Texture Descriptors for Automatic Classification of Surface Defects of the Hot-Rolled Steel Strip

被引:0
作者
Riego del Castillo, Virginia [1 ]
Sanchez-Gonzalez, Lidia [1 ]
Gutierrez-Fernandez, Alexis [1 ]
机构
[1] Univ Leon, Dept Ingn Mecan Informat & Aerosp, Leon 24071, Spain
来源
16TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING MODELS IN INDUSTRIAL AND ENVIRONMENTAL APPLICATIONS (SOCO 2021) | 2022年 / 1401卷
关键词
Machined parts; Steel strip; Haralick descriptors; Supervised learning;
D O I
10.1007/978-3-030-87869-6_24
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The surface of machined parts is one of the most scrutinised criteria, since it determines their machinability. In this paper, texture descriptors obtained from the Grey Level Co-ocurrence Matrix (GCLM) are used to detect and classify six different types of surface defects of hot-rolled steel strip collected in the NEU dataset. Then, the texture feature vectors are passed to multiple machine learning classifiers to determine the most appropriated one for the dataset, and it is found to be Random Forest. As the features are calculated considering multiple angles, a dimensionality reduction is developed to achieve 94.41% accuracy.
引用
收藏
页码:251 / 260
页数:10
相关论文
共 24 条
  • [21] Surface characterization of hot and cold rolled low-carbon steel strips after galvanizing and galvannealing
    de la Garza, Maribel
    Patricia Guerrero, Martha
    Zambrano, Patricia
    Colas, Rafael
    Houbaert, Yvan
    MATERIALS AND MANUFACTURING PROCESSES, 2007, 22 (03) : 323 - 327
  • [22] Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
    Li, Jiangyun
    Su, Zhenfeng
    Geng, Jiahui
    Yin, Yixin
    IFAC PAPERSONLINE, 2018, 51 (21): : 76 - 81
  • [23] Slighter Faster R-CNN for real-time detection of steel strip surface defects
    Ren, Qirui
    Geng, Jiahui
    Li, Jiangyun
    2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, : 2173 - 2178
  • [24] An End-to-End Steel Strip Surface Defects Detection Framework: Considering Complex Background Interference
    Liu, Rongqiang
    Huang, Min
    Cao, Peng
    PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 317 - 322