Microscopic Local Binary Pattern for Texture Classification

Jiangping HE; Wei SONG; Hongwei JI; Xin YANG

doi:10.1587/transfun.E95.A.1587

Microscopic Local Binary Pattern for Texture Classification

Jiangping HE, Wei SONG, Hongwei JI, Xin YANG

Full Text Views

0

Share
Cite this

Summary :

This paper presents a Microscopic Local Binary Pattern (MLBP) for texture classification. The conventional LBP methods which rely on the uniform patterns discard some texture information by merging the nonuniform patterns. MLBP preserves the information by classifying the nonuniform patterns using the structure similarity at microscopic level. First, the nonuniform patterns are classified into three groups using the macroscopic information. Second, the three groups are individually divided into several subgroups based on the microscopic structure information. The experiments show that MLBP achieves a better result compared with the other LBP related methods.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E95-A No.9 pp.1587-1595

Publication Date: 2012/09/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E95.A.1587

Type of Manuscript: PAPER

Category: Image

Cite this

Copy

Jiangping HE, Wei SONG, Hongwei JI, Xin YANG, "Microscopic Local Binary Pattern for Texture Classification" in IEICE TRANSACTIONS on Fundamentals, vol. E95-A, no. 9, pp. 1587-1595, September 2012, doi: 10.1587/transfun.E95.A.1587.
Abstract: This paper presents a Microscopic Local Binary Pattern (MLBP) for texture classification. The conventional LBP methods which rely on the uniform patterns discard some texture information by merging the nonuniform patterns. MLBP preserves the information by classifying the nonuniform patterns using the structure similarity at microscopic level. First, the nonuniform patterns are classified into three groups using the macroscopic information. Second, the three groups are individually divided into several subgroups based on the microscopic structure information. The experiments show that MLBP achieves a better result compared with the other LBP related methods.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E95.A.1587/_p

Copy

@ARTICLE{e95-a_9_1587,
author={Jiangping HE, Wei SONG, Hongwei JI, Xin YANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Microscopic Local Binary Pattern for Texture Classification},
year={2012},
volume={E95-A},
number={9},
pages={1587-1595},
abstract={This paper presents a Microscopic Local Binary Pattern (MLBP) for texture classification. The conventional LBP methods which rely on the uniform patterns discard some texture information by merging the nonuniform patterns. MLBP preserves the information by classifying the nonuniform patterns using the structure similarity at microscopic level. First, the nonuniform patterns are classified into three groups using the macroscopic information. Second, the three groups are individually divided into several subgroups based on the microscopic structure information. The experiments show that MLBP achieves a better result compared with the other LBP related methods.},
keywords={},
doi={10.1587/transfun.E95.A.1587},
ISSN={1745-1337},
month={September},}

Copy

TY - JOUR
TI - Microscopic Local Binary Pattern for Texture Classification
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1587
EP - 1595
AU - Jiangping HE
AU - Wei SONG
AU - Hongwei JI
AU - Xin YANG
PY - 2012
DO - 10.1587/transfun.E95.A.1587
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E95-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2012
AB - This paper presents a Microscopic Local Binary Pattern (MLBP) for texture classification. The conventional LBP methods which rely on the uniform patterns discard some texture information by merging the nonuniform patterns. MLBP preserves the information by classifying the nonuniform patterns using the structure similarity at microscopic level. First, the nonuniform patterns are classified into three groups using the macroscopic information. Second, the three groups are individually divided into several subgroups based on the microscopic structure information. The experiments show that MLBP achieves a better result compared with the other LBP related methods.
ER -