University of Hertfordshire

From the same journal

By the same authors

Standard

Surface Defect Classification for Hot-Rolled Steel Strips by Selectively Dominant Local Binary Patterns. / Luo, Qiwu; Fang, Xiaoxin; Sun, Yichuang; Liu, Li; Ai, Jiaqiu; Yang, Chunhua; Simpson, Oluyomi.

In: IEEE Access, Vol. 7, 11.02.2019, p. 23488 - 23499.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Luo, Qiwu ; Fang, Xiaoxin ; Sun, Yichuang ; Liu, Li ; Ai, Jiaqiu ; Yang, Chunhua ; Simpson, Oluyomi. / Surface Defect Classification for Hot-Rolled Steel Strips by Selectively Dominant Local Binary Patterns. In: IEEE Access. 2019 ; Vol. 7. pp. 23488 - 23499.

Bibtex

@article{14aa526c38cf49558cddb742f9a0cb96,
title = "Surface Defect Classification for Hot-Rolled Steel Strips by Selectively Dominant Local Binary Patterns",
abstract = "Developments in defect descriptors and computer vision-based algorithms for automatic optical inspection (AOI) allows for further development in image-based measurements. Defect classification is a vital part of an optical-imaging-based surface quality measuring instrument. The high-speed production rhythm of hot continuous rolling requires an ultra-rapid response to every component as well as algorithms in AOI instrument. In this paper, a simple, fast, yet robust texture descriptor, namely selectively dominant local binary patterns (SDLBPs), is proposed for defect classification. First, an intelligent searching algorithm with a quantitative thresholding mechanism is built to excavate the dominant non-uniform patterns (DNUPs). Second, two convertible schemes of pattern code mapping are developed for binary encoding of all uniform patterns and DNUPs. Third, feature extraction is carried out under SDLBP framework. Finally, an adaptive region weighting method is built for further strengthening the original nearest neighbor classifier in the feature matching stage. The extensive experiments carried out on an open texture database (Outex) and an actual surface defect database (Dragon) indicates that our proposed SDLBP yields promising performance on both classification accuracy and time efficiency",
keywords = "Automatic optical inspection (AOI) image classification local binary patterns (LBP) steel industry, surface texture",
author = "Qiwu Luo and Xiaoxin Fang and Yichuang Sun and Li Liu and Jiaqiu Ai and Chunhua Yang and Oluyomi Simpson",
year = "2019",
month = "2",
day = "11",
doi = "10.1109/ACCESS.2019.2898215",
language = "English",
volume = "7",
pages = "23488 -- 23499",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - Surface Defect Classification for Hot-Rolled Steel Strips by Selectively Dominant Local Binary Patterns

AU - Luo, Qiwu

AU - Fang, Xiaoxin

AU - Sun, Yichuang

AU - Liu, Li

AU - Ai, Jiaqiu

AU - Yang, Chunhua

AU - Simpson, Oluyomi

PY - 2019/2/11

Y1 - 2019/2/11

N2 - Developments in defect descriptors and computer vision-based algorithms for automatic optical inspection (AOI) allows for further development in image-based measurements. Defect classification is a vital part of an optical-imaging-based surface quality measuring instrument. The high-speed production rhythm of hot continuous rolling requires an ultra-rapid response to every component as well as algorithms in AOI instrument. In this paper, a simple, fast, yet robust texture descriptor, namely selectively dominant local binary patterns (SDLBPs), is proposed for defect classification. First, an intelligent searching algorithm with a quantitative thresholding mechanism is built to excavate the dominant non-uniform patterns (DNUPs). Second, two convertible schemes of pattern code mapping are developed for binary encoding of all uniform patterns and DNUPs. Third, feature extraction is carried out under SDLBP framework. Finally, an adaptive region weighting method is built for further strengthening the original nearest neighbor classifier in the feature matching stage. The extensive experiments carried out on an open texture database (Outex) and an actual surface defect database (Dragon) indicates that our proposed SDLBP yields promising performance on both classification accuracy and time efficiency

AB - Developments in defect descriptors and computer vision-based algorithms for automatic optical inspection (AOI) allows for further development in image-based measurements. Defect classification is a vital part of an optical-imaging-based surface quality measuring instrument. The high-speed production rhythm of hot continuous rolling requires an ultra-rapid response to every component as well as algorithms in AOI instrument. In this paper, a simple, fast, yet robust texture descriptor, namely selectively dominant local binary patterns (SDLBPs), is proposed for defect classification. First, an intelligent searching algorithm with a quantitative thresholding mechanism is built to excavate the dominant non-uniform patterns (DNUPs). Second, two convertible schemes of pattern code mapping are developed for binary encoding of all uniform patterns and DNUPs. Third, feature extraction is carried out under SDLBP framework. Finally, an adaptive region weighting method is built for further strengthening the original nearest neighbor classifier in the feature matching stage. The extensive experiments carried out on an open texture database (Outex) and an actual surface defect database (Dragon) indicates that our proposed SDLBP yields promising performance on both classification accuracy and time efficiency

KW - Automatic optical inspection (AOI) image classification local binary patterns (LBP) steel industry

KW - surface texture

UR - http://www.scopus.com/inward/record.url?scp=85062722382&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2898215

DO - 10.1109/ACCESS.2019.2898215

M3 - Article

VL - 7

SP - 23488

EP - 23499

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -