Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 3
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

A modification of the descriptor in a human detector using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is presented. The proposed modification requires inserting the values of average cell brightness resulting in the increase of the descriptor length from 3780 to 3908 values, but it is easy to compute and instantly gives ≈ 25% improvement of the miss rate at 10‒4 False Positives Per Window (FPPW). The modification has been tested on two versions of HOG-based descriptors: the classic Dalal-Triggs and the modified one, where, instead of spatial Gaussian masks for blocks, an additional central cell has been used. The proposed modification is suitable for hardware implementations of HOG-based detectors, enabling an increase of the detection accuracy or resignation from the use of some hardware-unfriendly operations, such as a spatial Gaussian mask. The results of testing its influence on the brightness changes of test images are also presented. The descriptor may be used in sensor networks equipped with hardware acceleration of image processing to detect humans in the images.

Go to article

Authors and Affiliations

Marek Wójcikowski
Download PDF Download RIS Download Bibtex

Abstract

Deposition defects like porosity, crack and lack of fusion in additive manufacturing process is a major obstacle to commercialization of the process. Thus, metallurgical microscopy analysis has been mainly conducted to optimize process conditions by detecting and investigating the defects. However, these defect detection methods indicate a deviation from the operator’s experience. In this study, artificial intelligence based YOLOv3 of object detection algorithm was applied to avoid the human dependency. The algorithm aims to automatically find and label the defects. To enable the aim, 80 training images and 20 verification images were prepared, and they were amplified into 640 training images and 160 verification images using augmentation algorithm of rotation, movement and scale down, randomly. To evaluate the performance of the algorithm, total loss was derived as the sum of localization loss, confidence loss, and classification loss. In the training process, the total loss was 8.672 for the initial 100 sample images. However, the total loss was reduced to 5.841 after training with additional 800 images. For the verification of the proposed method, new defect images were input and then the mean Average Precision (mAP) in terms of precision and recall was 0.3795. Therefore, the detection performance with high accuracy can be applied to industry for avoiding human errors.
Go to article

Bibliography

[1] O .H. Kwon, H.G. Kim, M.J. Ham, W.R. Kim, G.H. Kim, J.H. Cho, N.I. Kim, K.I. Kim, J. Intel. Manuf. 31, 375-386 (2020).
[2] L. Scime, J. Beuth, Addit. Manuf. 24, 273-286 (2018).
[3] L. Scime, J. Beuth, Addit. Manuf. 19, 114-126 (2018).
[4] L. Scime, J. Beuth, Addit. Manuf. 25, 151-165 (2019).
[5] L. Scime, J. Beuth, Addit. Manuf. 29, 100830, 1-9 (2019).
[6] M. Khanzadeh, W. Tian, A. Yadollahi, H.R. Doude, M.A. Tschopp, Addit. Manuf. 23, 443-456 (2018).
[7] M. Khanzadeh, S. Chowdhury, M. Marufuzzaman, M.A. Tschopp, L. Bian, J. Manuf. Syst. 47, 69-82 (2018).
[8] M. Khanzadeh, S. Chowdhury, M.A. Tschopp, H.R. Doude, M. Marufuzzaman, L. Bian, IISE Trans. 51, 5, 437-455 (2019)
[9] J . Redmon, A. Farhadi, arXiv preprint, 1804.02767 (2018).
[10] https://imageai.readthedocs.io/en/latest/
[11] https://github.com/tzutalin/labelImg
[12] http://www.image-net.org/
[13] https://imgaug.readthedocs.io/en/latest/index.html
[14] J .S. Kim, B.J. Kang, S.W. Lee, J. Mech. Sci. Technol. 33, 12, 1-7 (2019).
[15] A. Torralba, A.A. Efros, Proc. CVPR IEEE 12218709, 1521-1528 (2011).
Go to article

Authors and Affiliations

Byungjoo Choi
1
ORCID: ORCID
Yongjun Choi
1
ORCID: ORCID
Moon Gu Lee
1
ORCID: ORCID
Jung Sub Kim
2
ORCID: ORCID
Sang Won Lee
2
ORCID: ORCID
Yongho Jeon
1
ORCID: ORCID

  1. Ajou University, Department of Mechanical Engineering, 206, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi 16499, Republic of Korea
  2. Sungkyunkwan University School of Mechanical Engineering, Suwon, Republic of Korea

This page uses 'cookies'. Learn more