Polarization Thermal Image Segmentation Algorithm of Metal Fatigue Based on Gray Level and Information Entropy Fusion

Ruhai Zhao; Fangbin Wang

doi:10.3788/LOP202158.2410012

Laser & Optoelectronics Progress, Volume. 58, Issue 24, 2410012(2021)

Polarization Thermal Image Segmentation Algorithm of Metal Fatigue Based on Gray Level and Information Entropy Fusion

Ruhai Zhao^1,2、* and Fangbin Wang^1,2,3

Author Affiliations

¹School of Mechanical and Electrical Engineering, Anhui Jianzhu University, Hefei, Anhui 230601, China

²Key Laboratory of Construction Machinery Fault Diagnosis and Early Warning Technology, Anhui Jianzhu University, Hefei, Anhui 230601, China

³Key Laboratory of Intelligent Manufacturing of Construction Machinery, Anhui Jianzhu University, Hefei, Anhui 230601, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(15)

Fig. 1. Infrared polarization information images. (a) 0° azimuth image; (b) 60° azimuth image; (c) 120° azimuth image; (d) s₀ image; (e) s₁ image; (f) s₂ image; (g) DOP image; (h) AOP image

Download full size

Fig. 2. Process of searching potential target regions. (a) Fusion results of multi azimuth image gray level and information entropy; (b) potential target region images

Download full size

Fig. 3. Simulation segmentation results of 0°, 60°, 120° azimuth images

Download full size

Fig. 4. Flow chart of multi-channel infrared polarized thermal image overall segmentation

Download full size

Fig. 5. Specimen size

Download full size

Fig. 6. Original images

Download full size

Fig. 7. Process of multi-channel segmentation with fatigue cycle of 1000 times

Download full size

Fig. 8. Process of multi-channel segmentation with fatigue cycle of 8000 times

Download full size

Fig. 9. Process of multi-channel segmentation with fatigue cycle of 14000 times

Download full size

Fig. 10. Comparison of segmentation results of different algorithms

Download full size

Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times
View table
Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times
Parameter 0° 60° 120°
$\overset{̅}{G}$ 157 150 142
H 380.0 331.1 336.6
E_max 411.2 363.4 365.2
ρ -9.8788×10^-5 -4.2433×10^-4 -8.7336×10^-4

Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times
View table
Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times
Parameter 0° 60° 120°
$\overset{̅}{G}$ 158 147 138
H 406.8 384.5 382.5
E_max 436.4 411.6 406.5
ρ -2.3927×10^-4 -2.6528×10^-4 -6.1364×10^-4

Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000
View table
Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000
Parameter 0° 60° 120°
$\overset{̅}{G}$ 154 144 136
H 430.8 423.9 400.4
E_max 433.4 447.7 422.8
ρ -6.5729×10^-5 -1.7110×10^-4 -5.6997×10^-4

Table 4. GLC of different algorithms unit: %
View table
Table 4. GLC of different algorithms unit: %
Algorithm 1000 times 8000 times 14000 times
FCM 13.09 23.17 31.85
OTSU 14.82 31.57 36.07
MEM 38.06 30.14 36.29
Proposed algorithm 40.94 46.47 48.82

Table 5. δ_R of different algorithms unit: %
View table
Table 5. δ_R of different algorithms unit: %
Algorithm 1000 times 8000 times 14000 times
FCM 96.69 95.65 94.83
OTSU 96.34 94.17 93.66
MEM 63.51 93.59 93.66
Proposed algorithm 25.17 3.48 6.31

Tools

Get Citation

Copy Citation Text

Ruhai Zhao, Fangbin Wang. Polarization Thermal Image Segmentation Algorithm of Metal Fatigue Based on Gray Level and Information Entropy Fusion[J]. Laser & Optoelectronics Progress, 2021, 58(24): 2410012

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: May. 12, 2021

Accepted: Jun. 27, 2021

Published Online: Dec. 1, 2021

The Author Email: Ruhai Zhao (zhaoruhai@ahjzu.edu.cn)

DOI:10.3788/LOP202158.2410012

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times

Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times

Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times

Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times

Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000

Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000

Table 4. GLC of different algorithms unit: %

Table 4. GLC of different algorithms unit: %

Table 5. δ_R of different algorithms unit: %

Table 5. δ_R of different algorithms unit: %

Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times

Table 1. Some parameters and calculation results of potential target region at fatigue cycle of 1000 times

Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times

Table 2. Some parameters and calculation results of potential target region at fatigue cycle of 8000 times

Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000

Table 3. Some parameters and calculation results of potential target region at fatigue cycle 14000

Table 4. GLC of different algorithms unit: %

Table 4. GLC of different algorithms unit: %

Table 5. δR of different algorithms unit: %

Table 5. δR of different algorithms unit: %

Table 5. δ_R of different algorithms unit: %

Table 5. δ_R of different algorithms unit: %