Feature-learning-based printed circuit board inspection via speeded-up robust features and random forest

Eun Hye Yuk, Seung Hwan Park, Cheong Sool Park, Jun-Geol Baek

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB), which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF), then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE) map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.

Original languageEnglish
Article number932
JournalApplied Sciences (Switzerland)
Volume8
Issue number6
DOIs
Publication statusPublished - 2018 Jun 5

Fingerprint

printed circuits
circuit boards
Printed circuit boards
learning
inspection
Inspection
machine learning
Defects
Learning systems
defects
products
image processing
Image processing
electronics

Keywords

  • Fault pattern learning
  • Feature extraction
  • Image inspection
  • Non-referential method
  • Weighted kernel density estimation (WKDE)

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Feature-learning-based printed circuit board inspection via speeded-up robust features and random forest. / Yuk, Eun Hye; Park, Seung Hwan; Park, Cheong Sool; Baek, Jun-Geol.

In: Applied Sciences (Switzerland), Vol. 8, No. 6, 932, 05.06.2018.

Research output: Contribution to journalArticle

@article{c7c69cafa377415898b473114a3bb686,
title = "Feature-learning-based printed circuit board inspection via speeded-up robust features and random forest",
abstract = "With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB), which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF), then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE) map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.",
keywords = "Fault pattern learning, Feature extraction, Image inspection, Non-referential method, Weighted kernel density estimation (WKDE)",
author = "Yuk, {Eun Hye} and Park, {Seung Hwan} and Park, {Cheong Sool} and Jun-Geol Baek",
year = "2018",
month = "6",
day = "5",
doi = "10.3390/app8060932",
language = "English",
volume = "8",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "6",

}

TY - JOUR

T1 - Feature-learning-based printed circuit board inspection via speeded-up robust features and random forest

AU - Yuk, Eun Hye

AU - Park, Seung Hwan

AU - Park, Cheong Sool

AU - Baek, Jun-Geol

PY - 2018/6/5

Y1 - 2018/6/5

N2 - With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB), which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF), then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE) map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.

AB - With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB), which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF), then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE) map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.

KW - Fault pattern learning

KW - Feature extraction

KW - Image inspection

KW - Non-referential method

KW - Weighted kernel density estimation (WKDE)

UR - http://www.scopus.com/inward/record.url?scp=85048107369&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048107369&partnerID=8YFLogxK

U2 - 10.3390/app8060932

DO - 10.3390/app8060932

M3 - Article

VL - 8

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 6

M1 - 932

ER -