB - In this paper, a new class of image texture operators is proposed. We firstly determine that the number of gray levels in each B · B subblock is a fundamental property of the local image texture. Thus, an occurrence histogram for each B · B sub-block can be utilized to describe the texture of the image. Moreover, using a new multi-bit plane strategy, i.e., representing the image texture with the occurrence histogram of the first one or more significant bit-planes of the input image, more powerful operators for describing the image texture can be obtained. The proposed approach is invariant to gray scale variations since the operators are, by definition, invariant under any monotonic transformation of the gray scale, and robust to rotation. They can also be used as supplementary operators to local binary patterns (LBP) to improve their capability to resist illuminance variation, surface transformations, etc.

KW - Gray scale

KW - Multi-bit

KW - Rotation

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=85045090361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045090361&partnerID=8YFLogxK

U2 - 10.1007/s41095-015-0014-4

DO - 10.1007/s41095-015-0014-4

M3 - Article

VL - 1

SP - 157

EP - 170

JO - Computational Visual Media

JF - Computational Visual Media

SN - 2096-0433

IS - 2

ER -