Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine
In the production of cold-rolled strip, the strip surface may suffer from various defects which need to be detected and identified using an online inspection system. The system is equipped with high-speed and high-resolution cameras to acquire images from the moving strip surface. Features are then...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-03-01
|
Series: | Metals |
Subjects: | |
Online Access: | http://www.mdpi.com/2075-4701/8/3/197 |
_version_ | 1811261601097973760 |
---|---|
author | Yang Liu Ke Xu Dadong Wang |
author_facet | Yang Liu Ke Xu Dadong Wang |
author_sort | Yang Liu |
collection | DOAJ |
description | In the production of cold-rolled strip, the strip surface may suffer from various defects which need to be detected and identified using an online inspection system. The system is equipped with high-speed and high-resolution cameras to acquire images from the moving strip surface. Features are then extracted from the images and are used as inputs of a pre-trained classifier to identify the type of defect. New types of defect often appear in production. At this point the pre-trained classifier needs to be quickly retrained and deployed in seconds to meet the requirement of the online identification of all defects in the environment of a continuous production line. Therefore, the method for extracting the image features and the training for the classification model should be automated and fast enough, normally within seconds. This paper presents our findings in investigating the computational and classification performance of various feature extraction methods and classification models for the strip surface defect identification. The methods include Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF) and Local Binary Patterns (LBP). The classifiers we have assessed include Back Propagation (BP) neural network, Support Vector Machine (SVM) and Extreme Learning Machine (ELM). By comparing various combinations of different feature extraction and classification methods, our experiments show that the hybrid method of LBP for feature extraction and ELM for defect classification results in less training and identification time with higher classification accuracy, which satisfied online real-time identification. |
first_indexed | 2024-04-12T19:07:27Z |
format | Article |
id | doaj.art-149a9d874d9c4db5bbb3189ae36d6705 |
institution | Directory Open Access Journal |
issn | 2075-4701 |
language | English |
last_indexed | 2024-04-12T19:07:27Z |
publishDate | 2018-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Metals |
spelling | doaj.art-149a9d874d9c4db5bbb3189ae36d67052022-12-22T03:19:59ZengMDPI AGMetals2075-47012018-03-018319710.3390/met8030197met8030197Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning MachineYang Liu0Ke Xu1Dadong Wang2Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaCollaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaQuantitative Imaging Research Team, Data61, Commonwealth Scientific and Industrial Research Organization, Marsfield, NSW 2122, AustraliaIn the production of cold-rolled strip, the strip surface may suffer from various defects which need to be detected and identified using an online inspection system. The system is equipped with high-speed and high-resolution cameras to acquire images from the moving strip surface. Features are then extracted from the images and are used as inputs of a pre-trained classifier to identify the type of defect. New types of defect often appear in production. At this point the pre-trained classifier needs to be quickly retrained and deployed in seconds to meet the requirement of the online identification of all defects in the environment of a continuous production line. Therefore, the method for extracting the image features and the training for the classification model should be automated and fast enough, normally within seconds. This paper presents our findings in investigating the computational and classification performance of various feature extraction methods and classification models for the strip surface defect identification. The methods include Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF) and Local Binary Patterns (LBP). The classifiers we have assessed include Back Propagation (BP) neural network, Support Vector Machine (SVM) and Extreme Learning Machine (ELM). By comparing various combinations of different feature extraction and classification methods, our experiments show that the hybrid method of LBP for feature extraction and ELM for defect classification results in less training and identification time with higher classification accuracy, which satisfied online real-time identification.http://www.mdpi.com/2075-4701/8/3/197machine learningLBPELMsurface inspectiondefect identification |
spellingShingle | Yang Liu Ke Xu Dadong Wang Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine Metals machine learning LBP ELM surface inspection defect identification |
title | Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine |
title_full | Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine |
title_fullStr | Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine |
title_full_unstemmed | Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine |
title_short | Online Surface Defect Identification of Cold Rolled Strips Based on Local Binary Pattern and Extreme Learning Machine |
title_sort | online surface defect identification of cold rolled strips based on local binary pattern and extreme learning machine |
topic | machine learning LBP ELM surface inspection defect identification |
url | http://www.mdpi.com/2075-4701/8/3/197 |
work_keys_str_mv | AT yangliu onlinesurfacedefectidentificationofcoldrolledstripsbasedonlocalbinarypatternandextremelearningmachine AT kexu onlinesurfacedefectidentificationofcoldrolledstripsbasedonlocalbinarypatternandextremelearningmachine AT dadongwang onlinesurfacedefectidentificationofcoldrolledstripsbasedonlocalbinarypatternandextremelearningmachine |